Google Git
Sign in
apache / madlib-site / 1b386479a81f3b2a9e92716cdb3e5819e277191c / . / community-artifacts / Deep-learning / Train-multiple-models / AutoML-MLP-v1.ipynb
blob: c679b3c79b787aad1e4f4c0024ba51cb7f57e17a [file] [log] [blame]
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# AutoML for Multilayer Perceptron\n",
"\n",
"E2E classification example using autoML methods for optimizing hyperparameters and model architectures.\n",
"\n",
"Deep learning works best on very large datasets, but that is not convenient for a quick introduction to the syntax. So in this workbook we use the well known iris data set from https://archive.ics.uci.edu/ml/datasets/iris to help get you started. It is similar to the example in user docs http://madlib.apache.org/docs/latest/index.html\n",
"\n",
"For more realistic examples please refer to the deep learning notebooks at\n",
"https://github.com/apache/madlib-site/tree/asf-site/community-artifacts\n",
"\n",
"## Table of contents\n",
"\n",
"<a href=\"#create_input_data\">1. Create input data</a>\n",
"\n",
"<a href=\"#pp\">2. Call preprocessor for deep learning</a>\n",
"\n",
"<a href=\"#load\">3. Define and load model architecture</a>\n",
"\n",
"<a href=\"#hyperband\">4. Hyperband</a>\n",
"\n",
"<a href=\"#hyperopt\">5. Hyperopt</a>\n",
"\n",
"<a href=\"#pred\">6. Predict</a>"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"scrolled": false
},
"outputs": [],
"source": [
"%load_ext sql"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"# Greenplum Database 5.x on GCP (PM demo machine) - via tunnel\n",
"%sql postgresql://gpadmin@localhost:8000/madlib\n",
" \n",
"# PostgreSQL local\n",
"#%sql postgresql://fmcquillan@localhost:5432/madlib"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"1 rows affected.\n"
]
},
{
"data": {
"text/html": [
"<table>\n",
" <tr>\n",
" <th>version</th>\n",
" </tr>\n",
" <tr>\n",
" <td>MADlib version: 1.18.0-dev, git revision: rel/v1.17.0-89-g14a91ce, cmake configuration time: Fri Mar 5 23:08:38 UTC 2021, build type: release, build system: Linux-3.10.0-1160.11.1.el7.x86_64, C compiler: gcc 4.8.5, C++ compiler: g++ 4.8.5</td>\n",
" </tr>\n",
"</table>"
],
"text/plain": [
"[(u'MADlib version: 1.18.0-dev, git revision: rel/v1.17.0-89-g14a91ce, cmake configuration time: Fri Mar 5 23:08:38 UTC 2021, build type: release, build system: Linux-3.10.0-1160.11.1.el7.x86_64, C compiler: gcc 4.8.5, C++ compiler: g++ 4.8.5',)]"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"%sql select madlib.version();\n",
"#%sql select version();"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"<a id=\"class\"></a>\n",
"# Classification\n",
"\n",
"<a id=\"create_input_data\"></a>\n",
"# 1. Create input data\n",
"\n",
"Load iris data set."
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Done.\n",
"Done.\n",
"150 rows affected.\n",
"150 rows affected.\n"
]
},
{
"data": {
"text/html": [
"<table>\n",
" <tr>\n",
" <th>id</th>\n",
" <th>attributes</th>\n",
" <th>class_text</th>\n",
" </tr>\n",
" <tr>\n",
" <td>1</td>\n",
" <td>[Decimal('5.1'), Decimal('3.5'), Decimal('1.4'), Decimal('0.2')]</td>\n",
" <td>Iris-setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <td>2</td>\n",
" <td>[Decimal('4.9'), Decimal('3.0'), Decimal('1.4'), Decimal('0.2')]</td>\n",
" <td>Iris-setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <td>3</td>\n",
" <td>[Decimal('4.7'), Decimal('3.2'), Decimal('1.3'), Decimal('0.2')]</td>\n",
" <td>Iris-setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <td>4</td>\n",
" <td>[Decimal('4.6'), Decimal('3.1'), Decimal('1.5'), Decimal('0.2')]</td>\n",
" <td>Iris-setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <td>5</td>\n",
" <td>[Decimal('5.0'), Decimal('3.6'), Decimal('1.4'), Decimal('0.2')]</td>\n",
" <td>Iris-setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <td>6</td>\n",
" <td>[Decimal('5.4'), Decimal('3.9'), Decimal('1.7'), Decimal('0.4')]</td>\n",
" <td>Iris-setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <td>7</td>\n",
" <td>[Decimal('4.6'), Decimal('3.4'), Decimal('1.4'), Decimal('0.3')]</td>\n",
" <td>Iris-setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <td>8</td>\n",
" <td>[Decimal('5.0'), Decimal('3.4'), Decimal('1.5'), Decimal('0.2')]</td>\n",
" <td>Iris-setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <td>9</td>\n",
" <td>[Decimal('4.4'), Decimal('2.9'), Decimal('1.4'), Decimal('0.2')]</td>\n",
" <td>Iris-setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <td>10</td>\n",
" <td>[Decimal('4.9'), Decimal('3.1'), Decimal('1.5'), Decimal('0.1')]</td>\n",
" <td>Iris-setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <td>11</td>\n",
" <td>[Decimal('5.4'), Decimal('3.7'), Decimal('1.5'), Decimal('0.2')]</td>\n",
" <td>Iris-setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <td>12</td>\n",
" <td>[Decimal('4.8'), Decimal('3.4'), Decimal('1.6'), Decimal('0.2')]</td>\n",
" <td>Iris-setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <td>13</td>\n",
" <td>[Decimal('4.8'), Decimal('3.0'), Decimal('1.4'), Decimal('0.1')]</td>\n",
" <td>Iris-setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <td>14</td>\n",
" <td>[Decimal('4.3'), Decimal('3.0'), Decimal('1.1'), Decimal('0.1')]</td>\n",
" <td>Iris-setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <td>15</td>\n",
" <td>[Decimal('5.8'), Decimal('4.0'), Decimal('1.2'), Decimal('0.2')]</td>\n",
" <td>Iris-setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <td>16</td>\n",
" <td>[Decimal('5.7'), Decimal('4.4'), Decimal('1.5'), Decimal('0.4')]</td>\n",
" <td>Iris-setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <td>17</td>\n",
" <td>[Decimal('5.4'), Decimal('3.9'), Decimal('1.3'), Decimal('0.4')]</td>\n",
" <td>Iris-setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <td>18</td>\n",
" <td>[Decimal('5.1'), Decimal('3.5'), Decimal('1.4'), Decimal('0.3')]</td>\n",
" <td>Iris-setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <td>19</td>\n",
" <td>[Decimal('5.7'), Decimal('3.8'), Decimal('1.7'), Decimal('0.3')]</td>\n",
" <td>Iris-setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <td>20</td>\n",
" <td>[Decimal('5.1'), Decimal('3.8'), Decimal('1.5'), Decimal('0.3')]</td>\n",
" <td>Iris-setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <td>21</td>\n",
" <td>[Decimal('5.4'), Decimal('3.4'), Decimal('1.7'), Decimal('0.2')]</td>\n",
" <td>Iris-setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <td>22</td>\n",
" <td>[Decimal('5.1'), Decimal('3.7'), Decimal('1.5'), Decimal('0.4')]</td>\n",
" <td>Iris-setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <td>23</td>\n",
" <td>[Decimal('4.6'), Decimal('3.6'), Decimal('1.0'), Decimal('0.2')]</td>\n",
" <td>Iris-setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <td>24</td>\n",
" <td>[Decimal('5.1'), Decimal('3.3'), Decimal('1.7'), Decimal('0.5')]</td>\n",
" <td>Iris-setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <td>25</td>\n",
" <td>[Decimal('4.8'), Decimal('3.4'), Decimal('1.9'), Decimal('0.2')]</td>\n",
" <td>Iris-setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <td>26</td>\n",
" <td>[Decimal('5.0'), Decimal('3.0'), Decimal('1.6'), Decimal('0.2')]</td>\n",
" <td>Iris-setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <td>27</td>\n",
" <td>[Decimal('5.0'), Decimal('3.4'), Decimal('1.6'), Decimal('0.4')]</td>\n",
" <td>Iris-setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <td>28</td>\n",
" <td>[Decimal('5.2'), Decimal('3.5'), Decimal('1.5'), Decimal('0.2')]</td>\n",
" <td>Iris-setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <td>29</td>\n",
" <td>[Decimal('5.2'), Decimal('3.4'), Decimal('1.4'), Decimal('0.2')]</td>\n",
" <td>Iris-setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <td>30</td>\n",
" <td>[Decimal('4.7'), Decimal('3.2'), Decimal('1.6'), Decimal('0.2')]</td>\n",
" <td>Iris-setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <td>31</td>\n",
" <td>[Decimal('4.8'), Decimal('3.1'), Decimal('1.6'), Decimal('0.2')]</td>\n",
" <td>Iris-setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <td>32</td>\n",
" <td>[Decimal('5.4'), Decimal('3.4'), Decimal('1.5'), Decimal('0.4')]</td>\n",
" <td>Iris-setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <td>33</td>\n",
" <td>[Decimal('5.2'), Decimal('4.1'), Decimal('1.5'), Decimal('0.1')]</td>\n",
" <td>Iris-setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <td>34</td>\n",
" <td>[Decimal('5.5'), Decimal('4.2'), Decimal('1.4'), Decimal('0.2')]</td>\n",
" <td>Iris-setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <td>35</td>\n",
" <td>[Decimal('4.9'), Decimal('3.1'), Decimal('1.5'), Decimal('0.1')]</td>\n",
" <td>Iris-setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <td>36</td>\n",
" <td>[Decimal('5.0'), Decimal('3.2'), Decimal('1.2'), Decimal('0.2')]</td>\n",
" <td>Iris-setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <td>37</td>\n",
" <td>[Decimal('5.5'), Decimal('3.5'), Decimal('1.3'), Decimal('0.2')]</td>\n",
" <td>Iris-setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <td>38</td>\n",
" <td>[Decimal('4.9'), Decimal('3.1'), Decimal('1.5'), Decimal('0.1')]</td>\n",
" <td>Iris-setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <td>39</td>\n",
" <td>[Decimal('4.4'), Decimal('3.0'), Decimal('1.3'), Decimal('0.2')]</td>\n",
" <td>Iris-setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <td>40</td>\n",
" <td>[Decimal('5.1'), Decimal('3.4'), Decimal('1.5'), Decimal('0.2')]</td>\n",
" <td>Iris-setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <td>41</td>\n",
" <td>[Decimal('5.0'), Decimal('3.5'), Decimal('1.3'), Decimal('0.3')]</td>\n",
" <td>Iris-setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <td>42</td>\n",
" <td>[Decimal('4.5'), Decimal('2.3'), Decimal('1.3'), Decimal('0.3')]</td>\n",
" <td>Iris-setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <td>43</td>\n",
" <td>[Decimal('4.4'), Decimal('3.2'), Decimal('1.3'), Decimal('0.2')]</td>\n",
" <td>Iris-setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <td>44</td>\n",
" <td>[Decimal('5.0'), Decimal('3.5'), Decimal('1.6'), Decimal('0.6')]</td>\n",
" <td>Iris-setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <td>45</td>\n",
" <td>[Decimal('5.1'), Decimal('3.8'), Decimal('1.9'), Decimal('0.4')]</td>\n",
" <td>Iris-setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <td>46</td>\n",
" <td>[Decimal('4.8'), Decimal('3.0'), Decimal('1.4'), Decimal('0.3')]</td>\n",
" <td>Iris-setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <td>47</td>\n",
" <td>[Decimal('5.1'), Decimal('3.8'), Decimal('1.6'), Decimal('0.2')]</td>\n",
" <td>Iris-setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <td>48</td>\n",
" <td>[Decimal('4.6'), Decimal('3.2'), Decimal('1.4'), Decimal('0.2')]</td>\n",
" <td>Iris-setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <td>49</td>\n",
" <td>[Decimal('5.3'), Decimal('3.7'), Decimal('1.5'), Decimal('0.2')]</td>\n",
" <td>Iris-setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <td>50</td>\n",
" <td>[Decimal('5.0'), Decimal('3.3'), Decimal('1.4'), Decimal('0.2')]</td>\n",
" <td>Iris-setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <td>51</td>\n",
" <td>[Decimal('7.0'), Decimal('3.2'), Decimal('4.7'), Decimal('1.4')]</td>\n",
" <td>Iris-versicolor</td>\n",
" </tr>\n",
" <tr>\n",
" <td>52</td>\n",
" <td>[Decimal('6.4'), Decimal('3.2'), Decimal('4.5'), Decimal('1.5')]</td>\n",
" <td>Iris-versicolor</td>\n",
" </tr>\n",
" <tr>\n",
" <td>53</td>\n",
" <td>[Decimal('6.9'), Decimal('3.1'), Decimal('4.9'), Decimal('1.5')]</td>\n",
" <td>Iris-versicolor</td>\n",
" </tr>\n",
" <tr>\n",
" <td>54</td>\n",
" <td>[Decimal('5.5'), Decimal('2.3'), Decimal('4.0'), Decimal('1.3')]</td>\n",
" <td>Iris-versicolor</td>\n",
" </tr>\n",
" <tr>\n",
" <td>55</td>\n",
" <td>[Decimal('6.5'), Decimal('2.8'), Decimal('4.6'), Decimal('1.5')]</td>\n",
" <td>Iris-versicolor</td>\n",
" </tr>\n",
" <tr>\n",
" <td>56</td>\n",
" <td>[Decimal('5.7'), Decimal('2.8'), Decimal('4.5'), Decimal('1.3')]</td>\n",
" <td>Iris-versicolor</td>\n",
" </tr>\n",
" <tr>\n",
" <td>57</td>\n",
" <td>[Decimal('6.3'), Decimal('3.3'), Decimal('4.7'), Decimal('1.6')]</td>\n",
" <td>Iris-versicolor</td>\n",
" </tr>\n",
" <tr>\n",
" <td>58</td>\n",
" <td>[Decimal('4.9'), Decimal('2.4'), Decimal('3.3'), Decimal('1.0')]</td>\n",
" <td>Iris-versicolor</td>\n",
" </tr>\n",
" <tr>\n",
" <td>59</td>\n",
" <td>[Decimal('6.6'), Decimal('2.9'), Decimal('4.6'), Decimal('1.3')]</td>\n",
" <td>Iris-versicolor</td>\n",
" </tr>\n",
" <tr>\n",
" <td>60</td>\n",
" <td>[Decimal('5.2'), Decimal('2.7'), Decimal('3.9'), Decimal('1.4')]</td>\n",
" <td>Iris-versicolor</td>\n",
" </tr>\n",
" <tr>\n",
" <td>61</td>\n",
" <td>[Decimal('5.0'), Decimal('2.0'), Decimal('3.5'), Decimal('1.0')]</td>\n",
" <td>Iris-versicolor</td>\n",
" </tr>\n",
" <tr>\n",
" <td>62</td>\n",
" <td>[Decimal('5.9'), Decimal('3.0'), Decimal('4.2'), Decimal('1.5')]</td>\n",
" <td>Iris-versicolor</td>\n",
" </tr>\n",
" <tr>\n",
" <td>63</td>\n",
" <td>[Decimal('6.0'), Decimal('2.2'), Decimal('4.0'), Decimal('1.0')]</td>\n",
" <td>Iris-versicolor</td>\n",
" </tr>\n",
" <tr>\n",
" <td>64</td>\n",
" <td>[Decimal('6.1'), Decimal('2.9'), Decimal('4.7'), Decimal('1.4')]</td>\n",
" <td>Iris-versicolor</td>\n",
" </tr>\n",
" <tr>\n",
" <td>65</td>\n",
" <td>[Decimal('5.6'), Decimal('2.9'), Decimal('3.6'), Decimal('1.3')]</td>\n",
" <td>Iris-versicolor</td>\n",
" </tr>\n",
" <tr>\n",
" <td>66</td>\n",
" <td>[Decimal('6.7'), Decimal('3.1'), Decimal('4.4'), Decimal('1.4')]</td>\n",
" <td>Iris-versicolor</td>\n",
" </tr>\n",
" <tr>\n",
" <td>67</td>\n",
" <td>[Decimal('5.6'), Decimal('3.0'), Decimal('4.5'), Decimal('1.5')]</td>\n",
" <td>Iris-versicolor</td>\n",
" </tr>\n",
" <tr>\n",
" <td>68</td>\n",
" <td>[Decimal('5.8'), Decimal('2.7'), Decimal('4.1'), Decimal('1.0')]</td>\n",
" <td>Iris-versicolor</td>\n",
" </tr>\n",
" <tr>\n",
" <td>69</td>\n",
" <td>[Decimal('6.2'), Decimal('2.2'), Decimal('4.5'), Decimal('1.5')]</td>\n",
" <td>Iris-versicolor</td>\n",
" </tr>\n",
" <tr>\n",
" <td>70</td>\n",
" <td>[Decimal('5.6'), Decimal('2.5'), Decimal('3.9'), Decimal('1.1')]</td>\n",
" <td>Iris-versicolor</td>\n",
" </tr>\n",
" <tr>\n",
" <td>71</td>\n",
" <td>[Decimal('5.9'), Decimal('3.2'), Decimal('4.8'), Decimal('1.8')]</td>\n",
" <td>Iris-versicolor</td>\n",
" </tr>\n",
" <tr>\n",
" <td>72</td>\n",
" <td>[Decimal('6.1'), Decimal('2.8'), Decimal('4.0'), Decimal('1.3')]</td>\n",
" <td>Iris-versicolor</td>\n",
" </tr>\n",
" <tr>\n",
" <td>73</td>\n",
" <td>[Decimal('6.3'), Decimal('2.5'), Decimal('4.9'), Decimal('1.5')]</td>\n",
" <td>Iris-versicolor</td>\n",
" </tr>\n",
" <tr>\n",
" <td>74</td>\n",
" <td>[Decimal('6.1'), Decimal('2.8'), Decimal('4.7'), Decimal('1.2')]</td>\n",
" <td>Iris-versicolor</td>\n",
" </tr>\n",
" <tr>\n",
" <td>75</td>\n",
" <td>[Decimal('6.4'), Decimal('2.9'), Decimal('4.3'), Decimal('1.3')]</td>\n",
" <td>Iris-versicolor</td>\n",
" </tr>\n",
" <tr>\n",
" <td>76</td>\n",
" <td>[Decimal('6.6'), Decimal('3.0'), Decimal('4.4'), Decimal('1.4')]</td>\n",
" <td>Iris-versicolor</td>\n",
" </tr>\n",
" <tr>\n",
" <td>77</td>\n",
" <td>[Decimal('6.8'), Decimal('2.8'), Decimal('4.8'), Decimal('1.4')]</td>\n",
" <td>Iris-versicolor</td>\n",
" </tr>\n",
" <tr>\n",
" <td>78</td>\n",
" <td>[Decimal('6.7'), Decimal('3.0'), Decimal('5.0'), Decimal('1.7')]</td>\n",
" <td>Iris-versicolor</td>\n",
" </tr>\n",
" <tr>\n",
" <td>79</td>\n",
" <td>[Decimal('6.0'), Decimal('2.9'), Decimal('4.5'), Decimal('1.5')]</td>\n",
" <td>Iris-versicolor</td>\n",
" </tr>\n",
" <tr>\n",
" <td>80</td>\n",
" <td>[Decimal('5.7'), Decimal('2.6'), Decimal('3.5'), Decimal('1.0')]</td>\n",
" <td>Iris-versicolor</td>\n",
" </tr>\n",
" <tr>\n",
" <td>81</td>\n",
" <td>[Decimal('5.5'), Decimal('2.4'), Decimal('3.8'), Decimal('1.1')]</td>\n",
" <td>Iris-versicolor</td>\n",
" </tr>\n",
" <tr>\n",
" <td>82</td>\n",
" <td>[Decimal('5.5'), Decimal('2.4'), Decimal('3.7'), Decimal('1.0')]</td>\n",
" <td>Iris-versicolor</td>\n",
" </tr>\n",
" <tr>\n",
" <td>83</td>\n",
" <td>[Decimal('5.8'), Decimal('2.7'), Decimal('3.9'), Decimal('1.2')]</td>\n",
" <td>Iris-versicolor</td>\n",
" </tr>\n",
" <tr>\n",
" <td>84</td>\n",
" <td>[Decimal('6.0'), Decimal('2.7'), Decimal('5.1'), Decimal('1.6')]</td>\n",
" <td>Iris-versicolor</td>\n",
" </tr>\n",
" <tr>\n",
" <td>85</td>\n",
" <td>[Decimal('5.4'), Decimal('3.0'), Decimal('4.5'), Decimal('1.5')]</td>\n",
" <td>Iris-versicolor</td>\n",
" </tr>\n",
" <tr>\n",
" <td>86</td>\n",
" <td>[Decimal('6.0'), Decimal('3.4'), Decimal('4.5'), Decimal('1.6')]</td>\n",
" <td>Iris-versicolor</td>\n",
" </tr>\n",
" <tr>\n",
" <td>87</td>\n",
" <td>[Decimal('6.7'), Decimal('3.1'), Decimal('4.7'), Decimal('1.5')]</td>\n",
" <td>Iris-versicolor</td>\n",
" </tr>\n",
" <tr>\n",
" <td>88</td>\n",
" <td>[Decimal('6.3'), Decimal('2.3'), Decimal('4.4'), Decimal('1.3')]</td>\n",
" <td>Iris-versicolor</td>\n",
" </tr>\n",
" <tr>\n",
" <td>89</td>\n",
" <td>[Decimal('5.6'), Decimal('3.0'), Decimal('4.1'), Decimal('1.3')]</td>\n",
" <td>Iris-versicolor</td>\n",
" </tr>\n",
" <tr>\n",
" <td>90</td>\n",
" <td>[Decimal('5.5'), Decimal('2.5'), Decimal('4.0'), Decimal('1.3')]</td>\n",
" <td>Iris-versicolor</td>\n",
" </tr>\n",
" <tr>\n",
" <td>91</td>\n",
" <td>[Decimal('5.5'), Decimal('2.6'), Decimal('4.4'), Decimal('1.2')]</td>\n",
" <td>Iris-versicolor</td>\n",
" </tr>\n",
" <tr>\n",
" <td>92</td>\n",
" <td>[Decimal('6.1'), Decimal('3.0'), Decimal('4.6'), Decimal('1.4')]</td>\n",
" <td>Iris-versicolor</td>\n",
" </tr>\n",
" <tr>\n",
" <td>93</td>\n",
" <td>[Decimal('5.8'), Decimal('2.6'), Decimal('4.0'), Decimal('1.2')]</td>\n",
" <td>Iris-versicolor</td>\n",
" </tr>\n",
" <tr>\n",
" <td>94</td>\n",
" <td>[Decimal('5.0'), Decimal('2.3'), Decimal('3.3'), Decimal('1.0')]</td>\n",
" <td>Iris-versicolor</td>\n",
" </tr>\n",
" <tr>\n",
" <td>95</td>\n",
" <td>[Decimal('5.6'), Decimal('2.7'), Decimal('4.2'), Decimal('1.3')]</td>\n",
" <td>Iris-versicolor</td>\n",
" </tr>\n",
" <tr>\n",
" <td>96</td>\n",
" <td>[Decimal('5.7'), Decimal('3.0'), Decimal('4.2'), Decimal('1.2')]</td>\n",
" <td>Iris-versicolor</td>\n",
" </tr>\n",
" <tr>\n",
" <td>97</td>\n",
" <td>[Decimal('5.7'), Decimal('2.9'), Decimal('4.2'), Decimal('1.3')]</td>\n",
" <td>Iris-versicolor</td>\n",
" </tr>\n",
" <tr>\n",
" <td>98</td>\n",
" <td>[Decimal('6.2'), Decimal('2.9'), Decimal('4.3'), Decimal('1.3')]</td>\n",
" <td>Iris-versicolor</td>\n",
" </tr>\n",
" <tr>\n",
" <td>99</td>\n",
" <td>[Decimal('5.1'), Decimal('2.5'), Decimal('3.0'), Decimal('1.1')]</td>\n",
" <td>Iris-versicolor</td>\n",
" </tr>\n",
" <tr>\n",
" <td>100</td>\n",
" <td>[Decimal('5.7'), Decimal('2.8'), Decimal('4.1'), Decimal('1.3')]</td>\n",
" <td>Iris-versicolor</td>\n",
" </tr>\n",
" <tr>\n",
" <td>101</td>\n",
" <td>[Decimal('6.3'), Decimal('3.3'), Decimal('6.0'), Decimal('2.5')]</td>\n",
" <td>Iris-virginica</td>\n",
" </tr>\n",
" <tr>\n",
" <td>102</td>\n",
" <td>[Decimal('5.8'), Decimal('2.7'), Decimal('5.1'), Decimal('1.9')]</td>\n",
" <td>Iris-virginica</td>\n",
" </tr>\n",
" <tr>\n",
" <td>103</td>\n",
" <td>[Decimal('7.1'), Decimal('3.0'), Decimal('5.9'), Decimal('2.1')]</td>\n",
" <td>Iris-virginica</td>\n",
" </tr>\n",
" <tr>\n",
" <td>104</td>\n",
" <td>[Decimal('6.3'), Decimal('2.9'), Decimal('5.6'), Decimal('1.8')]</td>\n",
" <td>Iris-virginica</td>\n",
" </tr>\n",
" <tr>\n",
" <td>105</td>\n",
" <td>[Decimal('6.5'), Decimal('3.0'), Decimal('5.8'), Decimal('2.2')]</td>\n",
" <td>Iris-virginica</td>\n",
" </tr>\n",
" <tr>\n",
" <td>106</td>\n",
" <td>[Decimal('7.6'), Decimal('3.0'), Decimal('6.6'), Decimal('2.1')]</td>\n",
" <td>Iris-virginica</td>\n",
" </tr>\n",
" <tr>\n",
" <td>107</td>\n",
" <td>[Decimal('4.9'), Decimal('2.5'), Decimal('4.5'), Decimal('1.7')]</td>\n",
" <td>Iris-virginica</td>\n",
" </tr>\n",
" <tr>\n",
" <td>108</td>\n",
" <td>[Decimal('7.3'), Decimal('2.9'), Decimal('6.3'), Decimal('1.8')]</td>\n",
" <td>Iris-virginica</td>\n",
" </tr>\n",
" <tr>\n",
" <td>109</td>\n",
" <td>[Decimal('6.7'), Decimal('2.5'), Decimal('5.8'), Decimal('1.8')]</td>\n",
" <td>Iris-virginica</td>\n",
" </tr>\n",
" <tr>\n",
" <td>110</td>\n",
" <td>[Decimal('7.2'), Decimal('3.6'), Decimal('6.1'), Decimal('2.5')]</td>\n",
" <td>Iris-virginica</td>\n",
" </tr>\n",
" <tr>\n",
" <td>111</td>\n",
" <td>[Decimal('6.5'), Decimal('3.2'), Decimal('5.1'), Decimal('2.0')]</td>\n",
" <td>Iris-virginica</td>\n",
" </tr>\n",
" <tr>\n",
" <td>112</td>\n",
" <td>[Decimal('6.4'), Decimal('2.7'), Decimal('5.3'), Decimal('1.9')]</td>\n",
" <td>Iris-virginica</td>\n",
" </tr>\n",
" <tr>\n",
" <td>113</td>\n",
" <td>[Decimal('6.8'), Decimal('3.0'), Decimal('5.5'), Decimal('2.1')]</td>\n",
" <td>Iris-virginica</td>\n",
" </tr>\n",
" <tr>\n",
" <td>114</td>\n",
" <td>[Decimal('5.7'), Decimal('2.5'), Decimal('5.0'), Decimal('2.0')]</td>\n",
" <td>Iris-virginica</td>\n",
" </tr>\n",
" <tr>\n",
" <td>115</td>\n",
" <td>[Decimal('5.8'), Decimal('2.8'), Decimal('5.1'), Decimal('2.4')]</td>\n",
" <td>Iris-virginica</td>\n",
" </tr>\n",
" <tr>\n",
" <td>116</td>\n",
" <td>[Decimal('6.4'), Decimal('3.2'), Decimal('5.3'), Decimal('2.3')]</td>\n",
" <td>Iris-virginica</td>\n",
" </tr>\n",
" <tr>\n",
" <td>117</td>\n",
" <td>[Decimal('6.5'), Decimal('3.0'), Decimal('5.5'), Decimal('1.8')]</td>\n",
" <td>Iris-virginica</td>\n",
" </tr>\n",
" <tr>\n",
" <td>118</td>\n",
" <td>[Decimal('7.7'), Decimal('3.8'), Decimal('6.7'), Decimal('2.2')]</td>\n",
" <td>Iris-virginica</td>\n",
" </tr>\n",
" <tr>\n",
" <td>119</td>\n",
" <td>[Decimal('7.7'), Decimal('2.6'), Decimal('6.9'), Decimal('2.3')]</td>\n",
" <td>Iris-virginica</td>\n",
" </tr>\n",
" <tr>\n",
" <td>120</td>\n",
" <td>[Decimal('6.0'), Decimal('2.2'), Decimal('5.0'), Decimal('1.5')]</td>\n",
" <td>Iris-virginica</td>\n",
" </tr>\n",
" <tr>\n",
" <td>121</td>\n",
" <td>[Decimal('6.9'), Decimal('3.2'), Decimal('5.7'), Decimal('2.3')]</td>\n",
" <td>Iris-virginica</td>\n",
" </tr>\n",
" <tr>\n",
" <td>122</td>\n",
" <td>[Decimal('5.6'), Decimal('2.8'), Decimal('4.9'), Decimal('2.0')]</td>\n",
" <td>Iris-virginica</td>\n",
" </tr>\n",
" <tr>\n",
" <td>123</td>\n",
" <td>[Decimal('7.7'), Decimal('2.8'), Decimal('6.7'), Decimal('2.0')]</td>\n",
" <td>Iris-virginica</td>\n",
" </tr>\n",
" <tr>\n",
" <td>124</td>\n",
" <td>[Decimal('6.3'), Decimal('2.7'), Decimal('4.9'), Decimal('1.8')]</td>\n",
" <td>Iris-virginica</td>\n",
" </tr>\n",
" <tr>\n",
" <td>125</td>\n",
" <td>[Decimal('6.7'), Decimal('3.3'), Decimal('5.7'), Decimal('2.1')]</td>\n",
" <td>Iris-virginica</td>\n",
" </tr>\n",
" <tr>\n",
" <td>126</td>\n",
" <td>[Decimal('7.2'), Decimal('3.2'), Decimal('6.0'), Decimal('1.8')]</td>\n",
" <td>Iris-virginica</td>\n",
" </tr>\n",
" <tr>\n",
" <td>127</td>\n",
" <td>[Decimal('6.2'), Decimal('2.8'), Decimal('4.8'), Decimal('1.8')]</td>\n",
" <td>Iris-virginica</td>\n",
" </tr>\n",
" <tr>\n",
" <td>128</td>\n",
" <td>[Decimal('6.1'), Decimal('3.0'), Decimal('4.9'), Decimal('1.8')]</td>\n",
" <td>Iris-virginica</td>\n",
" </tr>\n",
" <tr>\n",
" <td>129</td>\n",
" <td>[Decimal('6.4'), Decimal('2.8'), Decimal('5.6'), Decimal('2.1')]</td>\n",
" <td>Iris-virginica</td>\n",
" </tr>\n",
" <tr>\n",
" <td>130</td>\n",
" <td>[Decimal('7.2'), Decimal('3.0'), Decimal('5.8'), Decimal('1.6')]</td>\n",
" <td>Iris-virginica</td>\n",
" </tr>\n",
" <tr>\n",
" <td>131</td>\n",
" <td>[Decimal('7.4'), Decimal('2.8'), Decimal('6.1'), Decimal('1.9')]</td>\n",
" <td>Iris-virginica</td>\n",
" </tr>\n",
" <tr>\n",
" <td>132</td>\n",
" <td>[Decimal('7.9'), Decimal('3.8'), Decimal('6.4'), Decimal('2.0')]</td>\n",
" <td>Iris-virginica</td>\n",
" </tr>\n",
" <tr>\n",
" <td>133</td>\n",
" <td>[Decimal('6.4'), Decimal('2.8'), Decimal('5.6'), Decimal('2.2')]</td>\n",
" <td>Iris-virginica</td>\n",
" </tr>\n",
" <tr>\n",
" <td>134</td>\n",
" <td>[Decimal('6.3'), Decimal('2.8'), Decimal('5.1'), Decimal('1.5')]</td>\n",
" <td>Iris-virginica</td>\n",
" </tr>\n",
" <tr>\n",
" <td>135</td>\n",
" <td>[Decimal('6.1'), Decimal('2.6'), Decimal('5.6'), Decimal('1.4')]</td>\n",
" <td>Iris-virginica</td>\n",
" </tr>\n",
" <tr>\n",
" <td>136</td>\n",
" <td>[Decimal('7.7'), Decimal('3.0'), Decimal('6.1'), Decimal('2.3')]</td>\n",
" <td>Iris-virginica</td>\n",
" </tr>\n",
" <tr>\n",
" <td>137</td>\n",
" <td>[Decimal('6.3'), Decimal('3.4'), Decimal('5.6'), Decimal('2.4')]</td>\n",
" <td>Iris-virginica</td>\n",
" </tr>\n",
" <tr>\n",
" <td>138</td>\n",
" <td>[Decimal('6.4'), Decimal('3.1'), Decimal('5.5'), Decimal('1.8')]</td>\n",
" <td>Iris-virginica</td>\n",
" </tr>\n",
" <tr>\n",
" <td>139</td>\n",
" <td>[Decimal('6.0'), Decimal('3.0'), Decimal('4.8'), Decimal('1.8')]</td>\n",
" <td>Iris-virginica</td>\n",
" </tr>\n",
" <tr>\n",
" <td>140</td>\n",
" <td>[Decimal('6.9'), Decimal('3.1'), Decimal('5.4'), Decimal('2.1')]</td>\n",
" <td>Iris-virginica</td>\n",
" </tr>\n",
" <tr>\n",
" <td>141</td>\n",
" <td>[Decimal('6.7'), Decimal('3.1'), Decimal('5.6'), Decimal('2.4')]</td>\n",
" <td>Iris-virginica</td>\n",
" </tr>\n",
" <tr>\n",
" <td>142</td>\n",
" <td>[Decimal('6.9'), Decimal('3.1'), Decimal('5.1'), Decimal('2.3')]</td>\n",
" <td>Iris-virginica</td>\n",
" </tr>\n",
" <tr>\n",
" <td>143</td>\n",
" <td>[Decimal('5.8'), Decimal('2.7'), Decimal('5.1'), Decimal('1.9')]</td>\n",
" <td>Iris-virginica</td>\n",
" </tr>\n",
" <tr>\n",
" <td>144</td>\n",
" <td>[Decimal('6.8'), Decimal('3.2'), Decimal('5.9'), Decimal('2.3')]</td>\n",
" <td>Iris-virginica</td>\n",
" </tr>\n",
" <tr>\n",
" <td>145</td>\n",
" <td>[Decimal('6.7'), Decimal('3.3'), Decimal('5.7'), Decimal('2.5')]</td>\n",
" <td>Iris-virginica</td>\n",
" </tr>\n",
" <tr>\n",
" <td>146</td>\n",
" <td>[Decimal('6.7'), Decimal('3.0'), Decimal('5.2'), Decimal('2.3')]</td>\n",
" <td>Iris-virginica</td>\n",
" </tr>\n",
" <tr>\n",
" <td>147</td>\n",
" <td>[Decimal('6.3'), Decimal('2.5'), Decimal('5.0'), Decimal('1.9')]</td>\n",
" <td>Iris-virginica</td>\n",
" </tr>\n",
" <tr>\n",
" <td>148</td>\n",
" <td>[Decimal('6.5'), Decimal('3.0'), Decimal('5.2'), Decimal('2.0')]</td>\n",
" <td>Iris-virginica</td>\n",
" </tr>\n",
" <tr>\n",
" <td>149</td>\n",
" <td>[Decimal('6.2'), Decimal('3.4'), Decimal('5.4'), Decimal('2.3')]</td>\n",
" <td>Iris-virginica</td>\n",
" </tr>\n",
" <tr>\n",
" <td>150</td>\n",
" <td>[Decimal('5.9'), Decimal('3.0'), Decimal('5.1'), Decimal('1.8')]</td>\n",
" <td>Iris-virginica</td>\n",
" </tr>\n",
"</table>"
],
"text/plain": [
"[(1, [Decimal('5.1'), Decimal('3.5'), Decimal('1.4'), Decimal('0.2')], u'Iris-setosa'),\n",
" (2, [Decimal('4.9'), Decimal('3.0'), Decimal('1.4'), Decimal('0.2')], u'Iris-setosa'),\n",
" (3, [Decimal('4.7'), Decimal('3.2'), Decimal('1.3'), Decimal('0.2')], u'Iris-setosa'),\n",
" (4, [Decimal('4.6'), Decimal('3.1'), Decimal('1.5'), Decimal('0.2')], u'Iris-setosa'),\n",
" (5, [Decimal('5.0'), Decimal('3.6'), Decimal('1.4'), Decimal('0.2')], u'Iris-setosa'),\n",
" (6, [Decimal('5.4'), Decimal('3.9'), Decimal('1.7'), Decimal('0.4')], u'Iris-setosa'),\n",
" (7, [Decimal('4.6'), Decimal('3.4'), Decimal('1.4'), Decimal('0.3')], u'Iris-setosa'),\n",
" (8, [Decimal('5.0'), Decimal('3.4'), Decimal('1.5'), Decimal('0.2')], u'Iris-setosa'),\n",
" (9, [Decimal('4.4'), Decimal('2.9'), Decimal('1.4'), Decimal('0.2')], u'Iris-setosa'),\n",
" (10, [Decimal('4.9'), Decimal('3.1'), Decimal('1.5'), Decimal('0.1')], u'Iris-setosa'),\n",
" (11, [Decimal('5.4'), Decimal('3.7'), Decimal('1.5'), Decimal('0.2')], u'Iris-setosa'),\n",
" (12, [Decimal('4.8'), Decimal('3.4'), Decimal('1.6'), Decimal('0.2')], u'Iris-setosa'),\n",
" (13, [Decimal('4.8'), Decimal('3.0'), Decimal('1.4'), Decimal('0.1')], u'Iris-setosa'),\n",
" (14, [Decimal('4.3'), Decimal('3.0'), Decimal('1.1'), Decimal('0.1')], u'Iris-setosa'),\n",
" (15, [Decimal('5.8'), Decimal('4.0'), Decimal('1.2'), Decimal('0.2')], u'Iris-setosa'),\n",
" (16, [Decimal('5.7'), Decimal('4.4'), Decimal('1.5'), Decimal('0.4')], u'Iris-setosa'),\n",
" (17, [Decimal('5.4'), Decimal('3.9'), Decimal('1.3'), Decimal('0.4')], u'Iris-setosa'),\n",
" (18, [Decimal('5.1'), Decimal('3.5'), Decimal('1.4'), Decimal('0.3')], u'Iris-setosa'),\n",
" (19, [Decimal('5.7'), Decimal('3.8'), Decimal('1.7'), Decimal('0.3')], u'Iris-setosa'),\n",
" (20, [Decimal('5.1'), Decimal('3.8'), Decimal('1.5'), Decimal('0.3')], u'Iris-setosa'),\n",
" (21, [Decimal('5.4'), Decimal('3.4'), Decimal('1.7'), Decimal('0.2')], u'Iris-setosa'),\n",
" (22, [Decimal('5.1'), Decimal('3.7'), Decimal('1.5'), Decimal('0.4')], u'Iris-setosa'),\n",
" (23, [Decimal('4.6'), Decimal('3.6'), Decimal('1.0'), Decimal('0.2')], u'Iris-setosa'),\n",
" (24, [Decimal('5.1'), Decimal('3.3'), Decimal('1.7'), Decimal('0.5')], u'Iris-setosa'),\n",
" (25, [Decimal('4.8'), Decimal('3.4'), Decimal('1.9'), Decimal('0.2')], u'Iris-setosa'),\n",
" (26, [Decimal('5.0'), Decimal('3.0'), Decimal('1.6'), Decimal('0.2')], u'Iris-setosa'),\n",
" (27, [Decimal('5.0'), Decimal('3.4'), Decimal('1.6'), Decimal('0.4')], u'Iris-setosa'),\n",
" (28, [Decimal('5.2'), Decimal('3.5'), Decimal('1.5'), Decimal('0.2')], u'Iris-setosa'),\n",
" (29, [Decimal('5.2'), Decimal('3.4'), Decimal('1.4'), Decimal('0.2')], u'Iris-setosa'),\n",
" (30, [Decimal('4.7'), Decimal('3.2'), Decimal('1.6'), Decimal('0.2')], u'Iris-setosa'),\n",
" (31, [Decimal('4.8'), Decimal('3.1'), Decimal('1.6'), Decimal('0.2')], u'Iris-setosa'),\n",
" (32, [Decimal('5.4'), Decimal('3.4'), Decimal('1.5'), Decimal('0.4')], u'Iris-setosa'),\n",
" (33, [Decimal('5.2'), Decimal('4.1'), Decimal('1.5'), Decimal('0.1')], u'Iris-setosa'),\n",
" (34, [Decimal('5.5'), Decimal('4.2'), Decimal('1.4'), Decimal('0.2')], u'Iris-setosa'),\n",
" (35, [Decimal('4.9'), Decimal('3.1'), Decimal('1.5'), Decimal('0.1')], u'Iris-setosa'),\n",
" (36, [Decimal('5.0'), Decimal('3.2'), Decimal('1.2'), Decimal('0.2')], u'Iris-setosa'),\n",
" (37, [Decimal('5.5'), Decimal('3.5'), Decimal('1.3'), Decimal('0.2')], u'Iris-setosa'),\n",
" (38, [Decimal('4.9'), Decimal('3.1'), Decimal('1.5'), Decimal('0.1')], u'Iris-setosa'),\n",
" (39, [Decimal('4.4'), Decimal('3.0'), Decimal('1.3'), Decimal('0.2')], u'Iris-setosa'),\n",
" (40, [Decimal('5.1'), Decimal('3.4'), Decimal('1.5'), Decimal('0.2')], u'Iris-setosa'),\n",
" (41, [Decimal('5.0'), Decimal('3.5'), Decimal('1.3'), Decimal('0.3')], u'Iris-setosa'),\n",
" (42, [Decimal('4.5'), Decimal('2.3'), Decimal('1.3'), Decimal('0.3')], u'Iris-setosa'),\n",
" (43, [Decimal('4.4'), Decimal('3.2'), Decimal('1.3'), Decimal('0.2')], u'Iris-setosa'),\n",
" (44, [Decimal('5.0'), Decimal('3.5'), Decimal('1.6'), Decimal('0.6')], u'Iris-setosa'),\n",
" (45, [Decimal('5.1'), Decimal('3.8'), Decimal('1.9'), Decimal('0.4')], u'Iris-setosa'),\n",
" (46, [Decimal('4.8'), Decimal('3.0'), Decimal('1.4'), Decimal('0.3')], u'Iris-setosa'),\n",
" (47, [Decimal('5.1'), Decimal('3.8'), Decimal('1.6'), Decimal('0.2')], u'Iris-setosa'),\n",
" (48, [Decimal('4.6'), Decimal('3.2'), Decimal('1.4'), Decimal('0.2')], u'Iris-setosa'),\n",
" (49, [Decimal('5.3'), Decimal('3.7'), Decimal('1.5'), Decimal('0.2')], u'Iris-setosa'),\n",
" (50, [Decimal('5.0'), Decimal('3.3'), Decimal('1.4'), Decimal('0.2')], u'Iris-setosa'),\n",
" (51, [Decimal('7.0'), Decimal('3.2'), Decimal('4.7'), Decimal('1.4')], u'Iris-versicolor'),\n",
" (52, [Decimal('6.4'), Decimal('3.2'), Decimal('4.5'), Decimal('1.5')], u'Iris-versicolor'),\n",
" (53, [Decimal('6.9'), Decimal('3.1'), Decimal('4.9'), Decimal('1.5')], u'Iris-versicolor'),\n",
" (54, [Decimal('5.5'), Decimal('2.3'), Decimal('4.0'), Decimal('1.3')], u'Iris-versicolor'),\n",
" (55, [Decimal('6.5'), Decimal('2.8'), Decimal('4.6'), Decimal('1.5')], u'Iris-versicolor'),\n",
" (56, [Decimal('5.7'), Decimal('2.8'), Decimal('4.5'), Decimal('1.3')], u'Iris-versicolor'),\n",
" (57, [Decimal('6.3'), Decimal('3.3'), Decimal('4.7'), Decimal('1.6')], u'Iris-versicolor'),\n",
" (58, [Decimal('4.9'), Decimal('2.4'), Decimal('3.3'), Decimal('1.0')], u'Iris-versicolor'),\n",
" (59, [Decimal('6.6'), Decimal('2.9'), Decimal('4.6'), Decimal('1.3')], u'Iris-versicolor'),\n",
" (60, [Decimal('5.2'), Decimal('2.7'), Decimal('3.9'), Decimal('1.4')], u'Iris-versicolor'),\n",
" (61, [Decimal('5.0'), Decimal('2.0'), Decimal('3.5'), Decimal('1.0')], u'Iris-versicolor'),\n",
" (62, [Decimal('5.9'), Decimal('3.0'), Decimal('4.2'), Decimal('1.5')], u'Iris-versicolor'),\n",
" (63, [Decimal('6.0'), Decimal('2.2'), Decimal('4.0'), Decimal('1.0')], u'Iris-versicolor'),\n",
" (64, [Decimal('6.1'), Decimal('2.9'), Decimal('4.7'), Decimal('1.4')], u'Iris-versicolor'),\n",
" (65, [Decimal('5.6'), Decimal('2.9'), Decimal('3.6'), Decimal('1.3')], u'Iris-versicolor'),\n",
" (66, [Decimal('6.7'), Decimal('3.1'), Decimal('4.4'), Decimal('1.4')], u'Iris-versicolor'),\n",
" (67, [Decimal('5.6'), Decimal('3.0'), Decimal('4.5'), Decimal('1.5')], u'Iris-versicolor'),\n",
" (68, [Decimal('5.8'), Decimal('2.7'), Decimal('4.1'), Decimal('1.0')], u'Iris-versicolor'),\n",
" (69, [Decimal('6.2'), Decimal('2.2'), Decimal('4.5'), Decimal('1.5')], u'Iris-versicolor'),\n",
" (70, [Decimal('5.6'), Decimal('2.5'), Decimal('3.9'), Decimal('1.1')], u'Iris-versicolor'),\n",
" (71, [Decimal('5.9'), Decimal('3.2'), Decimal('4.8'), Decimal('1.8')], u'Iris-versicolor'),\n",
" (72, [Decimal('6.1'), Decimal('2.8'), Decimal('4.0'), Decimal('1.3')], u'Iris-versicolor'),\n",
" (73, [Decimal('6.3'), Decimal('2.5'), Decimal('4.9'), Decimal('1.5')], u'Iris-versicolor'),\n",
" (74, [Decimal('6.1'), Decimal('2.8'), Decimal('4.7'), Decimal('1.2')], u'Iris-versicolor'),\n",
" (75, [Decimal('6.4'), Decimal('2.9'), Decimal('4.3'), Decimal('1.3')], u'Iris-versicolor'),\n",
" (76, [Decimal('6.6'), Decimal('3.0'), Decimal('4.4'), Decimal('1.4')], u'Iris-versicolor'),\n",
" (77, [Decimal('6.8'), Decimal('2.8'), Decimal('4.8'), Decimal('1.4')], u'Iris-versicolor'),\n",
" (78, [Decimal('6.7'), Decimal('3.0'), Decimal('5.0'), Decimal('1.7')], u'Iris-versicolor'),\n",
" (79, [Decimal('6.0'), Decimal('2.9'), Decimal('4.5'), Decimal('1.5')], u'Iris-versicolor'),\n",
" (80, [Decimal('5.7'), Decimal('2.6'), Decimal('3.5'), Decimal('1.0')], u'Iris-versicolor'),\n",
" (81, [Decimal('5.5'), Decimal('2.4'), Decimal('3.8'), Decimal('1.1')], u'Iris-versicolor'),\n",
" (82, [Decimal('5.5'), Decimal('2.4'), Decimal('3.7'), Decimal('1.0')], u'Iris-versicolor'),\n",
" (83, [Decimal('5.8'), Decimal('2.7'), Decimal('3.9'), Decimal('1.2')], u'Iris-versicolor'),\n",
" (84, [Decimal('6.0'), Decimal('2.7'), Decimal('5.1'), Decimal('1.6')], u'Iris-versicolor'),\n",
" (85, [Decimal('5.4'), Decimal('3.0'), Decimal('4.5'), Decimal('1.5')], u'Iris-versicolor'),\n",
" (86, [Decimal('6.0'), Decimal('3.4'), Decimal('4.5'), Decimal('1.6')], u'Iris-versicolor'),\n",
" (87, [Decimal('6.7'), Decimal('3.1'), Decimal('4.7'), Decimal('1.5')], u'Iris-versicolor'),\n",
" (88, [Decimal('6.3'), Decimal('2.3'), Decimal('4.4'), Decimal('1.3')], u'Iris-versicolor'),\n",
" (89, [Decimal('5.6'), Decimal('3.0'), Decimal('4.1'), Decimal('1.3')], u'Iris-versicolor'),\n",
" (90, [Decimal('5.5'), Decimal('2.5'), Decimal('4.0'), Decimal('1.3')], u'Iris-versicolor'),\n",
" (91, [Decimal('5.5'), Decimal('2.6'), Decimal('4.4'), Decimal('1.2')], u'Iris-versicolor'),\n",
" (92, [Decimal('6.1'), Decimal('3.0'), Decimal('4.6'), Decimal('1.4')], u'Iris-versicolor'),\n",
" (93, [Decimal('5.8'), Decimal('2.6'), Decimal('4.0'), Decimal('1.2')], u'Iris-versicolor'),\n",
" (94, [Decimal('5.0'), Decimal('2.3'), Decimal('3.3'), Decimal('1.0')], u'Iris-versicolor'),\n",
" (95, [Decimal('5.6'), Decimal('2.7'), Decimal('4.2'), Decimal('1.3')], u'Iris-versicolor'),\n",
" (96, [Decimal('5.7'), Decimal('3.0'), Decimal('4.2'), Decimal('1.2')], u'Iris-versicolor'),\n",
" (97, [Decimal('5.7'), Decimal('2.9'), Decimal('4.2'), Decimal('1.3')], u'Iris-versicolor'),\n",
" (98, [Decimal('6.2'), Decimal('2.9'), Decimal('4.3'), Decimal('1.3')], u'Iris-versicolor'),\n",
" (99, [Decimal('5.1'), Decimal('2.5'), Decimal('3.0'), Decimal('1.1')], u'Iris-versicolor'),\n",
" (100, [Decimal('5.7'), Decimal('2.8'), Decimal('4.1'), Decimal('1.3')], u'Iris-versicolor'),\n",
" (101, [Decimal('6.3'), Decimal('3.3'), Decimal('6.0'), Decimal('2.5')], u'Iris-virginica'),\n",
" (102, [Decimal('5.8'), Decimal('2.7'), Decimal('5.1'), Decimal('1.9')], u'Iris-virginica'),\n",
" (103, [Decimal('7.1'), Decimal('3.0'), Decimal('5.9'), Decimal('2.1')], u'Iris-virginica'),\n",
" (104, [Decimal('6.3'), Decimal('2.9'), Decimal('5.6'), Decimal('1.8')], u'Iris-virginica'),\n",
" (105, [Decimal('6.5'), Decimal('3.0'), Decimal('5.8'), Decimal('2.2')], u'Iris-virginica'),\n",
" (106, [Decimal('7.6'), Decimal('3.0'), Decimal('6.6'), Decimal('2.1')], u'Iris-virginica'),\n",
" (107, [Decimal('4.9'), Decimal('2.5'), Decimal('4.5'), Decimal('1.7')], u'Iris-virginica'),\n",
" (108, [Decimal('7.3'), Decimal('2.9'), Decimal('6.3'), Decimal('1.8')], u'Iris-virginica'),\n",
" (109, [Decimal('6.7'), Decimal('2.5'), Decimal('5.8'), Decimal('1.8')], u'Iris-virginica'),\n",
" (110, [Decimal('7.2'), Decimal('3.6'), Decimal('6.1'), Decimal('2.5')], u'Iris-virginica'),\n",
" (111, [Decimal('6.5'), Decimal('3.2'), Decimal('5.1'), Decimal('2.0')], u'Iris-virginica'),\n",
" (112, [Decimal('6.4'), Decimal('2.7'), Decimal('5.3'), Decimal('1.9')], u'Iris-virginica'),\n",
" (113, [Decimal('6.8'), Decimal('3.0'), Decimal('5.5'), Decimal('2.1')], u'Iris-virginica'),\n",
" (114, [Decimal('5.7'), Decimal('2.5'), Decimal('5.0'), Decimal('2.0')], u'Iris-virginica'),\n",
" (115, [Decimal('5.8'), Decimal('2.8'), Decimal('5.1'), Decimal('2.4')], u'Iris-virginica'),\n",
" (116, [Decimal('6.4'), Decimal('3.2'), Decimal('5.3'), Decimal('2.3')], u'Iris-virginica'),\n",
" (117, [Decimal('6.5'), Decimal('3.0'), Decimal('5.5'), Decimal('1.8')], u'Iris-virginica'),\n",
" (118, [Decimal('7.7'), Decimal('3.8'), Decimal('6.7'), Decimal('2.2')], u'Iris-virginica'),\n",
" (119, [Decimal('7.7'), Decimal('2.6'), Decimal('6.9'), Decimal('2.3')], u'Iris-virginica'),\n",
" (120, [Decimal('6.0'), Decimal('2.2'), Decimal('5.0'), Decimal('1.5')], u'Iris-virginica'),\n",
" (121, [Decimal('6.9'), Decimal('3.2'), Decimal('5.7'), Decimal('2.3')], u'Iris-virginica'),\n",
" (122, [Decimal('5.6'), Decimal('2.8'), Decimal('4.9'), Decimal('2.0')], u'Iris-virginica'),\n",
" (123, [Decimal('7.7'), Decimal('2.8'), Decimal('6.7'), Decimal('2.0')], u'Iris-virginica'),\n",
" (124, [Decimal('6.3'), Decimal('2.7'), Decimal('4.9'), Decimal('1.8')], u'Iris-virginica'),\n",
" (125, [Decimal('6.7'), Decimal('3.3'), Decimal('5.7'), Decimal('2.1')], u'Iris-virginica'),\n",
" (126, [Decimal('7.2'), Decimal('3.2'), Decimal('6.0'), Decimal('1.8')], u'Iris-virginica'),\n",
" (127, [Decimal('6.2'), Decimal('2.8'), Decimal('4.8'), Decimal('1.8')], u'Iris-virginica'),\n",
" (128, [Decimal('6.1'), Decimal('3.0'), Decimal('4.9'), Decimal('1.8')], u'Iris-virginica'),\n",
" (129, [Decimal('6.4'), Decimal('2.8'), Decimal('5.6'), Decimal('2.1')], u'Iris-virginica'),\n",
" (130, [Decimal('7.2'), Decimal('3.0'), Decimal('5.8'), Decimal('1.6')], u'Iris-virginica'),\n",
" (131, [Decimal('7.4'), Decimal('2.8'), Decimal('6.1'), Decimal('1.9')], u'Iris-virginica'),\n",
" (132, [Decimal('7.9'), Decimal('3.8'), Decimal('6.4'), Decimal('2.0')], u'Iris-virginica'),\n",
" (133, [Decimal('6.4'), Decimal('2.8'), Decimal('5.6'), Decimal('2.2')], u'Iris-virginica'),\n",
" (134, [Decimal('6.3'), Decimal('2.8'), Decimal('5.1'), Decimal('1.5')], u'Iris-virginica'),\n",
" (135, [Decimal('6.1'), Decimal('2.6'), Decimal('5.6'), Decimal('1.4')], u'Iris-virginica'),\n",
" (136, [Decimal('7.7'), Decimal('3.0'), Decimal('6.1'), Decimal('2.3')], u'Iris-virginica'),\n",
" (137, [Decimal('6.3'), Decimal('3.4'), Decimal('5.6'), Decimal('2.4')], u'Iris-virginica'),\n",
" (138, [Decimal('6.4'), Decimal('3.1'), Decimal('5.5'), Decimal('1.8')], u'Iris-virginica'),\n",
" (139, [Decimal('6.0'), Decimal('3.0'), Decimal('4.8'), Decimal('1.8')], u'Iris-virginica'),\n",
" (140, [Decimal('6.9'), Decimal('3.1'), Decimal('5.4'), Decimal('2.1')], u'Iris-virginica'),\n",
" (141, [Decimal('6.7'), Decimal('3.1'), Decimal('5.6'), Decimal('2.4')], u'Iris-virginica'),\n",
" (142, [Decimal('6.9'), Decimal('3.1'), Decimal('5.1'), Decimal('2.3')], u'Iris-virginica'),\n",
" (143, [Decimal('5.8'), Decimal('2.7'), Decimal('5.1'), Decimal('1.9')], u'Iris-virginica'),\n",
" (144, [Decimal('6.8'), Decimal('3.2'), Decimal('5.9'), Decimal('2.3')], u'Iris-virginica'),\n",
" (145, [Decimal('6.7'), Decimal('3.3'), Decimal('5.7'), Decimal('2.5')], u'Iris-virginica'),\n",
" (146, [Decimal('6.7'), Decimal('3.0'), Decimal('5.2'), Decimal('2.3')], u'Iris-virginica'),\n",
" (147, [Decimal('6.3'), Decimal('2.5'), Decimal('5.0'), Decimal('1.9')], u'Iris-virginica'),\n",
" (148, [Decimal('6.5'), Decimal('3.0'), Decimal('5.2'), Decimal('2.0')], u'Iris-virginica'),\n",
" (149, [Decimal('6.2'), Decimal('3.4'), Decimal('5.4'), Decimal('2.3')], u'Iris-virginica'),\n",
" (150, [Decimal('5.9'), Decimal('3.0'), Decimal('5.1'), Decimal('1.8')], u'Iris-virginica')]"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"%%sql \n",
"DROP TABLE IF EXISTS iris_data;\n",
"\n",
"CREATE TABLE iris_data(\n",
" id serial,\n",
" attributes numeric[],\n",
" class_text varchar\n",
");\n",
"\n",
"INSERT INTO iris_data(id, attributes, class_text) VALUES\n",
"(1,ARRAY[5.1,3.5,1.4,0.2],'Iris-setosa'),\n",
"(2,ARRAY[4.9,3.0,1.4,0.2],'Iris-setosa'),\n",
"(3,ARRAY[4.7,3.2,1.3,0.2],'Iris-setosa'),\n",
"(4,ARRAY[4.6,3.1,1.5,0.2],'Iris-setosa'),\n",
"(5,ARRAY[5.0,3.6,1.4,0.2],'Iris-setosa'),\n",
"(6,ARRAY[5.4,3.9,1.7,0.4],'Iris-setosa'),\n",
"(7,ARRAY[4.6,3.4,1.4,0.3],'Iris-setosa'),\n",
"(8,ARRAY[5.0,3.4,1.5,0.2],'Iris-setosa'),\n",
"(9,ARRAY[4.4,2.9,1.4,0.2],'Iris-setosa'),\n",
"(10,ARRAY[4.9,3.1,1.5,0.1],'Iris-setosa'),\n",
"(11,ARRAY[5.4,3.7,1.5,0.2],'Iris-setosa'),\n",
"(12,ARRAY[4.8,3.4,1.6,0.2],'Iris-setosa'),\n",
"(13,ARRAY[4.8,3.0,1.4,0.1],'Iris-setosa'),\n",
"(14,ARRAY[4.3,3.0,1.1,0.1],'Iris-setosa'),\n",
"(15,ARRAY[5.8,4.0,1.2,0.2],'Iris-setosa'),\n",
"(16,ARRAY[5.7,4.4,1.5,0.4],'Iris-setosa'),\n",
"(17,ARRAY[5.4,3.9,1.3,0.4],'Iris-setosa'),\n",
"(18,ARRAY[5.1,3.5,1.4,0.3],'Iris-setosa'),\n",
"(19,ARRAY[5.7,3.8,1.7,0.3],'Iris-setosa'),\n",
"(20,ARRAY[5.1,3.8,1.5,0.3],'Iris-setosa'),\n",
"(21,ARRAY[5.4,3.4,1.7,0.2],'Iris-setosa'),\n",
"(22,ARRAY[5.1,3.7,1.5,0.4],'Iris-setosa'),\n",
"(23,ARRAY[4.6,3.6,1.0,0.2],'Iris-setosa'),\n",
"(24,ARRAY[5.1,3.3,1.7,0.5],'Iris-setosa'),\n",
"(25,ARRAY[4.8,3.4,1.9,0.2],'Iris-setosa'),\n",
"(26,ARRAY[5.0,3.0,1.6,0.2],'Iris-setosa'),\n",
"(27,ARRAY[5.0,3.4,1.6,0.4],'Iris-setosa'),\n",
"(28,ARRAY[5.2,3.5,1.5,0.2],'Iris-setosa'),\n",
"(29,ARRAY[5.2,3.4,1.4,0.2],'Iris-setosa'),\n",
"(30,ARRAY[4.7,3.2,1.6,0.2],'Iris-setosa'),\n",
"(31,ARRAY[4.8,3.1,1.6,0.2],'Iris-setosa'),\n",
"(32,ARRAY[5.4,3.4,1.5,0.4],'Iris-setosa'),\n",
"(33,ARRAY[5.2,4.1,1.5,0.1],'Iris-setosa'),\n",
"(34,ARRAY[5.5,4.2,1.4,0.2],'Iris-setosa'),\n",
"(35,ARRAY[4.9,3.1,1.5,0.1],'Iris-setosa'),\n",
"(36,ARRAY[5.0,3.2,1.2,0.2],'Iris-setosa'),\n",
"(37,ARRAY[5.5,3.5,1.3,0.2],'Iris-setosa'),\n",
"(38,ARRAY[4.9,3.1,1.5,0.1],'Iris-setosa'),\n",
"(39,ARRAY[4.4,3.0,1.3,0.2],'Iris-setosa'),\n",
"(40,ARRAY[5.1,3.4,1.5,0.2],'Iris-setosa'),\n",
"(41,ARRAY[5.0,3.5,1.3,0.3],'Iris-setosa'),\n",
"(42,ARRAY[4.5,2.3,1.3,0.3],'Iris-setosa'),\n",
"(43,ARRAY[4.4,3.2,1.3,0.2],'Iris-setosa'),\n",
"(44,ARRAY[5.0,3.5,1.6,0.6],'Iris-setosa'),\n",
"(45,ARRAY[5.1,3.8,1.9,0.4],'Iris-setosa'),\n",
"(46,ARRAY[4.8,3.0,1.4,0.3],'Iris-setosa'),\n",
"(47,ARRAY[5.1,3.8,1.6,0.2],'Iris-setosa'),\n",
"(48,ARRAY[4.6,3.2,1.4,0.2],'Iris-setosa'),\n",
"(49,ARRAY[5.3,3.7,1.5,0.2],'Iris-setosa'),\n",
"(50,ARRAY[5.0,3.3,1.4,0.2],'Iris-setosa'),\n",
"(51,ARRAY[7.0,3.2,4.7,1.4],'Iris-versicolor'),\n",
"(52,ARRAY[6.4,3.2,4.5,1.5],'Iris-versicolor'),\n",
"(53,ARRAY[6.9,3.1,4.9,1.5],'Iris-versicolor'),\n",
"(54,ARRAY[5.5,2.3,4.0,1.3],'Iris-versicolor'),\n",
"(55,ARRAY[6.5,2.8,4.6,1.5],'Iris-versicolor'),\n",
"(56,ARRAY[5.7,2.8,4.5,1.3],'Iris-versicolor'),\n",
"(57,ARRAY[6.3,3.3,4.7,1.6],'Iris-versicolor'),\n",
"(58,ARRAY[4.9,2.4,3.3,1.0],'Iris-versicolor'),\n",
"(59,ARRAY[6.6,2.9,4.6,1.3],'Iris-versicolor'),\n",
"(60,ARRAY[5.2,2.7,3.9,1.4],'Iris-versicolor'),\n",
"(61,ARRAY[5.0,2.0,3.5,1.0],'Iris-versicolor'),\n",
"(62,ARRAY[5.9,3.0,4.2,1.5],'Iris-versicolor'),\n",
"(63,ARRAY[6.0,2.2,4.0,1.0],'Iris-versicolor'),\n",
"(64,ARRAY[6.1,2.9,4.7,1.4],'Iris-versicolor'),\n",
"(65,ARRAY[5.6,2.9,3.6,1.3],'Iris-versicolor'),\n",
"(66,ARRAY[6.7,3.1,4.4,1.4],'Iris-versicolor'),\n",
"(67,ARRAY[5.6,3.0,4.5,1.5],'Iris-versicolor'),\n",
"(68,ARRAY[5.8,2.7,4.1,1.0],'Iris-versicolor'),\n",
"(69,ARRAY[6.2,2.2,4.5,1.5],'Iris-versicolor'),\n",
"(70,ARRAY[5.6,2.5,3.9,1.1],'Iris-versicolor'),\n",
"(71,ARRAY[5.9,3.2,4.8,1.8],'Iris-versicolor'),\n",
"(72,ARRAY[6.1,2.8,4.0,1.3],'Iris-versicolor'),\n",
"(73,ARRAY[6.3,2.5,4.9,1.5],'Iris-versicolor'),\n",
"(74,ARRAY[6.1,2.8,4.7,1.2],'Iris-versicolor'),\n",
"(75,ARRAY[6.4,2.9,4.3,1.3],'Iris-versicolor'),\n",
"(76,ARRAY[6.6,3.0,4.4,1.4],'Iris-versicolor'),\n",
"(77,ARRAY[6.8,2.8,4.8,1.4],'Iris-versicolor'),\n",
"(78,ARRAY[6.7,3.0,5.0,1.7],'Iris-versicolor'),\n",
"(79,ARRAY[6.0,2.9,4.5,1.5],'Iris-versicolor'),\n",
"(80,ARRAY[5.7,2.6,3.5,1.0],'Iris-versicolor'),\n",
"(81,ARRAY[5.5,2.4,3.8,1.1],'Iris-versicolor'),\n",
"(82,ARRAY[5.5,2.4,3.7,1.0],'Iris-versicolor'),\n",
"(83,ARRAY[5.8,2.7,3.9,1.2],'Iris-versicolor'),\n",
"(84,ARRAY[6.0,2.7,5.1,1.6],'Iris-versicolor'),\n",
"(85,ARRAY[5.4,3.0,4.5,1.5],'Iris-versicolor'),\n",
"(86,ARRAY[6.0,3.4,4.5,1.6],'Iris-versicolor'),\n",
"(87,ARRAY[6.7,3.1,4.7,1.5],'Iris-versicolor'),\n",
"(88,ARRAY[6.3,2.3,4.4,1.3],'Iris-versicolor'),\n",
"(89,ARRAY[5.6,3.0,4.1,1.3],'Iris-versicolor'),\n",
"(90,ARRAY[5.5,2.5,4.0,1.3],'Iris-versicolor'),\n",
"(91,ARRAY[5.5,2.6,4.4,1.2],'Iris-versicolor'),\n",
"(92,ARRAY[6.1,3.0,4.6,1.4],'Iris-versicolor'),\n",
"(93,ARRAY[5.8,2.6,4.0,1.2],'Iris-versicolor'),\n",
"(94,ARRAY[5.0,2.3,3.3,1.0],'Iris-versicolor'),\n",
"(95,ARRAY[5.6,2.7,4.2,1.3],'Iris-versicolor'),\n",
"(96,ARRAY[5.7,3.0,4.2,1.2],'Iris-versicolor'),\n",
"(97,ARRAY[5.7,2.9,4.2,1.3],'Iris-versicolor'),\n",
"(98,ARRAY[6.2,2.9,4.3,1.3],'Iris-versicolor'),\n",
"(99,ARRAY[5.1,2.5,3.0,1.1],'Iris-versicolor'),\n",
"(100,ARRAY[5.7,2.8,4.1,1.3],'Iris-versicolor'),\n",
"(101,ARRAY[6.3,3.3,6.0,2.5],'Iris-virginica'),\n",
"(102,ARRAY[5.8,2.7,5.1,1.9],'Iris-virginica'),\n",
"(103,ARRAY[7.1,3.0,5.9,2.1],'Iris-virginica'),\n",
"(104,ARRAY[6.3,2.9,5.6,1.8],'Iris-virginica'),\n",
"(105,ARRAY[6.5,3.0,5.8,2.2],'Iris-virginica'),\n",
"(106,ARRAY[7.6,3.0,6.6,2.1],'Iris-virginica'),\n",
"(107,ARRAY[4.9,2.5,4.5,1.7],'Iris-virginica'),\n",
"(108,ARRAY[7.3,2.9,6.3,1.8],'Iris-virginica'),\n",
"(109,ARRAY[6.7,2.5,5.8,1.8],'Iris-virginica'),\n",
"(110,ARRAY[7.2,3.6,6.1,2.5],'Iris-virginica'),\n",
"(111,ARRAY[6.5,3.2,5.1,2.0],'Iris-virginica'),\n",
"(112,ARRAY[6.4,2.7,5.3,1.9],'Iris-virginica'),\n",
"(113,ARRAY[6.8,3.0,5.5,2.1],'Iris-virginica'),\n",
"(114,ARRAY[5.7,2.5,5.0,2.0],'Iris-virginica'),\n",
"(115,ARRAY[5.8,2.8,5.1,2.4],'Iris-virginica'),\n",
"(116,ARRAY[6.4,3.2,5.3,2.3],'Iris-virginica'),\n",
"(117,ARRAY[6.5,3.0,5.5,1.8],'Iris-virginica'),\n",
"(118,ARRAY[7.7,3.8,6.7,2.2],'Iris-virginica'),\n",
"(119,ARRAY[7.7,2.6,6.9,2.3],'Iris-virginica'),\n",
"(120,ARRAY[6.0,2.2,5.0,1.5],'Iris-virginica'),\n",
"(121,ARRAY[6.9,3.2,5.7,2.3],'Iris-virginica'),\n",
"(122,ARRAY[5.6,2.8,4.9,2.0],'Iris-virginica'),\n",
"(123,ARRAY[7.7,2.8,6.7,2.0],'Iris-virginica'),\n",
"(124,ARRAY[6.3,2.7,4.9,1.8],'Iris-virginica'),\n",
"(125,ARRAY[6.7,3.3,5.7,2.1],'Iris-virginica'),\n",
"(126,ARRAY[7.2,3.2,6.0,1.8],'Iris-virginica'),\n",
"(127,ARRAY[6.2,2.8,4.8,1.8],'Iris-virginica'),\n",
"(128,ARRAY[6.1,3.0,4.9,1.8],'Iris-virginica'),\n",
"(129,ARRAY[6.4,2.8,5.6,2.1],'Iris-virginica'),\n",
"(130,ARRAY[7.2,3.0,5.8,1.6],'Iris-virginica'),\n",
"(131,ARRAY[7.4,2.8,6.1,1.9],'Iris-virginica'),\n",
"(132,ARRAY[7.9,3.8,6.4,2.0],'Iris-virginica'),\n",
"(133,ARRAY[6.4,2.8,5.6,2.2],'Iris-virginica'),\n",
"(134,ARRAY[6.3,2.8,5.1,1.5],'Iris-virginica'),\n",
"(135,ARRAY[6.1,2.6,5.6,1.4],'Iris-virginica'),\n",
"(136,ARRAY[7.7,3.0,6.1,2.3],'Iris-virginica'),\n",
"(137,ARRAY[6.3,3.4,5.6,2.4],'Iris-virginica'),\n",
"(138,ARRAY[6.4,3.1,5.5,1.8],'Iris-virginica'),\n",
"(139,ARRAY[6.0,3.0,4.8,1.8],'Iris-virginica'),\n",
"(140,ARRAY[6.9,3.1,5.4,2.1],'Iris-virginica'),\n",
"(141,ARRAY[6.7,3.1,5.6,2.4],'Iris-virginica'),\n",
"(142,ARRAY[6.9,3.1,5.1,2.3],'Iris-virginica'),\n",
"(143,ARRAY[5.8,2.7,5.1,1.9],'Iris-virginica'),\n",
"(144,ARRAY[6.8,3.2,5.9,2.3],'Iris-virginica'),\n",
"(145,ARRAY[6.7,3.3,5.7,2.5],'Iris-virginica'),\n",
"(146,ARRAY[6.7,3.0,5.2,2.3],'Iris-virginica'),\n",
"(147,ARRAY[6.3,2.5,5.0,1.9],'Iris-virginica'),\n",
"(148,ARRAY[6.5,3.0,5.2,2.0],'Iris-virginica'),\n",
"(149,ARRAY[6.2,3.4,5.4,2.3],'Iris-virginica'),\n",
"(150,ARRAY[5.9,3.0,5.1,1.8],'Iris-virginica');\n",
"\n",
"SELECT * FROM iris_data ORDER BY id;"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Create a test/validation dataset from the training data"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Done.\n",
"1 rows affected.\n",
"1 rows affected.\n",
"1 rows affected.\n"
]
},
{
"data": {
"text/html": [
"<table>\n",
" <tr>\n",
" <th>count</th>\n",
" </tr>\n",
" <tr>\n",
" <td>120</td>\n",
" </tr>\n",
"</table>"
],
"text/plain": [
"[(120L,)]"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"%%sql\n",
"DROP TABLE IF EXISTS iris_train, iris_test;\n",
"\n",
"-- Set seed so results are reproducible\n",
"SELECT setseed(0);\n",
"\n",
"SELECT madlib.train_test_split('iris_data', -- Source table\n",
" 'iris', -- Output table root name\n",
" 0.8, -- Train proportion\n",
" NULL, -- Test proportion (0.2)\n",
" NULL, -- Strata definition\n",
" NULL, -- Output all columns\n",
" NULL, -- Sample without replacement\n",
" TRUE -- Separate output tables\n",
" );\n",
"\n",
"SELECT COUNT(*) FROM iris_train;"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"<a id=\"pp\"></a>\n",
"# 2. Call preprocessor for deep learning\n",
"Training dataset (uses training preprocessor):"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Done.\n",
"1 rows affected.\n",
"2 rows affected.\n"
]
},
{
"data": {
"text/html": [
"<table>\n",
" <tr>\n",
" <th>attributes_shape</th>\n",
" <th>class_text_shape</th>\n",
" <th>buffer_id</th>\n",
" </tr>\n",
" <tr>\n",
" <td>[60, 4]</td>\n",
" <td>[60, 3]</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <td>[60, 4]</td>\n",
" <td>[60, 3]</td>\n",
" <td>1</td>\n",
" </tr>\n",
"</table>"
],
"text/plain": [
"[([60, 4], [60, 3], 0), ([60, 4], [60, 3], 1)]"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"%%sql\n",
"DROP TABLE IF EXISTS iris_train_packed, iris_train_packed_summary;\n",
"\n",
"SELECT madlib.training_preprocessor_dl('iris_train', -- Source table\n",
" 'iris_train_packed', -- Output table\n",
" 'class_text', -- Dependent variable\n",
" 'attributes' -- Independent variable\n",
" ); \n",
"\n",
"SELECT attributes_shape, class_text_shape, buffer_id FROM iris_train_packed ORDER BY buffer_id;"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"1 rows affected.\n"
]
},
{
"data": {
"text/html": [
"<table>\n",
" <tr>\n",
" <th>source_table</th>\n",
" <th>output_table</th>\n",
" <th>dependent_varname</th>\n",
" <th>independent_varname</th>\n",
" <th>dependent_vartype</th>\n",
" <th>class_text_class_values</th>\n",
" <th>buffer_size</th>\n",
" <th>normalizing_const</th>\n",
" <th>num_classes</th>\n",
" <th>distribution_rules</th>\n",
" <th>__internal_gpu_config__</th>\n",
" </tr>\n",
" <tr>\n",
" <td>iris_train</td>\n",
" <td>iris_train_packed</td>\n",
" <td>[u'class_text']</td>\n",
" <td>[u'attributes']</td>\n",
" <td>[u'character varying']</td>\n",
" <td>[u'Iris-setosa', u'Iris-versicolor', u'Iris-virginica']</td>\n",
" <td>60</td>\n",
" <td>1.0</td>\n",
" <td>[3]</td>\n",
" <td>all_segments</td>\n",
" <td>all_segments</td>\n",
" </tr>\n",
"</table>"
],
"text/plain": [
"[(u'iris_train', u'iris_train_packed', [u'class_text'], [u'attributes'], [u'character varying'], [u'Iris-setosa', u'Iris-versicolor', u'Iris-virginica'], 60, 1.0, [3], 'all_segments', 'all_segments')]"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"%%sql\n",
"SELECT * FROM iris_train_packed_summary;"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Validation dataset (uses validation preprocessor):"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Done.\n",
"1 rows affected.\n",
"2 rows affected.\n"
]
},
{
"data": {
"text/html": [
"<table>\n",
" <tr>\n",
" <th>attributes_shape</th>\n",
" <th>class_text_shape</th>\n",
" <th>buffer_id</th>\n",
" </tr>\n",
" <tr>\n",
" <td>[15, 4]</td>\n",
" <td>[15, 3]</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <td>[15, 4]</td>\n",
" <td>[15, 3]</td>\n",
" <td>1</td>\n",
" </tr>\n",
"</table>"
],
"text/plain": [
"[([15, 4], [15, 3], 0), ([15, 4], [15, 3], 1)]"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"%%sql\n",
"DROP TABLE IF EXISTS iris_test_packed, iris_test_packed_summary;\n",
"\n",
"SELECT madlib.validation_preprocessor_dl('iris_test', -- Source table\n",
" 'iris_test_packed', -- Output table\n",
" 'class_text', -- Dependent variable\n",
" 'attributes', -- Independent variable\n",
" 'iris_train_packed' -- From training preprocessor step\n",
" ); \n",
"\n",
"SELECT attributes_shape, class_text_shape, buffer_id FROM iris_test_packed ORDER BY buffer_id;"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"1 rows affected.\n"
]
},
{
"data": {
"text/html": [
"<table>\n",
" <tr>\n",
" <th>source_table</th>\n",
" <th>output_table</th>\n",
" <th>dependent_varname</th>\n",
" <th>independent_varname</th>\n",
" <th>dependent_vartype</th>\n",
" <th>class_text_class_values</th>\n",
" <th>buffer_size</th>\n",
" <th>normalizing_const</th>\n",
" <th>num_classes</th>\n",
" <th>distribution_rules</th>\n",
" <th>__internal_gpu_config__</th>\n",
" </tr>\n",
" <tr>\n",
" <td>iris_test</td>\n",
" <td>iris_test_packed</td>\n",
" <td>[u'class_text']</td>\n",
" <td>[u'attributes']</td>\n",
" <td>[u'character varying']</td>\n",
" <td>[u'Iris-setosa', u'Iris-versicolor', u'Iris-virginica']</td>\n",
" <td>15</td>\n",
" <td>1.0</td>\n",
" <td>[3]</td>\n",
" <td>all_segments</td>\n",
" <td>all_segments</td>\n",
" </tr>\n",
"</table>"
],
"text/plain": [
"[(u'iris_test', u'iris_test_packed', [u'class_text'], [u'attributes'], [u'character varying'], [u'Iris-setosa', u'Iris-versicolor', u'Iris-virginica'], 15, 1.0, [3], 'all_segments', 'all_segments')]"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"%%sql\n",
"SELECT * FROM iris_test_packed_summary;"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"<a id=\"load\"></a>\n",
"# 3. Define and load model architecture\n",
"Import Keras libraries"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [],
"source": [
"from tensorflow import keras\n",
"from tensorflow.keras.models import Sequential\n",
"from tensorflow.keras.layers import Dense"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Define model architecture with 1 hidden layer:"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"WARNING:tensorflow:From /Users/fmcquillan/Library/Python/2.7/lib/python/site-packages/tensorflow/python/ops/init_ops.py:1251: calling __init__ (from tensorflow.python.ops.init_ops) with dtype is deprecated and will be removed in a future version.\n",
"Instructions for updating:\n",
"Call initializer instance with the dtype argument instead of passing it to the constructor\n",
"Model: \"sequential\"\n",
"_________________________________________________________________\n",
"Layer (type) Output Shape Param # \n",
"=================================================================\n",
"dense (Dense) (None, 10) 50 \n",
"_________________________________________________________________\n",
"dense_1 (Dense) (None, 10) 110 \n",
"_________________________________________________________________\n",
"dense_2 (Dense) (None, 3) 33 \n",
"=================================================================\n",
"Total params: 193\n",
"Trainable params: 193\n",
"Non-trainable params: 0\n",
"_________________________________________________________________\n"
]
}
],
"source": [
"model1 = Sequential()\n",
"model1.add(Dense(10, activation='relu', input_shape=(4,)))\n",
"model1.add(Dense(10, activation='relu'))\n",
"model1.add(Dense(3, activation='softmax'))\n",
" \n",
"model1.summary();"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'{\"class_name\": \"Sequential\", \"keras_version\": \"2.2.4-tf\", \"config\": {\"layers\": [{\"class_name\": \"Dense\", \"config\": {\"kernel_initializer\": {\"class_name\": \"GlorotUniform\", \"config\": {\"dtype\": \"float32\", \"seed\": null}}, \"name\": \"dense\", \"kernel_constraint\": null, \"bias_regularizer\": null, \"bias_constraint\": null, \"dtype\": \"float32\", \"activation\": \"relu\", \"trainable\": true, \"kernel_regularizer\": null, \"bias_initializer\": {\"class_name\": \"Zeros\", \"config\": {\"dtype\": \"float32\"}}, \"units\": 10, \"batch_input_shape\": [null, 4], \"use_bias\": true, \"activity_regularizer\": null}}, {\"class_name\": \"Dense\", \"config\": {\"kernel_initializer\": {\"class_name\": \"GlorotUniform\", \"config\": {\"dtype\": \"float32\", \"seed\": null}}, \"name\": \"dense_1\", \"kernel_constraint\": null, \"bias_regularizer\": null, \"bias_constraint\": null, \"dtype\": \"float32\", \"activation\": \"relu\", \"trainable\": true, \"kernel_regularizer\": null, \"bias_initializer\": {\"class_name\": \"Zeros\", \"config\": {\"dtype\": \"float32\"}}, \"units\": 10, \"use_bias\": true, \"activity_regularizer\": null}}, {\"class_name\": \"Dense\", \"config\": {\"kernel_initializer\": {\"class_name\": \"GlorotUniform\", \"config\": {\"dtype\": \"float32\", \"seed\": null}}, \"name\": \"dense_2\", \"kernel_constraint\": null, \"bias_regularizer\": null, \"bias_constraint\": null, \"dtype\": \"float32\", \"activation\": \"softmax\", \"trainable\": true, \"kernel_regularizer\": null, \"bias_initializer\": {\"class_name\": \"Zeros\", \"config\": {\"dtype\": \"float32\"}}, \"units\": 3, \"use_bias\": true, \"activity_regularizer\": null}}], \"name\": \"sequential\"}, \"backend\": \"tensorflow\"}'"
]
},
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"model1.to_json()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Define model architecture with 2 hidden layers:"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Model: \"sequential_1\"\n",
"_________________________________________________________________\n",
"Layer (type) Output Shape Param # \n",
"=================================================================\n",
"dense_3 (Dense) (None, 10) 50 \n",
"_________________________________________________________________\n",
"dense_4 (Dense) (None, 10) 110 \n",
"_________________________________________________________________\n",
"dense_5 (Dense) (None, 10) 110 \n",
"_________________________________________________________________\n",
"dense_6 (Dense) (None, 3) 33 \n",
"=================================================================\n",
"Total params: 303\n",
"Trainable params: 303\n",
"Non-trainable params: 0\n",
"_________________________________________________________________\n"
]
}
],
"source": [
"model2 = Sequential()\n",
"model2.add(Dense(10, activation='relu', input_shape=(4,)))\n",
"model2.add(Dense(10, activation='relu'))\n",
"model2.add(Dense(10, activation='relu'))\n",
"model2.add(Dense(3, activation='softmax'))\n",
" \n",
"model2.summary();"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'{\"class_name\": \"Sequential\", \"keras_version\": \"2.2.4-tf\", \"config\": {\"layers\": [{\"class_name\": \"Dense\", \"config\": {\"kernel_initializer\": {\"class_name\": \"GlorotUniform\", \"config\": {\"dtype\": \"float32\", \"seed\": null}}, \"name\": \"dense_3\", \"kernel_constraint\": null, \"bias_regularizer\": null, \"bias_constraint\": null, \"dtype\": \"float32\", \"activation\": \"relu\", \"trainable\": true, \"kernel_regularizer\": null, \"bias_initializer\": {\"class_name\": \"Zeros\", \"config\": {\"dtype\": \"float32\"}}, \"units\": 10, \"batch_input_shape\": [null, 4], \"use_bias\": true, \"activity_regularizer\": null}}, {\"class_name\": \"Dense\", \"config\": {\"kernel_initializer\": {\"class_name\": \"GlorotUniform\", \"config\": {\"dtype\": \"float32\", \"seed\": null}}, \"name\": \"dense_4\", \"kernel_constraint\": null, \"bias_regularizer\": null, \"bias_constraint\": null, \"dtype\": \"float32\", \"activation\": \"relu\", \"trainable\": true, \"kernel_regularizer\": null, \"bias_initializer\": {\"class_name\": \"Zeros\", \"config\": {\"dtype\": \"float32\"}}, \"units\": 10, \"use_bias\": true, \"activity_regularizer\": null}}, {\"class_name\": \"Dense\", \"config\": {\"kernel_initializer\": {\"class_name\": \"GlorotUniform\", \"config\": {\"dtype\": \"float32\", \"seed\": null}}, \"name\": \"dense_5\", \"kernel_constraint\": null, \"bias_regularizer\": null, \"bias_constraint\": null, \"dtype\": \"float32\", \"activation\": \"relu\", \"trainable\": true, \"kernel_regularizer\": null, \"bias_initializer\": {\"class_name\": \"Zeros\", \"config\": {\"dtype\": \"float32\"}}, \"units\": 10, \"use_bias\": true, \"activity_regularizer\": null}}, {\"class_name\": \"Dense\", \"config\": {\"kernel_initializer\": {\"class_name\": \"GlorotUniform\", \"config\": {\"dtype\": \"float32\", \"seed\": null}}, \"name\": \"dense_6\", \"kernel_constraint\": null, \"bias_regularizer\": null, \"bias_constraint\": null, \"dtype\": \"float32\", \"activation\": \"softmax\", \"trainable\": true, \"kernel_regularizer\": null, \"bias_initializer\": {\"class_name\": \"Zeros\", \"config\": {\"dtype\": \"float32\"}}, \"units\": 3, \"use_bias\": true, \"activity_regularizer\": null}}], \"name\": \"sequential_1\"}, \"backend\": \"tensorflow\"}'"
]
},
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"model2.to_json()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Load into model architecture table"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Done.\n",
"1 rows affected.\n",
"1 rows affected.\n",
"2 rows affected.\n"
]
},
{
"data": {
"text/html": [
"<table>\n",
" <tr>\n",
" <th>model_id</th>\n",
" <th>model_arch</th>\n",
" <th>model_weights</th>\n",
" <th>name</th>\n",
" <th>description</th>\n",
" <th>__internal_madlib_id__</th>\n",
" </tr>\n",
" <tr>\n",
" <td>1</td>\n",
" <td>{u'class_name': u'Sequential', u'keras_version': u'2.1.6', u'config': [{u'class_name': u'Dense', u'config': {u'kernel_initializer': {u'class_name': u'VarianceScaling', u'config': {u'distribution': u'uniform', u'scale': 1.0, u'seed': None, u'mode': u'fan_avg'}}, u'name': u'dense_1', u'kernel_constraint': None, u'bias_regularizer': None, u'bias_constraint': None, u'dtype': u'float32', u'activation': u'relu', u'trainable': True, u'kernel_regularizer': None, u'bias_initializer': {u'class_name': u'Zeros', u'config': {}}, u'units': 10, u'batch_input_shape': [None, 4], u'use_bias': True, u'activity_regularizer': None}}, {u'class_name': u'Dense', u'config': {u'kernel_initializer': {u'class_name': u'VarianceScaling', u'config': {u'distribution': u'uniform', u'scale': 1.0, u'seed': None, u'mode': u'fan_avg'}}, u'name': u'dense_2', u'kernel_constraint': None, u'bias_regularizer': None, u'bias_constraint': None, u'activation': u'relu', u'trainable': True, u'kernel_regularizer': None, u'bias_initializer': {u'class_name': u'Zeros', u'config': {}}, u'units': 10, u'use_bias': True, u'activity_regularizer': None}}, {u'class_name': u'Dense', u'config': {u'kernel_initializer': {u'class_name': u'VarianceScaling', u'config': {u'distribution': u'uniform', u'scale': 1.0, u'seed': None, u'mode': u'fan_avg'}}, u'name': u'dense_3', u'kernel_constraint': None, u'bias_regularizer': None, u'bias_constraint': None, u'activation': u'softmax', u'trainable': True, u'kernel_regularizer': None, u'bias_initializer': {u'class_name': u'Zeros', u'config': {}}, u'units': 3, u'use_bias': True, u'activity_regularizer': None}}], u'backend': u'tensorflow'}</td>\n",
" <td>None</td>\n",
" <td>Sophie</td>\n",
" <td>MLP with 1 hidden layer</td>\n",
" <td>__madlib_temp_71395301_1614988659_10232289__</td>\n",
" </tr>\n",
" <tr>\n",
" <td>2</td>\n",
" <td>{u'class_name': u'Sequential', u'keras_version': u'2.1.6', u'config': [{u'class_name': u'Dense', u'config': {u'kernel_initializer': {u'class_name': u'VarianceScaling', u'config': {u'distribution': u'uniform', u'scale': 1.0, u'seed': None, u'mode': u'fan_avg'}}, u'name': u'dense_4', u'kernel_constraint': None, u'bias_regularizer': None, u'bias_constraint': None, u'dtype': u'float32', u'activation': u'relu', u'trainable': True, u'kernel_regularizer': None, u'bias_initializer': {u'class_name': u'Zeros', u'config': {}}, u'units': 10, u'batch_input_shape': [None, 4], u'use_bias': True, u'activity_regularizer': None}}, {u'class_name': u'Dense', u'config': {u'kernel_initializer': {u'class_name': u'VarianceScaling', u'config': {u'distribution': u'uniform', u'scale': 1.0, u'seed': None, u'mode': u'fan_avg'}}, u'name': u'dense_5', u'kernel_constraint': None, u'bias_regularizer': None, u'bias_constraint': None, u'activation': u'relu', u'trainable': True, u'kernel_regularizer': None, u'bias_initializer': {u'class_name': u'Zeros', u'config': {}}, u'units': 10, u'use_bias': True, u'activity_regularizer': None}}, {u'class_name': u'Dense', u'config': {u'kernel_initializer': {u'class_name': u'VarianceScaling', u'config': {u'distribution': u'uniform', u'scale': 1.0, u'seed': None, u'mode': u'fan_avg'}}, u'name': u'dense_6', u'kernel_constraint': None, u'bias_regularizer': None, u'bias_constraint': None, u'activation': u'relu', u'trainable': True, u'kernel_regularizer': None, u'bias_initializer': {u'class_name': u'Zeros', u'config': {}}, u'units': 10, u'use_bias': True, u'activity_regularizer': None}}, {u'class_name': u'Dense', u'config': {u'kernel_initializer': {u'class_name': u'VarianceScaling', u'config': {u'distribution': u'uniform', u'scale': 1.0, u'seed': None, u'mode': u'fan_avg'}}, u'name': u'dense_7', u'kernel_constraint': None, u'bias_regularizer': None, u'bias_constraint': None, u'activation': u'softmax', u'trainable': True, u'kernel_regularizer': None, u'bias_initializer': {u'class_name': u'Zeros', u'config': {}}, u'units': 3, u'use_bias': True, u'activity_regularizer': None}}], u'backend': u'tensorflow'}</td>\n",
" <td>None</td>\n",
" <td>Maria</td>\n",
" <td>MLP with 2 hidden layers</td>\n",
" <td>__madlib_temp_60560187_1614988660_9612153__</td>\n",
" </tr>\n",
"</table>"
],
"text/plain": [
"[(1, {u'class_name': u'Sequential', u'keras_version': u'2.1.6', u'config': [{u'class_name': u'Dense', u'config': {u'kernel_initializer': {u'class_name': u' ... (1340 characters truncated) ... s_initializer': {u'class_name': u'Zeros', u'config': {}}, u'units': 3, u'use_bias': True, u'activity_regularizer': None}}], u'backend': u'tensorflow'}, None, u'Sophie', u'MLP with 1 hidden layer', u'__madlib_temp_71395301_1614988659_10232289__'),\n",
" (2, {u'class_name': u'Sequential', u'keras_version': u'2.1.6', u'config': [{u'class_name': u'Dense', u'config': {u'kernel_initializer': {u'class_name': u' ... (1835 characters truncated) ... s_initializer': {u'class_name': u'Zeros', u'config': {}}, u'units': 3, u'use_bias': True, u'activity_regularizer': None}}], u'backend': u'tensorflow'}, None, u'Maria', u'MLP with 2 hidden layers', u'__madlib_temp_60560187_1614988660_9612153__')]"
]
},
"execution_count": 15,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"%%sql\n",
"DROP TABLE IF EXISTS model_arch_library;\n",
"\n",
"SELECT madlib.load_keras_model('model_arch_library', -- Output table,\n",
" \n",
"$$\n",
"{\"class_name\": \"Sequential\", \"keras_version\": \"2.1.6\", \"config\": [{\"class_name\": \"Dense\", \"config\": {\"kernel_initializer\": {\"class_name\": \"VarianceScaling\", \"config\": {\"distribution\": \"uniform\", \"scale\": 1.0, \"seed\": null, \"mode\": \"fan_avg\"}}, \"name\": \"dense_1\", \"kernel_constraint\": null, \"bias_regularizer\": null, \"bias_constraint\": null, \"dtype\": \"float32\", \"activation\": \"relu\", \"trainable\": true, \"kernel_regularizer\": null, \"bias_initializer\": {\"class_name\": \"Zeros\", \"config\": {}}, \"units\": 10, \"batch_input_shape\": [null, 4], \"use_bias\": true, \"activity_regularizer\": null}}, {\"class_name\": \"Dense\", \"config\": {\"kernel_initializer\": {\"class_name\": \"VarianceScaling\", \"config\": {\"distribution\": \"uniform\", \"scale\": 1.0, \"seed\": null, \"mode\": \"fan_avg\"}}, \"name\": \"dense_2\", \"kernel_constraint\": null, \"bias_regularizer\": null, \"bias_constraint\": null, \"activation\": \"relu\", \"trainable\": true, \"kernel_regularizer\": null, \"bias_initializer\": {\"class_name\": \"Zeros\", \"config\": {}}, \"units\": 10, \"use_bias\": true, \"activity_regularizer\": null}}, {\"class_name\": \"Dense\", \"config\": {\"kernel_initializer\": {\"class_name\": \"VarianceScaling\", \"config\": {\"distribution\": \"uniform\", \"scale\": 1.0, \"seed\": null, \"mode\": \"fan_avg\"}}, \"name\": \"dense_3\", \"kernel_constraint\": null, \"bias_regularizer\": null, \"bias_constraint\": null, \"activation\": \"softmax\", \"trainable\": true, \"kernel_regularizer\": null, \"bias_initializer\": {\"class_name\": \"Zeros\", \"config\": {}}, \"units\": 3, \"use_bias\": true, \"activity_regularizer\": null}}], \"backend\": \"tensorflow\"}\n",
"$$\n",
"::json, -- JSON blob\n",
" NULL, -- Weights\n",
" 'Sophie', -- Name\n",
" 'MLP with 1 hidden layer' -- Descr\n",
");\n",
"\n",
"SELECT madlib.load_keras_model('model_arch_library', -- Output table,\n",
" \n",
"$$\n",
"{\"class_name\": \"Sequential\", \"keras_version\": \"2.1.6\", \"config\": [{\"class_name\": \"Dense\", \"config\": {\"kernel_initializer\": {\"class_name\": \"VarianceScaling\", \"config\": {\"distribution\": \"uniform\", \"scale\": 1.0, \"seed\": null, \"mode\": \"fan_avg\"}}, \"name\": \"dense_4\", \"kernel_constraint\": null, \"bias_regularizer\": null, \"bias_constraint\": null, \"dtype\": \"float32\", \"activation\": \"relu\", \"trainable\": true, \"kernel_regularizer\": null, \"bias_initializer\": {\"class_name\": \"Zeros\", \"config\": {}}, \"units\": 10, \"batch_input_shape\": [null, 4], \"use_bias\": true, \"activity_regularizer\": null}}, {\"class_name\": \"Dense\", \"config\": {\"kernel_initializer\": {\"class_name\": \"VarianceScaling\", \"config\": {\"distribution\": \"uniform\", \"scale\": 1.0, \"seed\": null, \"mode\": \"fan_avg\"}}, \"name\": \"dense_5\", \"kernel_constraint\": null, \"bias_regularizer\": null, \"bias_constraint\": null, \"activation\": \"relu\", \"trainable\": true, \"kernel_regularizer\": null, \"bias_initializer\": {\"class_name\": \"Zeros\", \"config\": {}}, \"units\": 10, \"use_bias\": true, \"activity_regularizer\": null}}, {\"class_name\": \"Dense\", \"config\": {\"kernel_initializer\": {\"class_name\": \"VarianceScaling\", \"config\": {\"distribution\": \"uniform\", \"scale\": 1.0, \"seed\": null, \"mode\": \"fan_avg\"}}, \"name\": \"dense_6\", \"kernel_constraint\": null, \"bias_regularizer\": null, \"bias_constraint\": null, \"activation\": \"relu\", \"trainable\": true, \"kernel_regularizer\": null, \"bias_initializer\": {\"class_name\": \"Zeros\", \"config\": {}}, \"units\": 10, \"use_bias\": true, \"activity_regularizer\": null}}, {\"class_name\": \"Dense\", \"config\": {\"kernel_initializer\": {\"class_name\": \"VarianceScaling\", \"config\": {\"distribution\": \"uniform\", \"scale\": 1.0, \"seed\": null, \"mode\": \"fan_avg\"}}, \"name\": \"dense_7\", \"kernel_constraint\": null, \"bias_regularizer\": null, \"bias_constraint\": null, \"activation\": \"softmax\", \"trainable\": true, \"kernel_regularizer\": null, \"bias_initializer\": {\"class_name\": \"Zeros\", \"config\": {}}, \"units\": 3, \"use_bias\": true, \"activity_regularizer\": null}}], \"backend\": \"tensorflow\"}\n",
"$$\n",
"::json, -- JSON blob\n",
" NULL, -- Weights\n",
" 'Maria', -- Name\n",
" 'MLP with 2 hidden layers' -- Descr\n",
");\n",
"\n",
"SELECT * FROM model_arch_library ORDER BY model_id;"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"<a id=\"hyperband\"></a>\n",
"# 4. Hyperband"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Print schedule for run:"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Done.\n",
"1 rows affected.\n",
"6 rows affected.\n"
]
},
{
"data": {
"text/html": [
"<table>\n",
" <tr>\n",
" <th>s</th>\n",
" <th>i</th>\n",
" <th>n_i</th>\n",
" <th>r_i</th>\n",
" </tr>\n",
" <tr>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" <td>9</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <td>2</td>\n",
" <td>1</td>\n",
" <td>3</td>\n",
" <td>3</td>\n",
" </tr>\n",
" <tr>\n",
" <td>2</td>\n",
" <td>2</td>\n",
" <td>1</td>\n",
" <td>9</td>\n",
" </tr>\n",
" <tr>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>3</td>\n",
" </tr>\n",
" <tr>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>9</td>\n",
" </tr>\n",
" <tr>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>9</td>\n",
" </tr>\n",
"</table>"
],
"text/plain": [
"[(2, 0, 9, 1),\n",
" (2, 1, 3, 3),\n",
" (2, 2, 1, 9),\n",
" (1, 0, 3, 3),\n",
" (1, 1, 1, 9),\n",
" (0, 0, 3, 9)]"
]
},
"execution_count": 16,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"%%sql\n",
"DROP TABLE IF EXISTS hb_schedule;\n",
"SELECT madlib.hyperband_schedule ('hb_schedule', \n",
" 9,\n",
" 3,\n",
" 0);\n",
"SELECT * FROM hb_schedule ORDER BY s DESC, i;"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Done.\n",
"1 rows affected.\n"
]
},
{
"data": {
"text/html": [
"<table>\n",
" <tr>\n",
" <th>madlib_keras_automl</th>\n",
" </tr>\n",
" <tr>\n",
" <td></td>\n",
" </tr>\n",
"</table>"
],
"text/plain": [
"[('',)]"
]
},
"execution_count": 17,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"%%sql\n",
"DROP TABLE IF EXISTS automl_output, automl_output_info, automl_output_summary, automl_mst_table, automl_mst_table_summary;\n",
"\n",
"SELECT madlib.madlib_keras_automl('iris_train_packed', -- source table\n",
" 'automl_output', -- model output table\n",
" 'model_arch_library', -- model architecture table\n",
" 'automl_mst_table', -- model selection output table\n",
" ARRAY[1,2], -- model IDs\n",
" $${\n",
" 'loss': ['categorical_crossentropy'], \n",
" 'optimizer_params_list': [ \n",
" {'optimizer': ['Adam'],'lr': [0.001, 0.1, 'log']},\n",
" {'optimizer': ['RMSprop'],'lr': [0.001, 0.1, 'log']}\n",
" ],\n",
" 'metrics': ['accuracy']\n",
" } $$, -- compile param grid\n",
" $${'batch_size': [4, 8], 'epochs': [1]}$$, -- fit params grid\n",
" 'hyperband', -- autoML method\n",
" 'R=9, eta=3, skip_last=0', -- autoML params\n",
" NULL, -- random state\n",
" NULL, -- object table\n",
" FALSE, -- use GPUs\n",
" 'iris_test_packed', -- validation table\n",
" 1, -- metrics compute freq\n",
" NULL, -- name\n",
" NULL); -- descr"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"View the model summary"
]
},
{
"cell_type": "code",
"execution_count": 18,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"1 rows affected.\n"
]
},
{
"data": {
"text/html": [
"<table>\n",
" <tr>\n",
" <th>source_table</th>\n",
" <th>validation_table</th>\n",
" <th>model</th>\n",
" <th>model_info</th>\n",
" <th>dependent_varname</th>\n",
" <th>independent_varname</th>\n",
" <th>model_arch_table</th>\n",
" <th>model_selection_table</th>\n",
" <th>automl_method</th>\n",
" <th>automl_params</th>\n",
" <th>random_state</th>\n",
" <th>object_table</th>\n",
" <th>use_gpus</th>\n",
" <th>metrics_compute_frequency</th>\n",
" <th>name</th>\n",
" <th>description</th>\n",
" <th>start_training_time</th>\n",
" <th>end_training_time</th>\n",
" <th>madlib_version</th>\n",
" <th>num_classes</th>\n",
" <th>class_text_class_values</th>\n",
" <th>dependent_vartype</th>\n",
" <th>normalizing_const</th>\n",
" </tr>\n",
" <tr>\n",
" <td>iris_train_packed</td>\n",
" <td>iris_test_packed</td>\n",
" <td>automl_output</td>\n",
" <td>automl_output_info</td>\n",
" <td>[u'class_text']</td>\n",
" <td>[u'attributes']</td>\n",
" <td>model_arch_library</td>\n",
" <td>automl_mst_table</td>\n",
" <td>hyperband</td>\n",
" <td>R=9, eta=3, skip_last=0</td>\n",
" <td>None</td>\n",
" <td>None</td>\n",
" <td>False</td>\n",
" <td>1</td>\n",
" <td>None</td>\n",
" <td>None</td>\n",
" <td>2021-03-05 23:57:44</td>\n",
" <td>2021-03-05 23:59:24</td>\n",
" <td>1.18.0-dev</td>\n",
" <td>[1]</td>\n",
" <td>[u'Iris-setosa', u'Iris-versicolor', u'Iris-virginica']</td>\n",
" <td>[u'character varying']</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
"</table>"
],
"text/plain": [
"[(u'iris_train_packed', u'iris_test_packed', u'automl_output', u'automl_output_info', [u'class_text'], [u'attributes'], u'model_arch_library', u'automl_mst_table', u'hyperband', u'R=9, eta=3, skip_last=0', None, None, False, 1, None, None, datetime.datetime(2021, 3, 5, 23, 57, 44), datetime.datetime(2021, 3, 5, 23, 59, 24), u'1.18.0-dev', [1], [u'Iris-setosa', u'Iris-versicolor', u'Iris-virginica'], [u'character varying'], 1.0)]"
]
},
"execution_count": 18,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"%%sql\n",
"SELECT * FROM automl_output_summary;"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"View results for each model"
]
},
{
"cell_type": "code",
"execution_count": 19,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"15 rows affected.\n"
]
},
{
"data": {
"text/html": [
"<table>\n",
" <tr>\n",
" <th>mst_key</th>\n",
" <th>model_id</th>\n",
" <th>compile_params</th>\n",
" <th>fit_params</th>\n",
" <th>model_type</th>\n",
" <th>model_size</th>\n",
" <th>metrics_elapsed_time</th>\n",
" <th>metrics_type</th>\n",
" <th>loss_type</th>\n",
" <th>training_metrics_final</th>\n",
" <th>training_loss_final</th>\n",
" <th>training_metrics</th>\n",
" <th>training_loss</th>\n",
" <th>validation_metrics_final</th>\n",
" <th>validation_loss_final</th>\n",
" <th>validation_metrics</th>\n",
" <th>validation_loss</th>\n",
" <th>metrics_iters</th>\n",
" <th>s</th>\n",
" <th>i</th>\n",
" </tr>\n",
" <tr>\n",
" <td>10</td>\n",
" <td>1</td>\n",
" <td>optimizer='Adam(lr=0.04232194170481019)',metrics=['accuracy'],loss='categorical_crossentropy'</td>\n",
" <td>epochs=1,batch_size=8</td>\n",
" <td>madlib_keras</td>\n",
" <td>0.75390625</td>\n",
" <td>[21.911346912384, 29.2674539089203, 36.8268938064575, 44.9022789001465, 51.1760609149933, 57.6593999862671, 64.184476852417, 70.5566418170929, 77.0253269672394, 83.4826798439026, 90.1138219833374, 96.4566838741302]</td>\n",
" <td>[u'accuracy']</td>\n",
" <td>categorical_crossentropy</td>\n",
" <td>0.975000023842</td>\n",
" <td>0.0775080993772</td>\n",
" <td>[0.791666686534882, 0.608333349227905, 0.966666638851166, 0.975000023841858, 0.966666638851166, 0.800000011920929, 0.975000023841858, 0.683333337306976, 0.733333349227905, 0.949999988079071, 0.949999988079071, 0.975000023841858]</td>\n",
" <td>[0.374035209417343, 0.732228577136993, 0.170820266008377, 0.112313792109489, 0.172022193670273, 0.384404003620148, 0.115418829023838, 0.450868725776672, 0.457187473773956, 0.140348106622696, 0.15950845181942, 0.0775080993771553]</td>\n",
" <td>1.0</td>\n",
" <td>0.0383280552924</td>\n",
" <td>[0.899999976158142, 0.566666662693024, 0.966666638851166, 1.0, 1.0, 0.800000011920929, 0.966666638851166, 0.833333313465118, 0.899999976158142, 1.0, 0.899999976158142, 1.0]</td>\n",
" <td>[0.273769021034241, 0.709117114543915, 0.154145583510399, 0.093109056353569, 0.130981177091599, 0.318724304437637, 0.102762393653393, 0.268609821796417, 0.253254026174545, 0.103913448750973, 0.194639429450035, 0.0383280552923679]</td>\n",
" <td>[2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13]</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <td>13</td>\n",
" <td>1</td>\n",
" <td>optimizer='Adam(lr=0.009905852828976726)',metrics=['accuracy'],loss='categorical_crossentropy'</td>\n",
" <td>epochs=1,batch_size=4</td>\n",
" <td>madlib_keras</td>\n",
" <td>0.75390625</td>\n",
" <td>[44.6836378574371, 50.92365193367, 57.3649659156799, 63.7576060295105, 70.1174209117889, 76.788703918457, 83.2217078208923, 89.8764188289642, 96.2273638248444]</td>\n",
" <td>[u'accuracy']</td>\n",
" <td>categorical_crossentropy</td>\n",
" <td>0.975000023842</td>\n",
" <td>0.0799522325397</td>\n",
" <td>[0.949999988079071, 0.791666686534882, 0.800000011920929, 0.850000023841858, 0.958333313465118, 0.975000023841858, 0.899999976158142, 0.975000023841858, 0.975000023841858]</td>\n",
" <td>[0.447714686393738, 0.36309215426445, 0.324623554944992, 0.301780551671982, 0.142947062849998, 0.120139442384243, 0.255296260118484, 0.0816238224506378, 0.0799522325396538]</td>\n",
" <td>0.966666638851</td>\n",
" <td>0.0760450512171</td>\n",
" <td>[0.966666638851166, 0.899999976158142, 0.800000011920929, 0.899999976158142, 0.966666638851166, 0.966666638851166, 0.899999976158142, 1.0, 0.966666638851166]</td>\n",
" <td>[0.370463252067566, 0.25237438082695, 0.317549884319305, 0.187985330820084, 0.104904659092426, 0.112288065254688, 0.160248279571533, 0.0687147378921509, 0.0760450512170792]</td>\n",
" <td>[5, 6, 7, 8, 9, 10, 11, 12, 13]</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <td>5</td>\n",
" <td>2</td>\n",
" <td>optimizer='Adam(lr=0.01678679876224294)',metrics=['accuracy'],loss='categorical_crossentropy'</td>\n",
" <td>epochs=1,batch_size=8</td>\n",
" <td>madlib_keras</td>\n",
" <td>1.18359375</td>\n",
" <td>[11.5813798904419, 21.0226759910583, 28.4713099002838, 35.9315679073334, 44.4656569957733, 50.7044010162354, 57.1448848247528, 63.4595718383789, 69.8967549800873, 76.3639938831329, 82.7779839038849, 89.6248579025269, 95.9936518669128]</td>\n",
" <td>[u'accuracy']</td>\n",
" <td>categorical_crossentropy</td>\n",
" <td>0.958333313465</td>\n",
" <td>0.113370150328</td>\n",
" <td>[0.641666650772095, 0.908333361148834, 0.891666650772095, 0.891666650772095, 0.866666674613953, 0.941666662693024, 0.941666662693024, 0.933333337306976, 0.933333337306976, 0.858333349227905, 0.966666638851166, 0.958333313465118, 0.958333313465118]</td>\n",
" <td>[0.656313836574554, 0.41341444849968, 0.324400961399078, 0.304112106561661, 0.336616456508636, 0.160554125905037, 0.135852053761482, 0.159805878996849, 0.174078181385994, 0.316538035869598, 0.104411341249943, 0.105065681040287, 0.113370150327682]</td>\n",
" <td>0.966666638851</td>\n",
" <td>0.121701933444</td>\n",
" <td>[0.766666650772095, 0.933333337306976, 0.866666674613953, 0.866666674613953, 0.899999976158142, 0.966666638851166, 0.899999976158142, 0.966666638851166, 0.966666638851166, 0.899999976158142, 0.966666638851166, 0.966666638851166, 0.966666638851166]</td>\n",
" <td>[0.563848853111267, 0.330921590328217, 0.292684972286224, 0.273869335651398, 0.317834258079529, 0.144475534558296, 0.147552534937859, 0.153202146291733, 0.158350095152855, 0.22741986811161, 0.114596471190453, 0.117612592875957, 0.121701933443546]</td>\n",
" <td>[1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13]</td>\n",
" <td>2</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <td>14</td>\n",
" <td>2</td>\n",
" <td>optimizer='RMSprop(lr=0.01930169481426345)',metrics=['accuracy'],loss='categorical_crossentropy'</td>\n",
" <td>epochs=1,batch_size=4</td>\n",
" <td>madlib_keras</td>\n",
" <td>1.18359375</td>\n",
" <td>[44.2033138275146, 50.4514999389648, 56.8880548477173, 63.2074518203735, 69.5435798168182, 76.1080069541931, 82.519660949707, 89.1418299674988, 95.518424987793]</td>\n",
" <td>[u'accuracy']</td>\n",
" <td>categorical_crossentropy</td>\n",
" <td>0.941666662693</td>\n",
" <td>0.206491559744</td>\n",
" <td>[0.566666662693024, 0.916666686534882, 0.883333325386047, 0.958333313465118, 0.841666638851166, 0.875, 0.783333361148834, 0.766666650772095, 0.941666662693024]</td>\n",
" <td>[0.774700284004211, 0.651901543140411, 0.496851295232773, 0.405008375644684, 0.356276631355286, 0.340960919857025, 0.381286114454269, 0.388935476541519, 0.206491559743881]</td>\n",
" <td>0.966666638851</td>\n",
" <td>0.170937761664</td>\n",
" <td>[0.733333349227905, 0.933333337306976, 0.866666674613953, 0.933333337306976, 0.866666674613953, 0.866666674613953, 0.833333313465118, 0.833333313465118, 0.966666638851166]</td>\n",
" <td>[0.76544976234436, 0.657529413700104, 0.4853755235672, 0.377188384532928, 0.356318116188049, 0.332274377346039, 0.372768431901932, 0.397462010383606, 0.170937761664391]</td>\n",
" <td>[5, 6, 7, 8, 9, 10, 11, 12, 13]</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <td>6</td>\n",
" <td>1</td>\n",
" <td>optimizer='Adam(lr=0.011578246765795313)',metrics=['accuracy'],loss='categorical_crossentropy'</td>\n",
" <td>epochs=1,batch_size=8</td>\n",
" <td>madlib_keras</td>\n",
" <td>0.75390625</td>\n",
" <td>[12.2524900436401, 22.163911819458, 29.4894979000092, 37.043762922287]</td>\n",
" <td>[u'accuracy']</td>\n",
" <td>categorical_crossentropy</td>\n",
" <td>0.791666686535</td>\n",
" <td>0.595036566257</td>\n",
" <td>[0.0333333350718021, 0.633333325386047, 0.816666662693024, 0.791666686534882]</td>\n",
" <td>[0.947992205619812, 0.782966256141663, 0.679944217205048, 0.595036566257477]</td>\n",
" <td>0.899999976158</td>\n",
" <td>0.56917822361</td>\n",
" <td>[0.100000001490116, 0.766666650772095, 0.933333337306976, 0.899999976158142]</td>\n",
" <td>[0.972650408744812, 0.776390075683594, 0.681758761405945, 0.569178223609924]</td>\n",
" <td>[1, 2, 3, 4]</td>\n",
" <td>2</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <td>12</td>\n",
" <td>1</td>\n",
" <td>optimizer='Adam(lr=0.0699102360375282)',metrics=['accuracy'],loss='categorical_crossentropy'</td>\n",
" <td>epochs=1,batch_size=8</td>\n",
" <td>madlib_keras</td>\n",
" <td>0.75390625</td>\n",
" <td>[22.5178759098053, 29.7163498401642, 37.2609059810638]</td>\n",
" <td>[u'accuracy']</td>\n",
" <td>categorical_crossentropy</td>\n",
" <td>0.699999988079</td>\n",
" <td>0.389858365059</td>\n",
" <td>[0.641666650772095, 0.641666650772095, 0.699999988079071]</td>\n",
" <td>[0.79219126701355, 0.460052192211151, 0.389858365058899]</td>\n",
" <td>0.866666674614</td>\n",
" <td>0.250768661499</td>\n",
" <td>[0.766666650772095, 0.766666650772095, 0.866666674613953]</td>\n",
" <td>[0.765598654747009, 0.334016799926758, 0.250768661499023]</td>\n",
" <td>[2, 3, 4]</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>optimizer='RMSprop(lr=0.024714880320122704)',metrics=['accuracy'],loss='categorical_crossentropy'</td>\n",
" <td>epochs=1,batch_size=4</td>\n",
" <td>madlib_keras</td>\n",
" <td>0.75390625</td>\n",
" <td>[12.0343589782715, 21.4979238510132, 29.0434989929199, 36.4899458885193]</td>\n",
" <td>[u'accuracy']</td>\n",
" <td>categorical_crossentropy</td>\n",
" <td>0.649999976158</td>\n",
" <td>0.673553228378</td>\n",
" <td>[0.691666662693024, 0.841666638851166, 0.983333349227905, 0.649999976158142]</td>\n",
" <td>[0.388701051473618, 0.424284487962723, 0.180928915739059, 0.673553228378296]</td>\n",
" <td>0.800000011921</td>\n",
" <td>0.384207844734</td>\n",
" <td>[0.833333313465118, 0.800000011920929, 0.966666638851166, 0.800000011920929]</td>\n",
" <td>[0.255310624837875, 0.357394397258759, 0.147510275244713, 0.384207844734192]</td>\n",
" <td>[1, 2, 3, 4]</td>\n",
" <td>2</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <td>15</td>\n",
" <td>2</td>\n",
" <td>optimizer='Adam(lr=0.05573574908119242)',metrics=['accuracy'],loss='categorical_crossentropy'</td>\n",
" <td>epochs=1,batch_size=8</td>\n",
" <td>madlib_keras</td>\n",
" <td>1.18359375</td>\n",
" <td>[45.168872833252, 51.7013738155365, 58.1221590042114, 64.4642739295959, 70.8308379650116, 77.295382976532, 83.7621510028839, 90.3811860084534, 96.7183079719543]</td>\n",
" <td>[u'accuracy']</td>\n",
" <td>categorical_crossentropy</td>\n",
" <td>0.816666662693</td>\n",
" <td>0.457783430815</td>\n",
" <td>[0.358333319425583, 0.925000011920929, 0.675000011920929, 0.733333349227905, 0.949999988079071, 0.666666686534882, 0.741666674613953, 0.908333361148834, 0.816666662693024]</td>\n",
" <td>[1.03486049175262, 0.43449866771698, 0.842896223068237, 0.392013370990753, 0.195524752140045, 0.572380185127258, 0.43743160367012, 0.278554767370224, 0.457783430814743]</td>\n",
" <td>0.733333349228</td>\n",
" <td>0.670406579971</td>\n",
" <td>[0.233333334326744, 0.966666638851166, 0.866666674613953, 0.866666674613953, 0.966666638851166, 0.666666686534882, 0.899999976158142, 0.933333337306976, 0.733333349227905]</td>\n",
" <td>[1.05548679828644, 0.372740298509598, 0.427788466215134, 0.282503575086594, 0.135918349027634, 0.589654743671417, 0.253296822309494, 0.159830048680305, 0.670406579971313]</td>\n",
" <td>[5, 6, 7, 8, 9, 10, 11, 12, 13]</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <td>8</td>\n",
" <td>1</td>\n",
" <td>optimizer='RMSprop(lr=0.09641245863612281)',metrics=['accuracy'],loss='categorical_crossentropy'</td>\n",
" <td>epochs=1,batch_size=4</td>\n",
" <td>madlib_keras</td>\n",
" <td>0.75390625</td>\n",
" <td>[12.7177708148956]</td>\n",
" <td>[u'accuracy']</td>\n",
" <td>categorical_crossentropy</td>\n",
" <td>0.658333361149</td>\n",
" <td>1.25986480713</td>\n",
" <td>[0.658333361148834]</td>\n",
" <td>[1.25986480712891]</td>\n",
" <td>0.633333325386</td>\n",
" <td>1.26717245579</td>\n",
" <td>[0.633333325386047]</td>\n",
" <td>[1.26717245578766]</td>\n",
" <td>[1]</td>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <td>2</td>\n",
" <td>1</td>\n",
" <td>optimizer='RMSprop(lr=0.003730347382813742)',metrics=['accuracy'],loss='categorical_crossentropy'</td>\n",
" <td>epochs=1,batch_size=4</td>\n",
" <td>madlib_keras</td>\n",
" <td>0.75390625</td>\n",
" <td>[11.1050899028778]</td>\n",
" <td>[u'accuracy']</td>\n",
" <td>categorical_crossentropy</td>\n",
" <td>0.600000023842</td>\n",
" <td>1.23435640335</td>\n",
" <td>[0.600000023841858]</td>\n",
" <td>[1.23435640335083]</td>\n",
" <td>0.5</td>\n",
" <td>1.37250542641</td>\n",
" <td>[0.5]</td>\n",
" <td>[1.37250542640686]</td>\n",
" <td>[1]</td>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <td>7</td>\n",
" <td>1</td>\n",
" <td>optimizer='Adam(lr=0.0018352035707327032)',metrics=['accuracy'],loss='categorical_crossentropy'</td>\n",
" <td>epochs=1,batch_size=8</td>\n",
" <td>madlib_keras</td>\n",
" <td>0.75390625</td>\n",
" <td>[11.3283720016479]</td>\n",
" <td>[u'accuracy']</td>\n",
" <td>categorical_crossentropy</td>\n",
" <td>0.466666668653</td>\n",
" <td>1.01645076275</td>\n",
" <td>[0.466666668653488]</td>\n",
" <td>[1.01645076274872]</td>\n",
" <td>0.433333337307</td>\n",
" <td>1.01912522316</td>\n",
" <td>[0.433333337306976]</td>\n",
" <td>[1.01912522315979]</td>\n",
" <td>[1]</td>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <td>4</td>\n",
" <td>2</td>\n",
" <td>optimizer='Adam(lr=0.03837714620063437)',metrics=['accuracy'],loss='categorical_crossentropy'</td>\n",
" <td>epochs=1,batch_size=4</td>\n",
" <td>madlib_keras</td>\n",
" <td>1.18359375</td>\n",
" <td>[12.5016968250275]</td>\n",
" <td>[u'accuracy']</td>\n",
" <td>categorical_crossentropy</td>\n",
" <td>0.308333337307</td>\n",
" <td>1.0995465517</td>\n",
" <td>[0.308333337306976]</td>\n",
" <td>[1.09954655170441]</td>\n",
" <td>0.433333337307</td>\n",
" <td>1.0980553627</td>\n",
" <td>[0.433333337306976]</td>\n",
" <td>[1.09805536270142]</td>\n",
" <td>[1]</td>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <td>9</td>\n",
" <td>2</td>\n",
" <td>optimizer='Adam(lr=0.0017052377620857802)',metrics=['accuracy'],loss='categorical_crossentropy'</td>\n",
" <td>epochs=1,batch_size=8</td>\n",
" <td>madlib_keras</td>\n",
" <td>1.18359375</td>\n",
" <td>[10.8097839355469]</td>\n",
" <td>[u'accuracy']</td>\n",
" <td>categorical_crossentropy</td>\n",
" <td>0.341666668653</td>\n",
" <td>1.28075575829</td>\n",
" <td>[0.341666668653488]</td>\n",
" <td>[1.28075575828552]</td>\n",
" <td>0.366666674614</td>\n",
" <td>1.43494951725</td>\n",
" <td>[0.366666674613953]</td>\n",
" <td>[1.43494951725006]</td>\n",
" <td>[1]</td>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <td>11</td>\n",
" <td>2</td>\n",
" <td>optimizer='Adam(lr=0.0015217424326594508)',metrics=['accuracy'],loss='categorical_crossentropy'</td>\n",
" <td>epochs=1,batch_size=8</td>\n",
" <td>madlib_keras</td>\n",
" <td>1.18359375</td>\n",
" <td>[21.2741727828979, 28.7427089214325, 36.1846778392792]</td>\n",
" <td>[u'accuracy']</td>\n",
" <td>categorical_crossentropy</td>\n",
" <td>0.333333343267</td>\n",
" <td>1.07403242588</td>\n",
" <td>[0.474999994039536, 0.358333319425583, 0.333333343267441]</td>\n",
" <td>[1.08657968044281, 1.07721281051636, 1.07403242588043]</td>\n",
" <td>0.333333343267</td>\n",
" <td>1.09314000607</td>\n",
" <td>[0.433333337306976, 0.300000011920929, 0.333333343267441]</td>\n",
" <td>[1.11294913291931, 1.10347521305084, 1.09314000606537]</td>\n",
" <td>[2, 3, 4]</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <td>3</td>\n",
" <td>1</td>\n",
" <td>optimizer='RMSprop(lr=0.051964270528848694)',metrics=['accuracy'],loss='categorical_crossentropy'</td>\n",
" <td>epochs=1,batch_size=4</td>\n",
" <td>madlib_keras</td>\n",
" <td>0.75390625</td>\n",
" <td>[11.8142108917236]</td>\n",
" <td>[u'accuracy']</td>\n",
" <td>categorical_crossentropy</td>\n",
" <td>0.333333343267</td>\n",
" <td>1.09948420525</td>\n",
" <td>[0.333333343267441]</td>\n",
" <td>[1.09948420524597]</td>\n",
" <td>0.333333343267</td>\n",
" <td>1.09620642662</td>\n",
" <td>[0.333333343267441]</td>\n",
" <td>[1.09620642662048]</td>\n",
" <td>[1]</td>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" </tr>\n",
"</table>"
],
"text/plain": [
"[(10, 1, u\"optimizer='Adam(lr=0.04232194170481019)',metrics=['accuracy'],loss='categorical_crossentropy'\", u'epochs=1,batch_size=8', u'madlib_keras', 0.75390625, [21.911346912384, 29.2674539089203, 36.8268938064575, 44.9022789001465, 51.1760609149933, 57.6593999862671, 64.184476852417, 70.5566418170929, 77.0253269672394, 83.4826798439026, 90.1138219833374, 96.4566838741302], [u'accuracy'], u'categorical_crossentropy', 0.975000023841858, 0.0775080993771553, [0.791666686534882, 0.608333349227905, 0.966666638851166, 0.975000023841858, 0.966666638851166, 0.800000011920929, 0.975000023841858, 0.683333337306976, 0.733333349227905, 0.949999988079071, 0.949999988079071, 0.975000023841858], [0.374035209417343, 0.732228577136993, 0.170820266008377, 0.112313792109489, 0.172022193670273, 0.384404003620148, 0.115418829023838, 0.450868725776672, 0.457187473773956, 0.140348106622696, 0.15950845181942, 0.0775080993771553], 1.0, 0.0383280552923679, [0.899999976158142, 0.566666662693024, 0.966666638851166, 1.0, 1.0, 0.800000011920929, 0.966666638851166, 0.833333313465118, 0.899999976158142, 1.0, 0.899999976158142, 1.0], [0.273769021034241, 0.709117114543915, 0.154145583510399, 0.093109056353569, 0.130981177091599, 0.318724304437637, 0.102762393653393, 0.268609821796417, 0.253254026174545, 0.103913448750973, 0.194639429450035, 0.0383280552923679], [2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13], 1, 1),\n",
" (13, 1, u\"optimizer='Adam(lr=0.009905852828976726)',metrics=['accuracy'],loss='categorical_crossentropy'\", u'epochs=1,batch_size=4', u'madlib_keras', 0.75390625, [44.6836378574371, 50.92365193367, 57.3649659156799, 63.7576060295105, 70.1174209117889, 76.788703918457, 83.2217078208923, 89.8764188289642, 96.2273638248444], [u'accuracy'], u'categorical_crossentropy', 0.975000023841858, 0.0799522325396538, [0.949999988079071, 0.791666686534882, 0.800000011920929, 0.850000023841858, 0.958333313465118, 0.975000023841858, 0.899999976158142, 0.975000023841858, 0.975000023841858], [0.447714686393738, 0.36309215426445, 0.324623554944992, 0.301780551671982, 0.142947062849998, 0.120139442384243, 0.255296260118484, 0.0816238224506378, 0.0799522325396538], 0.966666638851166, 0.0760450512170792, [0.966666638851166, 0.899999976158142, 0.800000011920929, 0.899999976158142, 0.966666638851166, 0.966666638851166, 0.899999976158142, 1.0, 0.966666638851166], [0.370463252067566, 0.25237438082695, 0.317549884319305, 0.187985330820084, 0.104904659092426, 0.112288065254688, 0.160248279571533, 0.0687147378921509, 0.0760450512170792], [5, 6, 7, 8, 9, 10, 11, 12, 13], 0, 0),\n",
" (5, 2, u\"optimizer='Adam(lr=0.01678679876224294)',metrics=['accuracy'],loss='categorical_crossentropy'\", u'epochs=1,batch_size=8', u'madlib_keras', 1.18359375, [11.5813798904419, 21.0226759910583, 28.4713099002838, 35.9315679073334, 44.4656569957733, 50.7044010162354, 57.1448848247528, 63.4595718383789, 69.8967549800873, 76.3639938831329, 82.7779839038849, 89.6248579025269, 95.9936518669128], [u'accuracy'], u'categorical_crossentropy', 0.958333313465118, 0.113370150327682, [0.641666650772095, 0.908333361148834, 0.891666650772095, 0.891666650772095, 0.866666674613953, 0.941666662693024, 0.941666662693024, 0.933333337306976, 0.933333337306976, 0.858333349227905, 0.966666638851166, 0.958333313465118, 0.958333313465118], [0.656313836574554, 0.41341444849968, 0.324400961399078, 0.304112106561661, 0.336616456508636, 0.160554125905037, 0.135852053761482, 0.159805878996849, 0.174078181385994, 0.316538035869598, 0.104411341249943, 0.105065681040287, 0.113370150327682], 0.966666638851166, 0.121701933443546, [0.766666650772095, 0.933333337306976, 0.866666674613953, 0.866666674613953, 0.899999976158142, 0.966666638851166, 0.899999976158142, 0.966666638851166, 0.966666638851166, 0.899999976158142, 0.966666638851166, 0.966666638851166, 0.966666638851166], [0.563848853111267, 0.330921590328217, 0.292684972286224, 0.273869335651398, 0.317834258079529, 0.144475534558296, 0.147552534937859, 0.153202146291733, 0.158350095152855, 0.22741986811161, 0.114596471190453, 0.117612592875957, 0.121701933443546], [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13], 2, 2),\n",
" (14, 2, u\"optimizer='RMSprop(lr=0.01930169481426345)',metrics=['accuracy'],loss='categorical_crossentropy'\", u'epochs=1,batch_size=4', u'madlib_keras', 1.18359375, [44.2033138275146, 50.4514999389648, 56.8880548477173, 63.2074518203735, 69.5435798168182, 76.1080069541931, 82.519660949707, 89.1418299674988, 95.518424987793], [u'accuracy'], u'categorical_crossentropy', 0.941666662693024, 0.206491559743881, [0.566666662693024, 0.916666686534882, 0.883333325386047, 0.958333313465118, 0.841666638851166, 0.875, 0.783333361148834, 0.766666650772095, 0.941666662693024], [0.774700284004211, 0.651901543140411, 0.496851295232773, 0.405008375644684, 0.356276631355286, 0.340960919857025, 0.381286114454269, 0.388935476541519, 0.206491559743881], 0.966666638851166, 0.170937761664391, [0.733333349227905, 0.933333337306976, 0.866666674613953, 0.933333337306976, 0.866666674613953, 0.866666674613953, 0.833333313465118, 0.833333313465118, 0.966666638851166], [0.76544976234436, 0.657529413700104, 0.4853755235672, 0.377188384532928, 0.356318116188049, 0.332274377346039, 0.372768431901932, 0.397462010383606, 0.170937761664391], [5, 6, 7, 8, 9, 10, 11, 12, 13], 0, 0),\n",
" (6, 1, u\"optimizer='Adam(lr=0.011578246765795313)',metrics=['accuracy'],loss='categorical_crossentropy'\", u'epochs=1,batch_size=8', u'madlib_keras', 0.75390625, [12.2524900436401, 22.163911819458, 29.4894979000092, 37.043762922287], [u'accuracy'], u'categorical_crossentropy', 0.791666686534882, 0.595036566257477, [0.0333333350718021, 0.633333325386047, 0.816666662693024, 0.791666686534882], [0.947992205619812, 0.782966256141663, 0.679944217205048, 0.595036566257477], 0.899999976158142, 0.569178223609924, [0.100000001490116, 0.766666650772095, 0.933333337306976, 0.899999976158142], [0.972650408744812, 0.776390075683594, 0.681758761405945, 0.569178223609924], [1, 2, 3, 4], 2, 1),\n",
" (12, 1, u\"optimizer='Adam(lr=0.0699102360375282)',metrics=['accuracy'],loss='categorical_crossentropy'\", u'epochs=1,batch_size=8', u'madlib_keras', 0.75390625, [22.5178759098053, 29.7163498401642, 37.2609059810638], [u'accuracy'], u'categorical_crossentropy', 0.699999988079071, 0.389858365058899, [0.641666650772095, 0.641666650772095, 0.699999988079071], [0.79219126701355, 0.460052192211151, 0.389858365058899], 0.866666674613953, 0.250768661499023, [0.766666650772095, 0.766666650772095, 0.866666674613953], [0.765598654747009, 0.334016799926758, 0.250768661499023], [2, 3, 4], 1, 0),\n",
" (1, 1, u\"optimizer='RMSprop(lr=0.024714880320122704)',metrics=['accuracy'],loss='categorical_crossentropy'\", u'epochs=1,batch_size=4', u'madlib_keras', 0.75390625, [12.0343589782715, 21.4979238510132, 29.0434989929199, 36.4899458885193], [u'accuracy'], u'categorical_crossentropy', 0.649999976158142, 0.673553228378296, [0.691666662693024, 0.841666638851166, 0.983333349227905, 0.649999976158142], [0.388701051473618, 0.424284487962723, 0.180928915739059, 0.673553228378296], 0.800000011920929, 0.384207844734192, [0.833333313465118, 0.800000011920929, 0.966666638851166, 0.800000011920929], [0.255310624837875, 0.357394397258759, 0.147510275244713, 0.384207844734192], [1, 2, 3, 4], 2, 1),\n",
" (15, 2, u\"optimizer='Adam(lr=0.05573574908119242)',metrics=['accuracy'],loss='categorical_crossentropy'\", u'epochs=1,batch_size=8', u'madlib_keras', 1.18359375, [45.168872833252, 51.7013738155365, 58.1221590042114, 64.4642739295959, 70.8308379650116, 77.295382976532, 83.7621510028839, 90.3811860084534, 96.7183079719543], [u'accuracy'], u'categorical_crossentropy', 0.816666662693024, 0.457783430814743, [0.358333319425583, 0.925000011920929, 0.675000011920929, 0.733333349227905, 0.949999988079071, 0.666666686534882, 0.741666674613953, 0.908333361148834, 0.816666662693024], [1.03486049175262, 0.43449866771698, 0.842896223068237, 0.392013370990753, 0.195524752140045, 0.572380185127258, 0.43743160367012, 0.278554767370224, 0.457783430814743], 0.733333349227905, 0.670406579971313, [0.233333334326744, 0.966666638851166, 0.866666674613953, 0.866666674613953, 0.966666638851166, 0.666666686534882, 0.899999976158142, 0.933333337306976, 0.733333349227905], [1.05548679828644, 0.372740298509598, 0.427788466215134, 0.282503575086594, 0.135918349027634, 0.589654743671417, 0.253296822309494, 0.159830048680305, 0.670406579971313], [5, 6, 7, 8, 9, 10, 11, 12, 13], 0, 0),\n",
" (8, 1, u\"optimizer='RMSprop(lr=0.09641245863612281)',metrics=['accuracy'],loss='categorical_crossentropy'\", u'epochs=1,batch_size=4', u'madlib_keras', 0.75390625, [12.7177708148956], [u'accuracy'], u'categorical_crossentropy', 0.658333361148834, 1.25986480712891, [0.658333361148834], [1.25986480712891], 0.633333325386047, 1.26717245578766, [0.633333325386047], [1.26717245578766], [1], 2, 0),\n",
" (2, 1, u\"optimizer='RMSprop(lr=0.003730347382813742)',metrics=['accuracy'],loss='categorical_crossentropy'\", u'epochs=1,batch_size=4', u'madlib_keras', 0.75390625, [11.1050899028778], [u'accuracy'], u'categorical_crossentropy', 0.600000023841858, 1.23435640335083, [0.600000023841858], [1.23435640335083], 0.5, 1.37250542640686, [0.5], [1.37250542640686], [1], 2, 0),\n",
" (7, 1, u\"optimizer='Adam(lr=0.0018352035707327032)',metrics=['accuracy'],loss='categorical_crossentropy'\", u'epochs=1,batch_size=8', u'madlib_keras', 0.75390625, [11.3283720016479], [u'accuracy'], u'categorical_crossentropy', 0.466666668653488, 1.01645076274872, [0.466666668653488], [1.01645076274872], 0.433333337306976, 1.01912522315979, [0.433333337306976], [1.01912522315979], [1], 2, 0),\n",
" (4, 2, u\"optimizer='Adam(lr=0.03837714620063437)',metrics=['accuracy'],loss='categorical_crossentropy'\", u'epochs=1,batch_size=4', u'madlib_keras', 1.18359375, [12.5016968250275], [u'accuracy'], u'categorical_crossentropy', 0.308333337306976, 1.09954655170441, [0.308333337306976], [1.09954655170441], 0.433333337306976, 1.09805536270142, [0.433333337306976], [1.09805536270142], [1], 2, 0),\n",
" (9, 2, u\"optimizer='Adam(lr=0.0017052377620857802)',metrics=['accuracy'],loss='categorical_crossentropy'\", u'epochs=1,batch_size=8', u'madlib_keras', 1.18359375, [10.8097839355469], [u'accuracy'], u'categorical_crossentropy', 0.341666668653488, 1.28075575828552, [0.341666668653488], [1.28075575828552], 0.366666674613953, 1.43494951725006, [0.366666674613953], [1.43494951725006], [1], 2, 0),\n",
" (11, 2, u\"optimizer='Adam(lr=0.0015217424326594508)',metrics=['accuracy'],loss='categorical_crossentropy'\", u'epochs=1,batch_size=8', u'madlib_keras', 1.18359375, [21.2741727828979, 28.7427089214325, 36.1846778392792], [u'accuracy'], u'categorical_crossentropy', 0.333333343267441, 1.07403242588043, [0.474999994039536, 0.358333319425583, 0.333333343267441], [1.08657968044281, 1.07721281051636, 1.07403242588043], 0.333333343267441, 1.09314000606537, [0.433333337306976, 0.300000011920929, 0.333333343267441], [1.11294913291931, 1.10347521305084, 1.09314000606537], [2, 3, 4], 1, 0),\n",
" (3, 1, u\"optimizer='RMSprop(lr=0.051964270528848694)',metrics=['accuracy'],loss='categorical_crossentropy'\", u'epochs=1,batch_size=4', u'madlib_keras', 0.75390625, [11.8142108917236], [u'accuracy'], u'categorical_crossentropy', 0.333333343267441, 1.09948420524597, [0.333333343267441], [1.09948420524597], 0.333333343267441, 1.09620642662048, [0.333333343267441], [1.09620642662048], [1], 2, 0)]"
]
},
"execution_count": 19,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"%%sql\n",
"SELECT * FROM automl_output_info ORDER BY validation_metrics_final DESC, validation_loss_final;"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Plot results"
]
},
{
"cell_type": "code",
"execution_count": 20,
"metadata": {},
"outputs": [],
"source": [
"%matplotlib notebook\n",
"import matplotlib.pyplot as plt\n",
"from matplotlib.ticker import MaxNLocator\n",
"from collections import defaultdict\n",
"import pandas as pd\n",
"import seaborn as sns\n",
"sns.set_palette(sns.color_palette(\"hls\", 20))\n",
"plt.rcParams.update({'font.size': 12})\n",
"pd.set_option('display.max_colwidth', -1)"
]
},
{
"cell_type": "code",
"execution_count": 21,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"15 rows affected.\n",
"1 rows affected.\n"
]
},
{
"data": {
"application/javascript": [
"/* Put everything inside the global mpl namespace */\n",
"window.mpl = {};\n",
"\n",
"\n",
"mpl.get_websocket_type = function() {\n",
" if (typeof(WebSocket) !== 'undefined') {\n",
" return WebSocket;\n",
" } else if (typeof(MozWebSocket) !== 'undefined') {\n",
" return MozWebSocket;\n",
" } else {\n",
" alert('Your browser does not have WebSocket support.' +\n",
" 'Please try Chrome, Safari or Firefox ≥ 6. ' +\n",
" 'Firefox 4 and 5 are also supported but you ' +\n",
" 'have to enable WebSockets in about:config.');\n",
" };\n",
"}\n",
"\n",
"mpl.figure = function(figure_id, websocket, ondownload, parent_element) {\n",
" this.id = figure_id;\n",
"\n",
" this.ws = websocket;\n",
"\n",
" this.supports_binary = (this.ws.binaryType != undefined);\n",
"\n",
" if (!this.supports_binary) {\n",
" var warnings = document.getElementById(\"mpl-warnings\");\n",
" if (warnings) {\n",
" warnings.style.display = 'block';\n",
" warnings.textContent = (\n",
" \"This browser does not support binary websocket messages. \" +\n",
" \"Performance may be slow.\");\n",
" }\n",
" }\n",
"\n",
" this.imageObj = new Image();\n",
"\n",
" this.context = undefined;\n",
" this.message = undefined;\n",
" this.canvas = undefined;\n",
" this.rubberband_canvas = undefined;\n",
" this.rubberband_context = undefined;\n",
" this.format_dropdown = undefined;\n",
"\n",
" this.image_mode = 'full';\n",
"\n",
" this.root = $('<div/>');\n",
" this._root_extra_style(this.root)\n",
" this.root.attr('style', 'display: inline-block');\n",
"\n",
" $(parent_element).append(this.root);\n",
"\n",
" this._init_header(this);\n",
" this._init_canvas(this);\n",
" this._init_toolbar(this);\n",
"\n",
" var fig = this;\n",
"\n",
" this.waiting = false;\n",
"\n",
" this.ws.onopen = function () {\n",
" fig.send_message(\"supports_binary\", {value: fig.supports_binary});\n",
" fig.send_message(\"send_image_mode\", {});\n",
" if (mpl.ratio != 1) {\n",
" fig.send_message(\"set_dpi_ratio\", {'dpi_ratio': mpl.ratio});\n",
" }\n",
" fig.send_message(\"refresh\", {});\n",
" }\n",
"\n",
" this.imageObj.onload = function() {\n",
" if (fig.image_mode == 'full') {\n",
" // Full images could contain transparency (where diff images\n",
" // almost always do), so we need to clear the canvas so that\n",
" // there is no ghosting.\n",
" fig.context.clearRect(0, 0, fig.canvas.width, fig.canvas.height);\n",
" }\n",
" fig.context.drawImage(fig.imageObj, 0, 0);\n",
" };\n",
"\n",
" this.imageObj.onunload = function() {\n",
" fig.ws.close();\n",
" }\n",
"\n",
" this.ws.onmessage = this._make_on_message_function(this);\n",
"\n",
" this.ondownload = ondownload;\n",
"}\n",
"\n",
"mpl.figure.prototype._init_header = function() {\n",
" var titlebar = $(\n",
" '<div class=\"ui-dialog-titlebar ui-widget-header ui-corner-all ' +\n",
" 'ui-helper-clearfix\"/>');\n",
" var titletext = $(\n",
" '<div class=\"ui-dialog-title\" style=\"width: 100%; ' +\n",
" 'text-align: center; padding: 3px;\"/>');\n",
" titlebar.append(titletext)\n",
" this.root.append(titlebar);\n",
" this.header = titletext[0];\n",
"}\n",
"\n",
"\n",
"\n",
"mpl.figure.prototype._canvas_extra_style = function(canvas_div) {\n",
"\n",
"}\n",
"\n",
"\n",
"mpl.figure.prototype._root_extra_style = function(canvas_div) {\n",
"\n",
"}\n",
"\n",
"mpl.figure.prototype._init_canvas = function() {\n",
" var fig = this;\n",
"\n",
" var canvas_div = $('<div/>');\n",
"\n",
" canvas_div.attr('style', 'position: relative; clear: both; outline: 0');\n",
"\n",
" function canvas_keyboard_event(event) {\n",
" return fig.key_event(event, event['data']);\n",
" }\n",
"\n",
" canvas_div.keydown('key_press', canvas_keyboard_event);\n",
" canvas_div.keyup('key_release', canvas_keyboard_event);\n",
" this.canvas_div = canvas_div\n",
" this._canvas_extra_style(canvas_div)\n",
" this.root.append(canvas_div);\n",
"\n",
" var canvas = $('<canvas/>');\n",
" canvas.addClass('mpl-canvas');\n",
" canvas.attr('style', \"left: 0; top: 0; z-index: 0; outline: 0\")\n",
"\n",
" this.canvas = canvas[0];\n",
" this.context = canvas[0].getContext(\"2d\");\n",
"\n",
" var backingStore = this.context.backingStorePixelRatio ||\n",
"\tthis.context.webkitBackingStorePixelRatio ||\n",
"\tthis.context.mozBackingStorePixelRatio ||\n",
"\tthis.context.msBackingStorePixelRatio ||\n",
"\tthis.context.oBackingStorePixelRatio ||\n",
"\tthis.context.backingStorePixelRatio || 1;\n",
"\n",
" mpl.ratio = (window.devicePixelRatio || 1) / backingStore;\n",
"\n",
" var rubberband = $('<canvas/>');\n",
" rubberband.attr('style', \"position: absolute; left: 0; top: 0; z-index: 1;\")\n",
"\n",
" var pass_mouse_events = true;\n",
"\n",
" canvas_div.resizable({\n",
" start: function(event, ui) {\n",
" pass_mouse_events = false;\n",
" },\n",
" resize: function(event, ui) {\n",
" fig.request_resize(ui.size.width, ui.size.height);\n",
" },\n",
" stop: function(event, ui) {\n",
" pass_mouse_events = true;\n",
" fig.request_resize(ui.size.width, ui.size.height);\n",
" },\n",
" });\n",
"\n",
" function mouse_event_fn(event) {\n",
" if (pass_mouse_events)\n",
" return fig.mouse_event(event, event['data']);\n",
" }\n",
"\n",
" rubberband.mousedown('button_press', mouse_event_fn);\n",
" rubberband.mouseup('button_release', mouse_event_fn);\n",
" // Throttle sequential mouse events to 1 every 20ms.\n",
" rubberband.mousemove('motion_notify', mouse_event_fn);\n",
"\n",
" rubberband.mouseenter('figure_enter', mouse_event_fn);\n",
" rubberband.mouseleave('figure_leave', mouse_event_fn);\n",
"\n",
" canvas_div.on(\"wheel\", function (event) {\n",
" event = event.originalEvent;\n",
" event['data'] = 'scroll'\n",
" if (event.deltaY < 0) {\n",
" event.step = 1;\n",
" } else {\n",
" event.step = -1;\n",
" }\n",
" mouse_event_fn(event);\n",
" });\n",
"\n",
" canvas_div.append(canvas);\n",
" canvas_div.append(rubberband);\n",
"\n",
" this.rubberband = rubberband;\n",
" this.rubberband_canvas = rubberband[0];\n",
" this.rubberband_context = rubberband[0].getContext(\"2d\");\n",
" this.rubberband_context.strokeStyle = \"#000000\";\n",
"\n",
" this._resize_canvas = function(width, height) {\n",
" // Keep the size of the canvas, canvas container, and rubber band\n",
" // canvas in synch.\n",
" canvas_div.css('width', width)\n",
" canvas_div.css('height', height)\n",
"\n",
" canvas.attr('width', width * mpl.ratio);\n",
" canvas.attr('height', height * mpl.ratio);\n",
" canvas.attr('style', 'width: ' + width + 'px; height: ' + height + 'px;');\n",
"\n",
" rubberband.attr('width', width);\n",
" rubberband.attr('height', height);\n",
" }\n",
"\n",
" // Set the figure to an initial 600x600px, this will subsequently be updated\n",
" // upon first draw.\n",
" this._resize_canvas(600, 600);\n",
"\n",
" // Disable right mouse context menu.\n",
" $(this.rubberband_canvas).bind(\"contextmenu\",function(e){\n",
" return false;\n",
" });\n",
"\n",
" function set_focus () {\n",
" canvas.focus();\n",
" canvas_div.focus();\n",
" }\n",
"\n",
" window.setTimeout(set_focus, 100);\n",
"}\n",
"\n",
"mpl.figure.prototype._init_toolbar = function() {\n",
" var fig = this;\n",
"\n",
" var nav_element = $('<div/>')\n",
" nav_element.attr('style', 'width: 100%');\n",
" this.root.append(nav_element);\n",
"\n",
" // Define a callback function for later on.\n",
" function toolbar_event(event) {\n",
" return fig.toolbar_button_onclick(event['data']);\n",
" }\n",
" function toolbar_mouse_event(event) {\n",
" return fig.toolbar_button_onmouseover(event['data']);\n",
" }\n",
"\n",
" for(var toolbar_ind in mpl.toolbar_items) {\n",
" var name = mpl.toolbar_items[toolbar_ind][0];\n",
" var tooltip = mpl.toolbar_items[toolbar_ind][1];\n",
" var image = mpl.toolbar_items[toolbar_ind][2];\n",
" var method_name = mpl.toolbar_items[toolbar_ind][3];\n",
"\n",
" if (!name) {\n",
" // put a spacer in here.\n",
" continue;\n",
" }\n",
" var button = $('<button/>');\n",
" button.addClass('ui-button ui-widget ui-state-default ui-corner-all ' +\n",
" 'ui-button-icon-only');\n",
" button.attr('role', 'button');\n",
" button.attr('aria-disabled', 'false');\n",
" button.click(method_name, toolbar_event);\n",
" button.mouseover(tooltip, toolbar_mouse_event);\n",
"\n",
" var icon_img = $('<span/>');\n",
" icon_img.addClass('ui-button-icon-primary ui-icon');\n",
" icon_img.addClass(image);\n",
" icon_img.addClass('ui-corner-all');\n",
"\n",
" var tooltip_span = $('<span/>');\n",
" tooltip_span.addClass('ui-button-text');\n",
" tooltip_span.html(tooltip);\n",
"\n",
" button.append(icon_img);\n",
" button.append(tooltip_span);\n",
"\n",
" nav_element.append(button);\n",
" }\n",
"\n",
" var fmt_picker_span = $('<span/>');\n",
"\n",
" var fmt_picker = $('<select/>');\n",
" fmt_picker.addClass('mpl-toolbar-option ui-widget ui-widget-content');\n",
" fmt_picker_span.append(fmt_picker);\n",
" nav_element.append(fmt_picker_span);\n",
" this.format_dropdown = fmt_picker[0];\n",
"\n",
" for (var ind in mpl.extensions) {\n",
" var fmt = mpl.extensions[ind];\n",
" var option = $(\n",
" '<option/>', {selected: fmt === mpl.default_extension}).html(fmt);\n",
" fmt_picker.append(option)\n",
" }\n",
"\n",
" // Add hover states to the ui-buttons\n",
" $( \".ui-button\" ).hover(\n",
" function() { $(this).addClass(\"ui-state-hover\");},\n",
" function() { $(this).removeClass(\"ui-state-hover\");}\n",
" );\n",
"\n",
" var status_bar = $('<span class=\"mpl-message\"/>');\n",
" nav_element.append(status_bar);\n",
" this.message = status_bar[0];\n",
"}\n",
"\n",
"mpl.figure.prototype.request_resize = function(x_pixels, y_pixels) {\n",
" // Request matplotlib to resize the figure. Matplotlib will then trigger a resize in the client,\n",
" // which will in turn request a refresh of the image.\n",
" this.send_message('resize', {'width': x_pixels, 'height': y_pixels});\n",
"}\n",
"\n",
"mpl.figure.prototype.send_message = function(type, properties) {\n",
" properties['type'] = type;\n",
" properties['figure_id'] = this.id;\n",
" this.ws.send(JSON.stringify(properties));\n",
"}\n",
"\n",
"mpl.figure.prototype.send_draw_message = function() {\n",
" if (!this.waiting) {\n",
" this.waiting = true;\n",
" this.ws.send(JSON.stringify({type: \"draw\", figure_id: this.id}));\n",
" }\n",
"}\n",
"\n",
"\n",
"mpl.figure.prototype.handle_save = function(fig, msg) {\n",
" var format_dropdown = fig.format_dropdown;\n",
" var format = format_dropdown.options[format_dropdown.selectedIndex].value;\n",
" fig.ondownload(fig, format);\n",
"}\n",
"\n",
"\n",
"mpl.figure.prototype.handle_resize = function(fig, msg) {\n",
" var size = msg['size'];\n",
" if (size[0] != fig.canvas.width || size[1] != fig.canvas.height) {\n",
" fig._resize_canvas(size[0], size[1]);\n",
" fig.send_message(\"refresh\", {});\n",
" };\n",
"}\n",
"\n",
"mpl.figure.prototype.handle_rubberband = function(fig, msg) {\n",
" var x0 = msg['x0'] / mpl.ratio;\n",
" var y0 = (fig.canvas.height - msg['y0']) / mpl.ratio;\n",
" var x1 = msg['x1'] / mpl.ratio;\n",
" var y1 = (fig.canvas.height - msg['y1']) / mpl.ratio;\n",
" x0 = Math.floor(x0) + 0.5;\n",
" y0 = Math.floor(y0) + 0.5;\n",
" x1 = Math.floor(x1) + 0.5;\n",
" y1 = Math.floor(y1) + 0.5;\n",
" var min_x = Math.min(x0, x1);\n",
" var min_y = Math.min(y0, y1);\n",
" var width = Math.abs(x1 - x0);\n",
" var height = Math.abs(y1 - y0);\n",
"\n",
" fig.rubberband_context.clearRect(\n",
" 0, 0, fig.canvas.width, fig.canvas.height);\n",
"\n",
" fig.rubberband_context.strokeRect(min_x, min_y, width, height);\n",
"}\n",
"\n",
"mpl.figure.prototype.handle_figure_label = function(fig, msg) {\n",
" // Updates the figure title.\n",
" fig.header.textContent = msg['label'];\n",
"}\n",
"\n",
"mpl.figure.prototype.handle_cursor = function(fig, msg) {\n",
" var cursor = msg['cursor'];\n",
" switch(cursor)\n",
" {\n",
" case 0:\n",
" cursor = 'pointer';\n",
" break;\n",
" case 1:\n",
" cursor = 'default';\n",
" break;\n",
" case 2:\n",
" cursor = 'crosshair';\n",
" break;\n",
" case 3:\n",
" cursor = 'move';\n",
" break;\n",
" }\n",
" fig.rubberband_canvas.style.cursor = cursor;\n",
"}\n",
"\n",
"mpl.figure.prototype.handle_message = function(fig, msg) {\n",
" fig.message.textContent = msg['message'];\n",
"}\n",
"\n",
"mpl.figure.prototype.handle_draw = function(fig, msg) {\n",
" // Request the server to send over a new figure.\n",
" fig.send_draw_message();\n",
"}\n",
"\n",
"mpl.figure.prototype.handle_image_mode = function(fig, msg) {\n",
" fig.image_mode = msg['mode'];\n",
"}\n",
"\n",
"mpl.figure.prototype.updated_canvas_event = function() {\n",
" // Called whenever the canvas gets updated.\n",
" this.send_message(\"ack\", {});\n",
"}\n",
"\n",
"// A function to construct a web socket function for onmessage handling.\n",
"// Called in the figure constructor.\n",
"mpl.figure.prototype._make_on_message_function = function(fig) {\n",
" return function socket_on_message(evt) {\n",
" if (evt.data instanceof Blob) {\n",
" /* FIXME: We get \"Resource interpreted as Image but\n",
" * transferred with MIME type text/plain:\" errors on\n",
" * Chrome. But how to set the MIME type? It doesn't seem\n",
" * to be part of the websocket stream */\n",
" evt.data.type = \"image/png\";\n",
"\n",
" /* Free the memory for the previous frames */\n",
" if (fig.imageObj.src) {\n",
" (window.URL || window.webkitURL).revokeObjectURL(\n",
" fig.imageObj.src);\n",
" }\n",
"\n",
" fig.imageObj.src = (window.URL || window.webkitURL).createObjectURL(\n",
" evt.data);\n",
" fig.updated_canvas_event();\n",
" fig.waiting = false;\n",
" return;\n",
" }\n",
" else if (typeof evt.data === 'string' && evt.data.slice(0, 21) == \"data:image/png;base64\") {\n",
" fig.imageObj.src = evt.data;\n",
" fig.updated_canvas_event();\n",
" fig.waiting = false;\n",
" return;\n",
" }\n",
"\n",
" var msg = JSON.parse(evt.data);\n",
" var msg_type = msg['type'];\n",
"\n",
" // Call the \"handle_{type}\" callback, which takes\n",
" // the figure and JSON message as its only arguments.\n",
" try {\n",
" var callback = fig[\"handle_\" + msg_type];\n",
" } catch (e) {\n",
" console.log(\"No handler for the '\" + msg_type + \"' message type: \", msg);\n",
" return;\n",
" }\n",
"\n",
" if (callback) {\n",
" try {\n",
" // console.log(\"Handling '\" + msg_type + \"' message: \", msg);\n",
" callback(fig, msg);\n",
" } catch (e) {\n",
" console.log(\"Exception inside the 'handler_\" + msg_type + \"' callback:\", e, e.stack, msg);\n",
" }\n",
" }\n",
" };\n",
"}\n",
"\n",
"// from http://stackoverflow.com/questions/1114465/getting-mouse-location-in-canvas\n",
"mpl.findpos = function(e) {\n",
" //this section is from http://www.quirksmode.org/js/events_properties.html\n",
" var targ;\n",
" if (!e)\n",
" e = window.event;\n",
" if (e.target)\n",
" targ = e.target;\n",
" else if (e.srcElement)\n",
" targ = e.srcElement;\n",
" if (targ.nodeType == 3) // defeat Safari bug\n",
" targ = targ.parentNode;\n",
"\n",
" // jQuery normalizes the pageX and pageY\n",
" // pageX,Y are the mouse positions relative to the document\n",
" // offset() returns the position of the element relative to the document\n",
" var x = e.pageX - $(targ).offset().left;\n",
" var y = e.pageY - $(targ).offset().top;\n",
"\n",
" return {\"x\": x, \"y\": y};\n",
"};\n",
"\n",
"/*\n",
" * return a copy of an object with only non-object keys\n",
" * we need this to avoid circular references\n",
" * http://stackoverflow.com/a/24161582/3208463\n",
" */\n",
"function simpleKeys (original) {\n",
" return Object.keys(original).reduce(function (obj, key) {\n",
" if (typeof original[key] !== 'object')\n",
" obj[key] = original[key]\n",
" return obj;\n",
" }, {});\n",
"}\n",
"\n",
"mpl.figure.prototype.mouse_event = function(event, name) {\n",
" var canvas_pos = mpl.findpos(event)\n",
"\n",
" if (name === 'button_press')\n",
" {\n",
" this.canvas.focus();\n",
" this.canvas_div.focus();\n",
" }\n",
"\n",
" var x = canvas_pos.x * mpl.ratio;\n",
" var y = canvas_pos.y * mpl.ratio;\n",
"\n",
" this.send_message(name, {x: x, y: y, button: event.button,\n",
" step: event.step,\n",
" guiEvent: simpleKeys(event)});\n",
"\n",
" /* This prevents the web browser from automatically changing to\n",
" * the text insertion cursor when the button is pressed. We want\n",
" * to control all of the cursor setting manually through the\n",
" * 'cursor' event from matplotlib */\n",
" event.preventDefault();\n",
" return false;\n",
"}\n",
"\n",
"mpl.figure.prototype._key_event_extra = function(event, name) {\n",
" // Handle any extra behaviour associated with a key event\n",
"}\n",
"\n",
"mpl.figure.prototype.key_event = function(event, name) {\n",
"\n",
" // Prevent repeat events\n",
" if (name == 'key_press')\n",
" {\n",
" if (event.which === this._key)\n",
" return;\n",
" else\n",
" this._key = event.which;\n",
" }\n",
" if (name == 'key_release')\n",
" this._key = null;\n",
"\n",
" var value = '';\n",
" if (event.ctrlKey && event.which != 17)\n",
" value += \"ctrl+\";\n",
" if (event.altKey && event.which != 18)\n",
" value += \"alt+\";\n",
" if (event.shiftKey && event.which != 16)\n",
" value += \"shift+\";\n",
"\n",
" value += 'k';\n",
" value += event.which.toString();\n",
"\n",
" this._key_event_extra(event, name);\n",
"\n",
" this.send_message(name, {key: value,\n",
" guiEvent: simpleKeys(event)});\n",
" return false;\n",
"}\n",
"\n",
"mpl.figure.prototype.toolbar_button_onclick = function(name) {\n",
" if (name == 'download') {\n",
" this.handle_save(this, null);\n",
" } else {\n",
" this.send_message(\"toolbar_button\", {name: name});\n",
" }\n",
"};\n",
"\n",
"mpl.figure.prototype.toolbar_button_onmouseover = function(tooltip) {\n",
" this.message.textContent = tooltip;\n",
"};\n",
"mpl.toolbar_items = [[\"Home\", \"Reset original view\", \"fa fa-home icon-home\", \"home\"], [\"Back\", \"Back to previous view\", \"fa fa-arrow-left icon-arrow-left\", \"back\"], [\"Forward\", \"Forward to next view\", \"fa fa-arrow-right icon-arrow-right\", \"forward\"], [\"\", \"\", \"\", \"\"], [\"Pan\", \"Pan axes with left mouse, zoom with right\", \"fa fa-arrows icon-move\", \"pan\"], [\"Zoom\", \"Zoom to rectangle\", \"fa fa-square-o icon-check-empty\", \"zoom\"], [\"\", \"\", \"\", \"\"], [\"Download\", \"Download plot\", \"fa fa-floppy-o icon-save\", \"download\"]];\n",
"\n",
"mpl.extensions = [\"eps\", \"jpeg\", \"pdf\", \"png\", \"ps\", \"raw\", \"svg\", \"tif\"];\n",
"\n",
"mpl.default_extension = \"png\";var comm_websocket_adapter = function(comm) {\n",
" // Create a \"websocket\"-like object which calls the given IPython comm\n",
" // object with the appropriate methods. Currently this is a non binary\n",
" // socket, so there is still some room for performance tuning.\n",
" var ws = {};\n",
"\n",
" ws.close = function() {\n",
" comm.close()\n",
" };\n",
" ws.send = function(m) {\n",
" //console.log('sending', m);\n",
" comm.send(m);\n",
" };\n",
" // Register the callback with on_msg.\n",
" comm.on_msg(function(msg) {\n",
" //console.log('receiving', msg['content']['data'], msg);\n",
" // Pass the mpl event to the overridden (by mpl) onmessage function.\n",
" ws.onmessage(msg['content']['data'])\n",
" });\n",
" return ws;\n",
"}\n",
"\n",
"mpl.mpl_figure_comm = function(comm, msg) {\n",
" // This is the function which gets called when the mpl process\n",
" // starts-up an IPython Comm through the \"matplotlib\" channel.\n",
"\n",
" var id = msg.content.data.id;\n",
" // Get hold of the div created by the display call when the Comm\n",
" // socket was opened in Python.\n",
" var element = $(\"#\" + id);\n",
" var ws_proxy = comm_websocket_adapter(comm)\n",
"\n",
" function ondownload(figure, format) {\n",
" window.open(figure.imageObj.src);\n",
" }\n",
"\n",
" var fig = new mpl.figure(id, ws_proxy,\n",
" ondownload,\n",
" element.get(0));\n",
"\n",
" // Call onopen now - mpl needs it, as it is assuming we've passed it a real\n",
" // web socket which is closed, not our websocket->open comm proxy.\n",
" ws_proxy.onopen();\n",
"\n",
" fig.parent_element = element.get(0);\n",
" fig.cell_info = mpl.find_output_cell(\"<div id='\" + id + \"'></div>\");\n",
" if (!fig.cell_info) {\n",
" console.error(\"Failed to find cell for figure\", id, fig);\n",
" return;\n",
" }\n",
"\n",
" var output_index = fig.cell_info[2]\n",
" var cell = fig.cell_info[0];\n",
"\n",
"};\n",
"\n",
"mpl.figure.prototype.handle_close = function(fig, msg) {\n",
" var width = fig.canvas.width/mpl.ratio\n",
" fig.root.unbind('remove')\n",
"\n",
" // Update the output cell to use the data from the current canvas.\n",
" fig.push_to_output();\n",
" var dataURL = fig.canvas.toDataURL();\n",
" // Re-enable the keyboard manager in IPython - without this line, in FF,\n",
" // the notebook keyboard shortcuts fail.\n",
" IPython.keyboard_manager.enable()\n",
" $(fig.parent_element).html('<img src=\"' + dataURL + '\" width=\"' + width + '\">');\n",
" fig.close_ws(fig, msg);\n",
"}\n",
"\n",
"mpl.figure.prototype.close_ws = function(fig, msg){\n",
" fig.send_message('closing', msg);\n",
" // fig.ws.close()\n",
"}\n",
"\n",
"mpl.figure.prototype.push_to_output = function(remove_interactive) {\n",
" // Turn the data on the canvas into data in the output cell.\n",
" var width = this.canvas.width/mpl.ratio\n",
" var dataURL = this.canvas.toDataURL();\n",
" this.cell_info[1]['text/html'] = '<img src=\"' + dataURL + '\" width=\"' + width + '\">';\n",
"}\n",
"\n",
"mpl.figure.prototype.updated_canvas_event = function() {\n",
" // Tell IPython that the notebook contents must change.\n",
" IPython.notebook.set_dirty(true);\n",
" this.send_message(\"ack\", {});\n",
" var fig = this;\n",
" // Wait a second, then push the new image to the DOM so\n",
" // that it is saved nicely (might be nice to debounce this).\n",
" setTimeout(function () { fig.push_to_output() }, 1000);\n",
"}\n",
"\n",
"mpl.figure.prototype._init_toolbar = function() {\n",
" var fig = this;\n",
"\n",
" var nav_element = $('<div/>')\n",
" nav_element.attr('style', 'width: 100%');\n",
" this.root.append(nav_element);\n",
"\n",
" // Define a callback function for later on.\n",
" function toolbar_event(event) {\n",
" return fig.toolbar_button_onclick(event['data']);\n",
" }\n",
" function toolbar_mouse_event(event) {\n",
" return fig.toolbar_button_onmouseover(event['data']);\n",
" }\n",
"\n",
" for(var toolbar_ind in mpl.toolbar_items){\n",
" var name = mpl.toolbar_items[toolbar_ind][0];\n",
" var tooltip = mpl.toolbar_items[toolbar_ind][1];\n",
" var image = mpl.toolbar_items[toolbar_ind][2];\n",
" var method_name = mpl.toolbar_items[toolbar_ind][3];\n",
"\n",
" if (!name) { continue; };\n",
"\n",
" var button = $('<button class=\"btn btn-default\" href=\"#\" title=\"' + name + '\"><i class=\"fa ' + image + ' fa-lg\"></i></button>');\n",
" button.click(method_name, toolbar_event);\n",
" button.mouseover(tooltip, toolbar_mouse_event);\n",
" nav_element.append(button);\n",
" }\n",
"\n",
" // Add the status bar.\n",
" var status_bar = $('<span class=\"mpl-message\" style=\"text-align:right; float: right;\"/>');\n",
" nav_element.append(status_bar);\n",
" this.message = status_bar[0];\n",
"\n",
" // Add the close button to the window.\n",
" var buttongrp = $('<div class=\"btn-group inline pull-right\"></div>');\n",
" var button = $('<button class=\"btn btn-mini btn-primary\" href=\"#\" title=\"Stop Interaction\"><i class=\"fa fa-power-off icon-remove icon-large\"></i></button>');\n",
" button.click(function (evt) { fig.handle_close(fig, {}); } );\n",
" button.mouseover('Stop Interaction', toolbar_mouse_event);\n",
" buttongrp.append(button);\n",
" var titlebar = this.root.find($('.ui-dialog-titlebar'));\n",
" titlebar.prepend(buttongrp);\n",
"}\n",
"\n",
"mpl.figure.prototype._root_extra_style = function(el){\n",
" var fig = this\n",
" el.on(\"remove\", function(){\n",
"\tfig.close_ws(fig, {});\n",
" });\n",
"}\n",
"\n",
"mpl.figure.prototype._canvas_extra_style = function(el){\n",
" // this is important to make the div 'focusable\n",
" el.attr('tabindex', 0)\n",
" // reach out to IPython and tell the keyboard manager to turn it's self\n",
" // off when our div gets focus\n",
"\n",
" // location in version 3\n",
" if (IPython.notebook.keyboard_manager) {\n",
" IPython.notebook.keyboard_manager.register_events(el);\n",
" }\n",
" else {\n",
" // location in version 2\n",
" IPython.keyboard_manager.register_events(el);\n",
" }\n",
"\n",
"}\n",
"\n",
"mpl.figure.prototype._key_event_extra = function(event, name) {\n",
" var manager = IPython.notebook.keyboard_manager;\n",
" if (!manager)\n",
" manager = IPython.keyboard_manager;\n",
"\n",
" // Check for shift+enter\n",
" if (event.shiftKey && event.which == 13) {\n",
" this.canvas_div.blur();\n",
" // select the cell after this one\n",
" var index = IPython.notebook.find_cell_index(this.cell_info[0]);\n",
" IPython.notebook.select(index + 1);\n",
" }\n",
"}\n",
"\n",
"mpl.figure.prototype.handle_save = function(fig, msg) {\n",
" fig.ondownload(fig, null);\n",
"}\n",
"\n",
"\n",
"mpl.find_output_cell = function(html_output) {\n",
" // Return the cell and output element which can be found *uniquely* in the notebook.\n",
" // Note - this is a bit hacky, but it is done because the \"notebook_saving.Notebook\"\n",
" // IPython event is triggered only after the cells have been serialised, which for\n",
" // our purposes (turning an active figure into a static one), is too late.\n",
" var cells = IPython.notebook.get_cells();\n",
" var ncells = cells.length;\n",
" for (var i=0; i<ncells; i++) {\n",
" var cell = cells[i];\n",
" if (cell.cell_type === 'code'){\n",
" for (var j=0; j<cell.output_area.outputs.length; j++) {\n",
" var data = cell.output_area.outputs[j];\n",
" if (data.data) {\n",
" // IPython >= 3 moved mimebundle to data attribute of output\n",
" data = data.data;\n",
" }\n",
" if (data['text/html'] == html_output) {\n",
" return [cell, data, j];\n",
" }\n",
" }\n",
" }\n",
" }\n",
"}\n",
"\n",
"// Register the function which deals with the matplotlib target/channel.\n",
"// The kernel may be null if the page has been refreshed.\n",
"if (IPython.notebook.kernel != null) {\n",
" IPython.notebook.kernel.comm_manager.register_target('matplotlib', mpl.mpl_figure_comm);\n",
"}\n"
],
"text/plain": [
"<IPython.core.display.Javascript object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<img src=\"data:image/png;base64,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\" width=\"720\">"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"1 rows affected.\n",
"1 rows affected.\n",
"1 rows affected.\n",
"1 rows affected.\n",
"1 rows affected.\n",
"1 rows affected.\n",
"1 rows affected.\n",
"1 rows affected.\n",
"1 rows affected.\n",
"1 rows affected.\n",
"1 rows affected.\n",
"1 rows affected.\n",
"1 rows affected.\n",
"1 rows affected.\n",
"1 rows affected.\n"
]
}
],
"source": [
"df_results = %sql SELECT * FROM automl_output_info;\n",
"df_results = df_results.DataFrame()\n",
"\n",
"df_summary = %sql SELECT * FROM automl_output_summary;\n",
"df_summary = df_summary.DataFrame()\n",
"\n",
"#set up plots\n",
"fig, axs = plt.subplots(nrows=1, ncols=2, figsize=(10,5))\n",
"fig.legend(ncol=4)\n",
"fig.tight_layout()\n",
"\n",
"ax_metric = axs[0]\n",
"ax_loss = axs[1]\n",
"\n",
"ax_metric.xaxis.set_major_locator(MaxNLocator(integer=True))\n",
"ax_metric.set_xlabel('Iteration')\n",
"ax_metric.set_ylabel('Metric')\n",
"ax_metric.set_title('Validation metric curve')\n",
"\n",
"ax_loss.xaxis.set_major_locator(MaxNLocator(integer=True))\n",
"ax_loss.set_xlabel('Iteration')\n",
"ax_loss.set_ylabel('Loss')\n",
"ax_loss.set_title('Validation loss curve')\n",
"\n",
"for mst_key in df_results['mst_key']:\n",
" df_output_info = %sql SELECT validation_metrics,validation_loss,metrics_iters FROM automl_output_info WHERE mst_key = $mst_key;\n",
" df_output_info = df_output_info.DataFrame()\n",
" validation_metrics = df_output_info['validation_metrics'][0]\n",
" validation_loss = df_output_info['validation_loss'][0]\n",
" iters = df_output_info['metrics_iters'][0]\n",
" \n",
" #ax_metric.plot(iters, validation_metrics, label=mst_key, marker='o')\n",
" ax_metric.plot(iters, validation_metrics, marker='o')\n",
" #ax_loss.plot(iters, validation_loss, label=mst_key, marker='o')\n",
" ax_loss.plot(iters, validation_loss, marker='o')\n",
"\n",
"plt.legend();\n",
"# fig.savefig('./lc_keras_fit.png', dpi = 300)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"<a id=\"hyperopt\"></a>\n",
"# 5. Hyperopt"
]
},
{
"cell_type": "code",
"execution_count": 22,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Done.\n",
"1 rows affected.\n"
]
},
{
"data": {
"text/html": [
"<table>\n",
" <tr>\n",
" <th>madlib_keras_automl</th>\n",
" </tr>\n",
" <tr>\n",
" <td></td>\n",
" </tr>\n",
"</table>"
],
"text/plain": [
"[('',)]"
]
},
"execution_count": 22,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"%%sql\n",
"DROP TABLE IF EXISTS automl_output, automl_output_info, automl_output_summary, automl_mst_table, automl_mst_table_summary;\n",
"\n",
"SELECT madlib.madlib_keras_automl('iris_train_packed', -- source table\n",
" 'automl_output', -- model output table\n",
" 'model_arch_library', -- model architecture table\n",
" 'automl_mst_table', -- model selection output table\n",
" ARRAY[1,2], -- model IDs\n",
" $${\n",
" 'loss': ['categorical_crossentropy'], \n",
" 'optimizer_params_list': [ \n",
" {'optimizer': ['Adam'],'lr': [0.001, 0.1, 'log']},\n",
" {'optimizer': ['RMSprop'],'lr': [0.001, 0.1, 'log']}\n",
" ],\n",
" 'metrics': ['accuracy']\n",
" } $$, -- compile param grid\n",
" $${'batch_size': [4, 8], 'epochs': [1]}$$, -- fit params grid\n",
" 'hyperopt', -- autoML method\n",
" 'num_configs=20, num_iterations=10, algorithm=tpe', -- autoML params\n",
" NULL, -- random state\n",
" NULL, -- object table\n",
" FALSE, -- use GPUs\n",
" 'iris_test_packed', -- validation table\n",
" 1, -- metrics compute freq\n",
" NULL, -- name\n",
" NULL); -- descr"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"View the model summary"
]
},
{
"cell_type": "code",
"execution_count": 23,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"1 rows affected.\n"
]
},
{
"data": {
"text/html": [
"<table>\n",
" <tr>\n",
" <th>source_table</th>\n",
" <th>validation_table</th>\n",
" <th>model</th>\n",
" <th>model_info</th>\n",
" <th>dependent_varname</th>\n",
" <th>independent_varname</th>\n",
" <th>model_arch_table</th>\n",
" <th>model_selection_table</th>\n",
" <th>automl_method</th>\n",
" <th>automl_params</th>\n",
" <th>random_state</th>\n",
" <th>object_table</th>\n",
" <th>use_gpus</th>\n",
" <th>metrics_compute_frequency</th>\n",
" <th>name</th>\n",
" <th>description</th>\n",
" <th>start_training_time</th>\n",
" <th>end_training_time</th>\n",
" <th>madlib_version</th>\n",
" <th>num_classes</th>\n",
" <th>class_text_class_values</th>\n",
" <th>dependent_vartype</th>\n",
" <th>normalizing_const</th>\n",
" </tr>\n",
" <tr>\n",
" <td>iris_train_packed</td>\n",
" <td>iris_test_packed</td>\n",
" <td>automl_output</td>\n",
" <td>automl_output_info</td>\n",
" <td>[u'class_text']</td>\n",
" <td>[u'attributes']</td>\n",
" <td>model_arch_library</td>\n",
" <td>automl_mst_table</td>\n",
" <td>hyperopt</td>\n",
" <td>num_configs=20, num_iterations=10, algorithm=tpe</td>\n",
" <td>None</td>\n",
" <td>None</td>\n",
" <td>False</td>\n",
" <td>1</td>\n",
" <td>None</td>\n",
" <td>None</td>\n",
" <td>2021-03-05 23:59:31</td>\n",
" <td>2021-03-06 00:03:57</td>\n",
" <td>1.18.0-dev</td>\n",
" <td>[1]</td>\n",
" <td>[u'Iris-setosa', u'Iris-versicolor', u'Iris-virginica']</td>\n",
" <td>[u'character varying']</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
"</table>"
],
"text/plain": [
"[(u'iris_train_packed', u'iris_test_packed', u'automl_output', u'automl_output_info', [u'class_text'], [u'attributes'], u'model_arch_library', u'automl_mst_table', u'hyperopt', u'num_configs=20, num_iterations=10, algorithm=tpe', None, None, False, 1, None, None, datetime.datetime(2021, 3, 5, 23, 59, 31), datetime.datetime(2021, 3, 6, 0, 3, 57), u'1.18.0-dev', [1], [u'Iris-setosa', u'Iris-versicolor', u'Iris-virginica'], [u'character varying'], 1.0)]"
]
},
"execution_count": 23,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"%%sql\n",
"SELECT * FROM automl_output_summary;"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"View the results for each model"
]
},
{
"cell_type": "code",
"execution_count": 24,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"20 rows affected.\n"
]
},
{
"data": {
"text/html": [
"<table>\n",
" <tr>\n",
" <th>mst_key</th>\n",
" <th>model_id</th>\n",
" <th>compile_params</th>\n",
" <th>fit_params</th>\n",
" <th>model_type</th>\n",
" <th>model_size</th>\n",
" <th>metrics_elapsed_time</th>\n",
" <th>metrics_type</th>\n",
" <th>loss_type</th>\n",
" <th>training_metrics_final</th>\n",
" <th>training_loss_final</th>\n",
" <th>training_metrics</th>\n",
" <th>training_loss</th>\n",
" <th>validation_metrics_final</th>\n",
" <th>validation_loss_final</th>\n",
" <th>validation_metrics</th>\n",
" <th>validation_loss</th>\n",
" <th>metrics_iters</th>\n",
" </tr>\n",
" <tr>\n",
" <td>5</td>\n",
" <td>2</td>\n",
" <td>optimizer='RMSprop(lr=0.0084793872639979)',metrics=['accuracy'],loss='categorical_crossentropy'</td>\n",
" <td>epochs=1,batch_size=4</td>\n",
" <td>madlib_keras</td>\n",
" <td>1.18359375</td>\n",
" <td>[56.9403030872345, 59.805566072464, 62.2339789867401, 64.8922078609467, 67.5616340637207, 70.2253429889679, 72.8736228942871, 75.5874469280243, 78.2902030944824, 80.9871909618378]</td>\n",
" <td>[u'accuracy']</td>\n",
" <td>categorical_crossentropy</td>\n",
" <td>0.975000023842</td>\n",
" <td>0.0910520926118</td>\n",
" <td>[0.649999976158142, 0.891666650772095, 0.883333325386047, 0.949999988079071, 0.975000023841858, 0.883333325386047, 0.850000023841858, 0.949999988079071, 0.975000023841858, 0.975000023841858]</td>\n",
" <td>[0.559232711791992, 0.335382640361786, 0.259929001331329, 0.158979862928391, 0.114544428884983, 0.269487291574478, 0.293675005435944, 0.0902178362011909, 0.0766977593302727, 0.0910520926117897]</td>\n",
" <td>0.966666638851</td>\n",
" <td>0.0768957436085</td>\n",
" <td>[0.833333313465118, 0.933333337306976, 0.899999976158142, 0.966666638851166, 0.966666638851166, 0.899999976158142, 0.899999976158142, 0.933333337306976, 0.966666638851166, 0.966666638851166]</td>\n",
" <td>[0.485892802476883, 0.249617904424667, 0.258282363414764, 0.11016520857811, 0.0912857726216316, 0.280073672533035, 0.178015038371086, 0.087411992251873, 0.062506839632988, 0.0768957436084747]</td>\n",
" <td>[1, 2, 3, 4, 5, 6, 7, 8, 9, 10]</td>\n",
" </tr>\n",
" <tr>\n",
" <td>14</td>\n",
" <td>1</td>\n",
" <td>optimizer='RMSprop(lr=0.03366551083145706)',metrics=['accuracy'],loss='categorical_crossentropy'</td>\n",
" <td>epochs=1,batch_size=8</td>\n",
" <td>madlib_keras</td>\n",
" <td>0.75390625</td>\n",
" <td>[161.690346240997, 164.041937112808, 166.454420089722, 168.906048059464, 171.067217111588, 173.555004119873, 175.944698095322, 178.445127248764, 180.502294063568, 183.037788152695]</td>\n",
" <td>[u'accuracy']</td>\n",
" <td>categorical_crossentropy</td>\n",
" <td>0.949999988079</td>\n",
" <td>0.144752591848</td>\n",
" <td>[0.316666662693024, 0.666666686534882, 0.716666638851166, 0.641666650772095, 0.675000011920929, 0.975000023841858, 0.791666686534882, 0.975000023841858, 0.966666638851166, 0.949999988079071]</td>\n",
" <td>[1.57745933532715, 0.405172228813171, 0.471270889043808, 1.00022745132446, 0.840015530586243, 0.128021001815796, 0.473532497882843, 0.091586634516716, 0.112696528434753, 0.144752591848373]</td>\n",
" <td>0.966666638851</td>\n",
" <td>0.100186347961</td>\n",
" <td>[0.433333337306976, 0.666666686534882, 0.899999976158142, 0.766666650772095, 0.866666674613953, 0.966666638851166, 0.899999976158142, 0.933333337306976, 0.966666638851166, 0.966666638851166]</td>\n",
" <td>[1.36917245388031, 0.372486144304276, 0.266377687454224, 0.571163833141327, 0.457086622714996, 0.103041857481003, 0.276452839374542, 0.0908508822321892, 0.0997116342186928, 0.100186347961426]</td>\n",
" <td>[1, 2, 3, 4, 5, 6, 7, 8, 9, 10]</td>\n",
" </tr>\n",
" <tr>\n",
" <td>15</td>\n",
" <td>1</td>\n",
" <td>optimizer='Adam(lr=0.009794369846837002)',metrics=['accuracy'],loss='categorical_crossentropy'</td>\n",
" <td>epochs=1,batch_size=8</td>\n",
" <td>madlib_keras</td>\n",
" <td>0.75390625</td>\n",
" <td>[186.611872196198, 188.95641207695, 191.037184238434, 193.397297143936, 195.740861177444, 197.805513143539, 200.180992126465, 202.689172029495, 205.040098190308, 207.208242177963]</td>\n",
" <td>[u'accuracy']</td>\n",
" <td>categorical_crossentropy</td>\n",
" <td>0.949999988079</td>\n",
" <td>0.116746708751</td>\n",
" <td>[0.75, 0.975000023841858, 0.850000023841858, 0.941666662693024, 0.933333337306976, 0.949999988079071, 0.949999988079071, 0.983333349227905, 0.958333313465118, 0.949999988079071]</td>\n",
" <td>[0.5159512758255, 0.353324204683304, 0.333910763263702, 0.245715036988258, 0.188893154263496, 0.161517903208733, 0.137443989515305, 0.122971840202808, 0.14612153172493, 0.116746708750725]</td>\n",
" <td>0.966666638851</td>\n",
" <td>0.106192082167</td>\n",
" <td>[0.899999976158142, 0.966666638851166, 0.899999976158142, 0.966666638851166, 0.933333337306976, 0.933333337306976, 0.966666638851166, 0.966666638851166, 0.966666638851166, 0.966666638851166]</td>\n",
" <td>[0.423073083162308, 0.298538327217102, 0.234973803162575, 0.176778241991997, 0.170526877045631, 0.145023569464684, 0.119270212948322, 0.103897586464882, 0.104170136153698, 0.106192082166672]</td>\n",
" <td>[1, 2, 3, 4, 5, 6, 7, 8, 9, 10]</td>\n",
" </tr>\n",
" <tr>\n",
" <td>6</td>\n",
" <td>2</td>\n",
" <td>optimizer='Adam(lr=0.007581048101981366)',metrics=['accuracy'],loss='categorical_crossentropy'</td>\n",
" <td>epochs=1,batch_size=8</td>\n",
" <td>madlib_keras</td>\n",
" <td>1.18359375</td>\n",
" <td>[57.225380897522, 60.0725290775299, 62.731920003891, 65.1544499397278, 67.8143260478973, 70.4762139320374, 73.1227269172668, 75.8475530147552, 78.555095911026, 81.2564718723297]</td>\n",
" <td>[u'accuracy']</td>\n",
" <td>categorical_crossentropy</td>\n",
" <td>0.958333313465</td>\n",
" <td>0.133664950728</td>\n",
" <td>[0.649999976158142, 0.883333325386047, 0.941666662693024, 0.899999976158142, 0.958333313465118, 0.925000011920929, 0.941666662693024, 0.933333337306976, 0.983333349227905, 0.958333313465118]</td>\n",
" <td>[1.03808128833771, 0.883756637573242, 0.686505734920502, 0.517532765865326, 0.401096671819687, 0.259793311357498, 0.177235946059227, 0.168946355581284, 0.128713861107826, 0.133664950728416]</td>\n",
" <td>0.966666638851</td>\n",
" <td>0.122641228139</td>\n",
" <td>[0.633333325386047, 0.899999976158142, 0.933333337306976, 0.933333337306976, 0.966666638851166, 0.933333337306976, 0.933333337306976, 0.933333337306976, 0.966666638851166, 0.966666638851166]</td>\n",
" <td>[1.02865540981293, 0.850838720798492, 0.612184524536133, 0.452387690544128, 0.33221709728241, 0.23906472325325, 0.165990635752678, 0.164969280362129, 0.12097629904747, 0.1226412281394]</td>\n",
" <td>[1, 2, 3, 4, 5, 6, 7, 8, 9, 10]</td>\n",
" </tr>\n",
" <tr>\n",
" <td>12</td>\n",
" <td>1</td>\n",
" <td>optimizer='RMSprop(lr=0.012596538573477555)',metrics=['accuracy'],loss='categorical_crossentropy'</td>\n",
" <td>epochs=1,batch_size=8</td>\n",
" <td>madlib_keras</td>\n",
" <td>0.75390625</td>\n",
" <td>[137.034833192825, 139.500956058502, 141.807043075562, 143.897747039795, 146.264532089233, 148.888093233109, 150.934833049774, 153.475459098816, 155.848874092102, 158.239592075348]</td>\n",
" <td>[u'accuracy']</td>\n",
" <td>categorical_crossentropy</td>\n",
" <td>0.916666686535</td>\n",
" <td>0.184266731143</td>\n",
" <td>[0.566666662693024, 0.933333337306976, 0.649999976158142, 0.666666686534882, 0.808333337306976, 0.891666650772095, 0.891666650772095, 0.975000023841858, 0.933333337306976, 0.916666686534882]</td>\n",
" <td>[0.829304933547974, 0.631127297878265, 0.597909092903137, 0.552545011043549, 0.428654760122299, 0.233174994587898, 0.236562281847, 0.119615346193314, 0.191903278231621, 0.184266731142998]</td>\n",
" <td>0.966666638851</td>\n",
" <td>0.124655880034</td>\n",
" <td>[0.699999988079071, 0.899999976158142, 0.800000011920929, 0.833333313465118, 0.899999976158142, 0.933333337306976, 0.866666674613953, 1.0, 0.966666638851166, 0.966666638851166]</td>\n",
" <td>[0.74066150188446, 0.532437741756439, 0.480882078409195, 0.435436576604843, 0.310187846422195, 0.234515085816383, 0.247250944375992, 0.107902131974697, 0.136675015091896, 0.12465588003397]</td>\n",
" <td>[1, 2, 3, 4, 5, 6, 7, 8, 9, 10]</td>\n",
" </tr>\n",
" <tr>\n",
" <td>9</td>\n",
" <td>2</td>\n",
" <td>optimizer='RMSprop(lr=0.005441362966347114)',metrics=['accuracy'],loss='categorical_crossentropy'</td>\n",
" <td>epochs=1,batch_size=8</td>\n",
" <td>madlib_keras</td>\n",
" <td>1.18359375</td>\n",
" <td>[109.630754947662, 112.341638088226, 114.763943910599, 117.389002084732, 119.991095066071, 122.593973875046, 125.238317966461, 127.8488509655, 130.375853061676, 133.020073890686]</td>\n",
" <td>[u'accuracy']</td>\n",
" <td>categorical_crossentropy</td>\n",
" <td>0.916666686535</td>\n",
" <td>0.216380029917</td>\n",
" <td>[0.641666650772095, 0.733333349227905, 0.649999976158142, 0.858333349227905, 0.958333313465118, 0.699999988079071, 0.916666686534882, 0.858333349227905, 0.966666638851166, 0.916666686534882]</td>\n",
" <td>[0.73615950345993, 0.489604264497757, 0.45263683795929, 0.37542662024498, 0.334106951951981, 0.419453173875809, 0.284875482320786, 0.27151495218277, 0.185230866074562, 0.216380029916763]</td>\n",
" <td>0.966666638851</td>\n",
" <td>0.127150848508</td>\n",
" <td>[0.766666650772095, 0.699999988079071, 0.800000011920929, 0.933333337306976, 0.966666638851166, 0.666666686534882, 0.899999976158142, 0.933333337306976, 0.966666638851166, 0.966666638851166]</td>\n",
" <td>[0.631976008415222, 0.448555260896683, 0.323729306459427, 0.28750941157341, 0.281407296657562, 0.421543717384338, 0.259464651346207, 0.158164814114571, 0.135125860571861, 0.127150848507881]</td>\n",
" <td>[1, 2, 3, 4, 5, 6, 7, 8, 9, 10]</td>\n",
" </tr>\n",
" <tr>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>optimizer='Adam(lr=0.04966544234738768)',metrics=['accuracy'],loss='categorical_crossentropy'</td>\n",
" <td>epochs=1,batch_size=8</td>\n",
" <td>madlib_keras</td>\n",
" <td>0.75390625</td>\n",
" <td>[2.26167011260986, 4.64152717590332, 7.38891315460205, 10.1575191020966, 12.6948411464691, 15.5193021297455, 17.8266370296478, 20.364767074585, 23.1241211891174, 25.6702241897583]</td>\n",
" <td>[u'accuracy']</td>\n",
" <td>categorical_crossentropy</td>\n",
" <td>0.949999988079</td>\n",
" <td>0.183234125376</td>\n",
" <td>[0.641666650772095, 0.666666686534882, 0.966666638851166, 0.958333313465118, 0.716666638851166, 0.983333349227905, 0.966666638851166, 0.983333349227905, 0.975000023841858, 0.949999988079071]</td>\n",
" <td>[0.829066038131714, 0.490932732820511, 0.341925740242004, 0.215810611844063, 0.400910943746567, 0.107548490166664, 0.0985226780176163, 0.0732712596654892, 0.070111908018589, 0.183234125375748]</td>\n",
" <td>0.966666638851</td>\n",
" <td>0.137178555131</td>\n",
" <td>[0.866666674613953, 0.666666686534882, 0.966666638851166, 0.966666638851166, 0.699999988079071, 0.966666638851166, 0.966666638851166, 0.933333337306976, 1.0, 0.966666638851166]</td>\n",
" <td>[0.843752980232239, 0.435137718915939, 0.26888644695282, 0.157842606306076, 0.406648069620132, 0.0976309478282928, 0.0788726136088371, 0.0751720294356346, 0.0686705932021141, 0.137178555130959]</td>\n",
" <td>[1, 2, 3, 4, 5, 6, 7, 8, 9, 10]</td>\n",
" </tr>\n",
" <tr>\n",
" <td>3</td>\n",
" <td>1</td>\n",
" <td>optimizer='Adam(lr=0.0023223781742022285)',metrics=['accuracy'],loss='categorical_crossentropy'</td>\n",
" <td>epochs=1,batch_size=4</td>\n",
" <td>madlib_keras</td>\n",
" <td>0.75390625</td>\n",
" <td>[29.5305609703064, 31.8714768886566, 34.5841488838196, 37.194139957428, 40.0518889427185, 42.6473689079285, 44.9830038547516, 47.734827041626, 50.3327059745789, 52.9546790122986]</td>\n",
" <td>[u'accuracy']</td>\n",
" <td>categorical_crossentropy</td>\n",
" <td>0.966666638851</td>\n",
" <td>0.247659549117</td>\n",
" <td>[0.641666650772095, 0.691666662693024, 0.641666650772095, 0.966666638851166, 0.941666662693024, 0.958333313465118, 0.933333337306976, 0.925000011920929, 0.966666638851166, 0.966666638851166]</td>\n",
" <td>[0.949797213077545, 0.797480285167694, 0.672827661037445, 0.523928940296173, 0.444453626871109, 0.386174380779266, 0.347499698400497, 0.321201831102371, 0.278330504894257, 0.247659549117088]</td>\n",
" <td>0.966666638851</td>\n",
" <td>0.198830261827</td>\n",
" <td>[0.766666650772095, 0.833333313465118, 0.766666650772095, 0.966666638851166, 0.966666638851166, 0.933333337306976, 0.966666638851166, 0.899999976158142, 0.966666638851166, 0.966666638851166]</td>\n",
" <td>[0.931245148181915, 0.763193428516388, 0.600658059120178, 0.456866592168808, 0.373299777507782, 0.326453566551208, 0.275230079889297, 0.284671515226364, 0.221188083291054, 0.198830261826515]</td>\n",
" <td>[1, 2, 3, 4, 5, 6, 7, 8, 9, 10]</td>\n",
" </tr>\n",
" <tr>\n",
" <td>7</td>\n",
" <td>1</td>\n",
" <td>optimizer='RMSprop(lr=0.0014467801648012073)',metrics=['accuracy'],loss='categorical_crossentropy'</td>\n",
" <td>epochs=1,batch_size=4</td>\n",
" <td>madlib_keras</td>\n",
" <td>0.75390625</td>\n",
" <td>[84.6684620380402, 86.9988820552826, 89.4947271347046, 91.8522582054138, 93.9668672084808, 96.3584721088409, 98.7448561191559, 101.170181035995, 103.282526016235, 105.678196191788]</td>\n",
" <td>[u'accuracy']</td>\n",
" <td>categorical_crossentropy</td>\n",
" <td>0.966666638851</td>\n",
" <td>0.395356565714</td>\n",
" <td>[0.625, 0.641666650772095, 0.741666674613953, 0.883333325386047, 0.833333313465118, 0.941666662693024, 0.949999988079071, 0.983333349227905, 0.875, 0.966666638851166]</td>\n",
" <td>[0.941141128540039, 0.820547699928284, 0.723011374473572, 0.646571576595306, 0.57060444355011, 0.514499425888062, 0.46852970123291, 0.439025938510895, 0.416335105895996, 0.395356565713882]</td>\n",
" <td>0.966666638851</td>\n",
" <td>0.326709568501</td>\n",
" <td>[0.766666650772095, 0.766666650772095, 0.899999976158142, 0.933333337306976, 0.933333337306976, 0.966666638851166, 0.966666638851166, 0.966666638851166, 0.933333337306976, 0.966666638851166]</td>\n",
" <td>[0.941896796226501, 0.816571235656738, 0.707062959671021, 0.61734527349472, 0.521940350532532, 0.45942959189415, 0.405136495828629, 0.374987095594406, 0.33730074763298, 0.326709568500519]</td>\n",
" <td>[1, 2, 3, 4, 5, 6, 7, 8, 9, 10]</td>\n",
" </tr>\n",
" <tr>\n",
" <td>19</td>\n",
" <td>2</td>\n",
" <td>optimizer='Adam(lr=0.0011757973913283008)',metrics=['accuracy'],loss='categorical_crossentropy'</td>\n",
" <td>epochs=1,batch_size=8</td>\n",
" <td>madlib_keras</td>\n",
" <td>1.18359375</td>\n",
" <td>[237.369596242905, 240.072783231735, 242.490661382675, 245.210073232651, 247.916568279266, 250.679228305817, 253.465747356415, 256.328309297562, 259.131007194519, 262.085569381714]</td>\n",
" <td>[u'accuracy']</td>\n",
" <td>categorical_crossentropy</td>\n",
" <td>0.916666686535</td>\n",
" <td>0.567601382732</td>\n",
" <td>[0.333333343267441, 0.441666662693024, 0.433333337306976, 0.349999994039536, 0.349999994039536, 0.675000011920929, 0.683333337306976, 0.800000011920929, 0.774999976158142, 0.916666686534882]</td>\n",
" <td>[1.14459049701691, 1.08465170860291, 1.02045607566833, 0.952999651432037, 0.883513271808624, 0.809052526950836, 0.748401284217834, 0.682490110397339, 0.620046377182007, 0.567601382732391]</td>\n",
" <td>0.966666638851</td>\n",
" <td>0.512901842594</td>\n",
" <td>[0.333333343267441, 0.400000005960464, 0.400000005960464, 0.366666674613953, 0.366666674613953, 0.800000011920929, 0.800000011920929, 0.866666674613953, 0.866666674613953, 0.966666638851166]</td>\n",
" <td>[1.21284127235413, 1.13662087917328, 1.04775261878967, 0.957895994186401, 0.871163666248322, 0.780500650405884, 0.705705106258392, 0.636253237724304, 0.558390736579895, 0.512901842594147]</td>\n",
" <td>[1, 2, 3, 4, 5, 6, 7, 8, 9, 10]</td>\n",
" </tr>\n",
" <tr>\n",
" <td>17</td>\n",
" <td>1</td>\n",
" <td>optimizer='RMSprop(lr=0.003695186053629043)',metrics=['accuracy'],loss='categorical_crossentropy'</td>\n",
" <td>epochs=1,batch_size=8</td>\n",
" <td>madlib_keras</td>\n",
" <td>0.75390625</td>\n",
" <td>[211.166339159012, 213.628123044968, 216.070516109467, 218.28012919426, 220.77138209343, 223.166202068329, 225.899930000305, 228.167545080185, 230.690491199493, 233.073115110397]</td>\n",
" <td>[u'accuracy']</td>\n",
" <td>categorical_crossentropy</td>\n",
" <td>0.966666638851</td>\n",
" <td>0.114436306059</td>\n",
" <td>[0.641666650772095, 0.875, 0.824999988079071, 0.824999988079071, 0.958333313465118, 0.866666674613953, 0.966666638851166, 0.941666662693024, 0.958333313465118, 0.966666638851166]</td>\n",
" <td>[0.718437075614929, 0.535359025001526, 0.403026401996613, 0.348048120737076, 0.244051590561867, 0.264052510261536, 0.1720110476017, 0.164029255509377, 0.154526039958, 0.114436306059361]</td>\n",
" <td>0.933333337307</td>\n",
" <td>0.107093170285</td>\n",
" <td>[0.766666650772095, 0.933333337306976, 0.899999976158142, 0.833333313465118, 0.933333337306976, 0.933333337306976, 0.966666638851166, 0.933333337306976, 0.966666638851166, 0.933333337306976]</td>\n",
" <td>[0.647899329662323, 0.474290877580643, 0.308415770530701, 0.318869024515152, 0.206334576010704, 0.250639617443085, 0.129751890897751, 0.156522572040558, 0.112601205706596, 0.107093170285225]</td>\n",
" <td>[1, 2, 3, 4, 5, 6, 7, 8, 9, 10]</td>\n",
" </tr>\n",
" <tr>\n",
" <td>11</td>\n",
" <td>1</td>\n",
" <td>optimizer='Adam(lr=0.03271173767396424)',metrics=['accuracy'],loss='categorical_crossentropy'</td>\n",
" <td>epochs=1,batch_size=4</td>\n",
" <td>madlib_keras</td>\n",
" <td>0.75390625</td>\n",
" <td>[136.810528039932, 139.271977186203, 141.348733186722, 143.678931236267, 146.042705059052, 148.659409046173, 150.713799238205, 153.240673065186, 155.618861198425, 158.003229141235]</td>\n",
" <td>[u'accuracy']</td>\n",
" <td>categorical_crossentropy</td>\n",
" <td>0.899999976158</td>\n",
" <td>0.200596183538</td>\n",
" <td>[0.341666668653488, 0.925000011920929, 0.958333313465118, 0.675000011920929, 0.966666638851166, 0.766666650772095, 0.975000023841858, 0.75, 0.975000023841858, 0.899999976158142]</td>\n",
" <td>[1.04381895065308, 0.384325951337814, 0.263480663299561, 0.593676149845123, 0.141404688358307, 0.362050473690033, 0.0923048332333565, 0.351189643144608, 0.0946881100535393, 0.200596183538437]</td>\n",
" <td>0.899999976158</td>\n",
" <td>0.257636517286</td>\n",
" <td>[0.533333361148834, 0.866666674613953, 0.966666638851166, 0.800000011920929, 0.966666638851166, 0.833333313465118, 0.966666638851166, 0.866666674613953, 0.966666638851166, 0.899999976158142]</td>\n",
" <td>[0.91362202167511, 0.340268641710281, 0.21289549767971, 0.362329840660095, 0.136535987257957, 0.327440768480301, 0.111000411212444, 0.227803841233253, 0.111130490899086, 0.257636517286301]</td>\n",
" <td>[1, 2, 3, 4, 5, 6, 7, 8, 9, 10]</td>\n",
" </tr>\n",
" <tr>\n",
" <td>13</td>\n",
" <td>1</td>\n",
" <td>optimizer='RMSprop(lr=0.0027814197503322115)',metrics=['accuracy'],loss='categorical_crossentropy'</td>\n",
" <td>epochs=1,batch_size=8</td>\n",
" <td>madlib_keras</td>\n",
" <td>0.75390625</td>\n",
" <td>[161.464279174805, 163.823823213577, 166.230634212494, 168.657960176468, 170.846117019653, 173.335704088211, 175.715650081635, 178.106207132339, 180.278338193893, 182.815184116364]</td>\n",
" <td>[u'accuracy']</td>\n",
" <td>categorical_crossentropy</td>\n",
" <td>0.933333337307</td>\n",
" <td>0.351116120815</td>\n",
" <td>[0.600000023841858, 0.558333337306976, 0.541666686534882, 0.600000023841858, 0.899999976158142, 0.916666686534882, 0.850000023841858, 0.925000011920929, 0.933333337306976, 0.933333337306976]</td>\n",
" <td>[0.9764444231987, 0.860457479953766, 0.76110851764679, 0.688599288463593, 0.623845517635345, 0.558117687702179, 0.516568541526794, 0.438872784376144, 0.389935582876205, 0.351116120815277]</td>\n",
" <td>0.899999976158</td>\n",
" <td>0.326276868582</td>\n",
" <td>[0.433333337306976, 0.433333337306976, 0.5, 0.433333337306976, 0.899999976158142, 0.866666674613953, 0.933333337306976, 0.866666674613953, 0.899999976158142, 0.899999976158142]</td>\n",
" <td>[1.03803777694702, 0.913994610309601, 0.794906616210938, 0.723303020000458, 0.652373254299164, 0.566653609275818, 0.481746405363083, 0.454111516475677, 0.379933565855026, 0.326276868581772]</td>\n",
" <td>[1, 2, 3, 4, 5, 6, 7, 8, 9, 10]</td>\n",
" </tr>\n",
" <tr>\n",
" <td>2</td>\n",
" <td>2</td>\n",
" <td>optimizer='Adam(lr=0.035340389425615855)',metrics=['accuracy'],loss='categorical_crossentropy'</td>\n",
" <td>epochs=1,batch_size=8</td>\n",
" <td>madlib_keras</td>\n",
" <td>1.18359375</td>\n",
" <td>[2.53016018867493, 5.03768014907837, 7.64597201347351, 10.4127900600433, 13.0584251880646, 15.7928349971771, 18.0860531330109, 20.625785112381, 23.3826050758362, 25.9297461509705]</td>\n",
" <td>[u'accuracy']</td>\n",
" <td>categorical_crossentropy</td>\n",
" <td>0.875</td>\n",
" <td>0.28657540679</td>\n",
" <td>[0.850000023841858, 0.491666674613953, 0.941666662693024, 0.783333361148834, 0.925000011920929, 0.850000023841858, 0.966666638851166, 0.958333313465118, 0.908333361148834, 0.875]</td>\n",
" <td>[0.313798636198044, 0.746647894382477, 0.232485517859459, 0.384049296379089, 0.201492115855217, 0.276773244142532, 0.144450753927231, 0.116710871458054, 0.210491970181465, 0.28657540678978]</td>\n",
" <td>0.899999976158</td>\n",
" <td>0.334158778191</td>\n",
" <td>[0.833333313465118, 0.533333361148834, 0.833333313465118, 0.899999976158142, 0.899999976158142, 0.833333313465118, 0.966666638851166, 1.0, 0.899999976158142, 0.899999976158142]</td>\n",
" <td>[0.281513780355453, 0.781840145587921, 0.252955704927444, 0.219736546278, 0.268592208623886, 0.332309901714325, 0.131899908185005, 0.0595534667372704, 0.255705177783966, 0.334158778190613]</td>\n",
" <td>[1, 2, 3, 4, 5, 6, 7, 8, 9, 10]</td>\n",
" </tr>\n",
" <tr>\n",
" <td>8</td>\n",
" <td>1</td>\n",
" <td>optimizer='Adam(lr=0.08208550087461897)',metrics=['accuracy'],loss='categorical_crossentropy'</td>\n",
" <td>epochs=1,batch_size=8</td>\n",
" <td>madlib_keras</td>\n",
" <td>0.75390625</td>\n",
" <td>[84.8872451782227, 87.2208690643311, 89.7248260974884, 92.1014380455017, 94.1999170780182, 96.5836410522461, 98.9723200798035, 101.409075021744, 103.511981010437, 105.902093172073]</td>\n",
" <td>[u'accuracy']</td>\n",
" <td>categorical_crossentropy</td>\n",
" <td>0.766666650772</td>\n",
" <td>0.591654956341</td>\n",
" <td>[0.333333343267441, 0.641666650772095, 0.566666662693024, 0.591666638851166, 0.758333325386047, 0.666666686534882, 0.966666638851166, 0.916666686534882, 0.949999988079071, 0.766666650772095]</td>\n",
" <td>[1.02616000175476, 0.486202239990234, 0.636112213134766, 0.692184090614319, 0.505898773670197, 0.467963546514511, 0.268672525882721, 0.176122322678566, 0.122547559440136, 0.59165495634079]</td>\n",
" <td>0.899999976158</td>\n",
" <td>0.33915963769</td>\n",
" <td>[0.333333343267441, 0.766666650772095, 0.733333349227905, 0.766666650772095, 0.733333349227905, 0.666666686534882, 0.966666638851166, 0.899999976158142, 0.899999976158142, 0.899999976158142]</td>\n",
" <td>[1.12080752849579, 0.381140530109406, 0.5174320936203, 0.473030716180801, 0.607473373413086, 0.409501492977142, 0.212725415825844, 0.296080023050308, 0.18353745341301, 0.33915963768959]</td>\n",
" <td>[1, 2, 3, 4, 5, 6, 7, 8, 9, 10]</td>\n",
" </tr>\n",
" <tr>\n",
" <td>16</td>\n",
" <td>1</td>\n",
" <td>optimizer='Adam(lr=0.0025753473010720596)',metrics=['accuracy'],loss='categorical_crossentropy'</td>\n",
" <td>epochs=1,batch_size=8</td>\n",
" <td>madlib_keras</td>\n",
" <td>0.75390625</td>\n",
" <td>[186.835414171219, 189.195631027222, 191.254861116409, 193.619318246841, 195.966614246368, 198.311106204987, 200.407158136368, 202.908673048019, 205.313441038132, 207.438939094543]</td>\n",
" <td>[u'accuracy']</td>\n",
" <td>categorical_crossentropy</td>\n",
" <td>0.891666650772</td>\n",
" <td>0.950204193592</td>\n",
" <td>[0.358333319425583, 0.358333319425583, 0.358333319425583, 0.449999988079071, 0.400000005960464, 0.516666650772095, 0.583333313465118, 0.608333349227905, 0.899999976158142, 0.891666650772095]</td>\n",
" <td>[1.09640550613403, 1.08471190929413, 1.0751405954361, 1.06720495223999, 1.06165635585785, 1.0469172000885, 1.0301650762558, 1.00463593006134, 0.979537725448608, 0.950204193592072]</td>\n",
" <td>0.866666674614</td>\n",
" <td>0.931918859482</td>\n",
" <td>[0.233333334326744, 0.233333334326744, 0.233333334326744, 0.366666674613953, 0.266666680574417, 0.400000005960464, 0.400000005960464, 0.433333337306976, 0.833333313465118, 0.866666674613953]</td>\n",
" <td>[1.10118973255157, 1.08938491344452, 1.07863283157349, 1.06669425964355, 1.06701147556305, 1.04324889183044, 1.02750730514526, 0.996739327907562, 0.966157376766205, 0.931918859481812]</td>\n",
" <td>[1, 2, 3, 4, 5, 6, 7, 8, 9, 10]</td>\n",
" </tr>\n",
" <tr>\n",
" <td>20</td>\n",
" <td>2</td>\n",
" <td>optimizer='RMSprop(lr=0.056702169442788934)',metrics=['accuracy'],loss='categorical_crossentropy'</td>\n",
" <td>epochs=1,batch_size=8</td>\n",
" <td>madlib_keras</td>\n",
" <td>1.18359375</td>\n",
" <td>[237.640507221222, 240.350925207138, 243.027331352234, 245.468372344971, 248.176068305969, 250.940598249435, 253.720994234085, 256.680767297745, 259.394066333771, 262.358667373657]</td>\n",
" <td>[u'accuracy']</td>\n",
" <td>categorical_crossentropy</td>\n",
" <td>0.649999976158</td>\n",
" <td>0.545458972454</td>\n",
" <td>[0.658333361148834, 0.649999976158142, 0.641666650772095, 0.641666650772095, 0.641666650772095, 0.666666686534882, 0.666666686534882, 0.666666686534882, 0.666666686534882, 0.649999976158142]</td>\n",
" <td>[0.616556286811829, 0.493021905422211, 0.488242834806442, 0.486079841852188, 0.479775160551071, 0.482189744710922, 0.496939599514008, 0.479279518127441, 0.543927192687988, 0.545458972454071]</td>\n",
" <td>0.800000011921</td>\n",
" <td>0.362693428993</td>\n",
" <td>[0.633333325386047, 0.800000011920929, 0.766666650772095, 0.766666650772095, 0.766666650772095, 0.666666686534882, 0.666666686534882, 0.666666686534882, 0.666666686534882, 0.800000011920929]</td>\n",
" <td>[0.53449285030365, 0.394388288259506, 0.390281409025192, 0.385460764169693, 0.392662823200226, 0.410547375679016, 0.439140349626541, 0.395850986242294, 0.503270268440247, 0.362693428993225]</td>\n",
" <td>[1, 2, 3, 4, 5, 6, 7, 8, 9, 10]</td>\n",
" </tr>\n",
" <tr>\n",
" <td>4</td>\n",
" <td>2</td>\n",
" <td>optimizer='Adam(lr=0.06312207575548352)',metrics=['accuracy'],loss='categorical_crossentropy'</td>\n",
" <td>epochs=1,batch_size=8</td>\n",
" <td>madlib_keras</td>\n",
" <td>1.18359375</td>\n",
" <td>[29.8041570186615, 32.351331949234, 34.8423700332642, 37.4489560127258, 40.3089909553528, 42.915864944458, 45.6521019935608, 47.9889349937439, 50.5978739261627, 53.2138829231262]</td>\n",
" <td>[u'accuracy']</td>\n",
" <td>categorical_crossentropy</td>\n",
" <td>0.641666650772</td>\n",
" <td>0.471347987652</td>\n",
" <td>[0.666666686534882, 0.641666650772095, 0.641666650772095, 0.366666674613953, 0.666666686534882, 0.966666638851166, 0.483333319425583, 0.641666650772095, 0.941666662693024, 0.641666650772095]</td>\n",
" <td>[0.520724713802338, 0.578253924846649, 0.518827021121979, 1.67398142814636, 0.512235522270203, 0.131752595305443, 1.25291848182678, 0.453146934509277, 0.185879185795784, 0.471347987651825]</td>\n",
" <td>0.766666650772</td>\n",
" <td>0.337222576141</td>\n",
" <td>[0.666666686534882, 0.766666650772095, 0.766666650772095, 0.333333343267441, 0.666666686534882, 0.933333337306976, 0.566666662693024, 0.766666650772095, 0.899999976158142, 0.766666650772095]</td>\n",
" <td>[0.462848216295242, 0.38900101184845, 0.356701970100403, 1.92939758300781, 0.458910882472992, 0.14183434844017, 0.83171159029007, 0.332331091165543, 0.311882764101028, 0.337222576141357]</td>\n",
" <td>[1, 2, 3, 4, 5, 6, 7, 8, 9, 10]</td>\n",
" </tr>\n",
" <tr>\n",
" <td>18</td>\n",
" <td>1</td>\n",
" <td>optimizer='RMSprop(lr=0.0658839037116738)',metrics=['accuracy'],loss='categorical_crossentropy'</td>\n",
" <td>epochs=1,batch_size=8</td>\n",
" <td>madlib_keras</td>\n",
" <td>0.75390625</td>\n",
" <td>[211.389490127563, 213.85792016983, 216.39094209671, 218.503707170486, 220.992606163025, 223.471295118332, 226.145341157913, 228.394971132278, 230.912840127945, 233.303599119186]</td>\n",
" <td>[u'accuracy']</td>\n",
" <td>categorical_crossentropy</td>\n",
" <td>0.641666650772</td>\n",
" <td>0.482037603855</td>\n",
" <td>[0.800000011920929, 0.666666686534882, 0.666666686534882, 0.808333337306976, 0.683333337306976, 0.666666686534882, 0.875, 0.666666686534882, 0.666666686534882, 0.641666650772095]</td>\n",
" <td>[0.508525788784027, 0.431755125522614, 0.435203284025192, 0.344938695430756, 0.478766769170761, 0.330143094062805, 0.273075610399246, 0.479535788297653, 0.48390719294548, 0.482037603855133]</td>\n",
" <td>0.766666650772</td>\n",
" <td>0.39202862978</td>\n",
" <td>[0.833333313465118, 0.666666686534882, 0.666666686534882, 0.899999976158142, 0.666666686534882, 0.666666686534882, 0.933333337306976, 0.666666686534882, 0.666666686534882, 0.766666650772095]</td>\n",
" <td>[0.443316102027893, 0.401963800191879, 0.399077832698822, 0.240811541676521, 0.410095393657684, 0.290450870990753, 0.254536032676697, 0.396871030330658, 0.413692444562912, 0.392028629779816]</td>\n",
" <td>[1, 2, 3, 4, 5, 6, 7, 8, 9, 10]</td>\n",
" </tr>\n",
" <tr>\n",
" <td>10</td>\n",
" <td>1</td>\n",
" <td>optimizer='RMSprop(lr=0.0020197253642543623)',metrics=['accuracy'],loss='categorical_crossentropy'</td>\n",
" <td>epochs=1,batch_size=8</td>\n",
" <td>madlib_keras</td>\n",
" <td>0.75390625</td>\n",
" <td>[109.946217060089, 112.64745092392, 115.244435071945, 117.609509944916, 120.211313962936, 122.821636915207, 125.485604047775, 128.088088035583, 130.593991041183, 133.237344026566]</td>\n",
" <td>[u'accuracy']</td>\n",
" <td>categorical_crossentropy</td>\n",
" <td>0.725000023842</td>\n",
" <td>0.553534567356</td>\n",
" <td>[0.358333319425583, 0.358333319425583, 0.508333325386047, 0.916666686534882, 0.658333361148834, 0.633333325386047, 0.633333325386047, 0.641666650772095, 0.649999976158142, 0.725000023841858]</td>\n",
" <td>[1.44853103160858, 1.05627000331879, 0.960374653339386, 0.903020858764648, 0.811912178993225, 0.744573473930359, 0.693612813949585, 0.683376550674438, 0.593345999717712, 0.55353456735611]</td>\n",
" <td>0.766666650772</td>\n",
" <td>0.458936661482</td>\n",
" <td>[0.233333334326744, 0.233333334326744, 0.433333337306976, 0.933333337306976, 0.733333349227905, 0.733333349227905, 0.733333349227905, 0.766666650772095, 0.766666650772095, 0.766666650772095]</td>\n",
" <td>[1.5010712146759, 1.05707538127899, 0.939342617988586, 0.863560140132904, 0.760088205337524, 0.681271374225616, 0.617161631584167, 0.568128407001495, 0.501981496810913, 0.458936661481857]</td>\n",
" <td>[1, 2, 3, 4, 5, 6, 7, 8, 9, 10]</td>\n",
" </tr>\n",
"</table>"
],
"text/plain": [
"[(5, 2, u\"optimizer='RMSprop(lr=0.0084793872639979)',metrics=['accuracy'],loss='categorical_crossentropy'\", u'epochs=1,batch_size=4', u'madlib_keras', 1.18359375, [56.9403030872345, 59.805566072464, 62.2339789867401, 64.8922078609467, 67.5616340637207, 70.2253429889679, 72.8736228942871, 75.5874469280243, 78.2902030944824, 80.9871909618378], [u'accuracy'], u'categorical_crossentropy', 0.975000023841858, 0.0910520926117897, [0.649999976158142, 0.891666650772095, 0.883333325386047, 0.949999988079071, 0.975000023841858, 0.883333325386047, 0.850000023841858, 0.949999988079071, 0.975000023841858, 0.975000023841858], [0.559232711791992, 0.335382640361786, 0.259929001331329, 0.158979862928391, 0.114544428884983, 0.269487291574478, 0.293675005435944, 0.0902178362011909, 0.0766977593302727, 0.0910520926117897], 0.966666638851166, 0.0768957436084747, [0.833333313465118, 0.933333337306976, 0.899999976158142, 0.966666638851166, 0.966666638851166, 0.899999976158142, 0.899999976158142, 0.933333337306976, 0.966666638851166, 0.966666638851166], [0.485892802476883, 0.249617904424667, 0.258282363414764, 0.11016520857811, 0.0912857726216316, 0.280073672533035, 0.178015038371086, 0.087411992251873, 0.062506839632988, 0.0768957436084747], [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]),\n",
" (14, 1, u\"optimizer='RMSprop(lr=0.03366551083145706)',metrics=['accuracy'],loss='categorical_crossentropy'\", u'epochs=1,batch_size=8', u'madlib_keras', 0.75390625, [161.690346240997, 164.041937112808, 166.454420089722, 168.906048059464, 171.067217111588, 173.555004119873, 175.944698095322, 178.445127248764, 180.502294063568, 183.037788152695], [u'accuracy'], u'categorical_crossentropy', 0.949999988079071, 0.144752591848373, [0.316666662693024, 0.666666686534882, 0.716666638851166, 0.641666650772095, 0.675000011920929, 0.975000023841858, 0.791666686534882, 0.975000023841858, 0.966666638851166, 0.949999988079071], [1.57745933532715, 0.405172228813171, 0.471270889043808, 1.00022745132446, 0.840015530586243, 0.128021001815796, 0.473532497882843, 0.091586634516716, 0.112696528434753, 0.144752591848373], 0.966666638851166, 0.100186347961426, [0.433333337306976, 0.666666686534882, 0.899999976158142, 0.766666650772095, 0.866666674613953, 0.966666638851166, 0.899999976158142, 0.933333337306976, 0.966666638851166, 0.966666638851166], [1.36917245388031, 0.372486144304276, 0.266377687454224, 0.571163833141327, 0.457086622714996, 0.103041857481003, 0.276452839374542, 0.0908508822321892, 0.0997116342186928, 0.100186347961426], [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]),\n",
" (15, 1, u\"optimizer='Adam(lr=0.009794369846837002)',metrics=['accuracy'],loss='categorical_crossentropy'\", u'epochs=1,batch_size=8', u'madlib_keras', 0.75390625, [186.611872196198, 188.95641207695, 191.037184238434, 193.397297143936, 195.740861177444, 197.805513143539, 200.180992126465, 202.689172029495, 205.040098190308, 207.208242177963], [u'accuracy'], u'categorical_crossentropy', 0.949999988079071, 0.116746708750725, [0.75, 0.975000023841858, 0.850000023841858, 0.941666662693024, 0.933333337306976, 0.949999988079071, 0.949999988079071, 0.983333349227905, 0.958333313465118, 0.949999988079071], [0.5159512758255, 0.353324204683304, 0.333910763263702, 0.245715036988258, 0.188893154263496, 0.161517903208733, 0.137443989515305, 0.122971840202808, 0.14612153172493, 0.116746708750725], 0.966666638851166, 0.106192082166672, [0.899999976158142, 0.966666638851166, 0.899999976158142, 0.966666638851166, 0.933333337306976, 0.933333337306976, 0.966666638851166, 0.966666638851166, 0.966666638851166, 0.966666638851166], [0.423073083162308, 0.298538327217102, 0.234973803162575, 0.176778241991997, 0.170526877045631, 0.145023569464684, 0.119270212948322, 0.103897586464882, 0.104170136153698, 0.106192082166672], [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]),\n",
" (6, 2, u\"optimizer='Adam(lr=0.007581048101981366)',metrics=['accuracy'],loss='categorical_crossentropy'\", u'epochs=1,batch_size=8', u'madlib_keras', 1.18359375, [57.225380897522, 60.0725290775299, 62.731920003891, 65.1544499397278, 67.8143260478973, 70.4762139320374, 73.1227269172668, 75.8475530147552, 78.555095911026, 81.2564718723297], [u'accuracy'], u'categorical_crossentropy', 0.958333313465118, 0.133664950728416, [0.649999976158142, 0.883333325386047, 0.941666662693024, 0.899999976158142, 0.958333313465118, 0.925000011920929, 0.941666662693024, 0.933333337306976, 0.983333349227905, 0.958333313465118], [1.03808128833771, 0.883756637573242, 0.686505734920502, 0.517532765865326, 0.401096671819687, 0.259793311357498, 0.177235946059227, 0.168946355581284, 0.128713861107826, 0.133664950728416], 0.966666638851166, 0.1226412281394, [0.633333325386047, 0.899999976158142, 0.933333337306976, 0.933333337306976, 0.966666638851166, 0.933333337306976, 0.933333337306976, 0.933333337306976, 0.966666638851166, 0.966666638851166], [1.02865540981293, 0.850838720798492, 0.612184524536133, 0.452387690544128, 0.33221709728241, 0.23906472325325, 0.165990635752678, 0.164969280362129, 0.12097629904747, 0.1226412281394], [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]),\n",
" (12, 1, u\"optimizer='RMSprop(lr=0.012596538573477555)',metrics=['accuracy'],loss='categorical_crossentropy'\", u'epochs=1,batch_size=8', u'madlib_keras', 0.75390625, [137.034833192825, 139.500956058502, 141.807043075562, 143.897747039795, 146.264532089233, 148.888093233109, 150.934833049774, 153.475459098816, 155.848874092102, 158.239592075348], [u'accuracy'], u'categorical_crossentropy', 0.916666686534882, 0.184266731142998, [0.566666662693024, 0.933333337306976, 0.649999976158142, 0.666666686534882, 0.808333337306976, 0.891666650772095, 0.891666650772095, 0.975000023841858, 0.933333337306976, 0.916666686534882], [0.829304933547974, 0.631127297878265, 0.597909092903137, 0.552545011043549, 0.428654760122299, 0.233174994587898, 0.236562281847, 0.119615346193314, 0.191903278231621, 0.184266731142998], 0.966666638851166, 0.12465588003397, [0.699999988079071, 0.899999976158142, 0.800000011920929, 0.833333313465118, 0.899999976158142, 0.933333337306976, 0.866666674613953, 1.0, 0.966666638851166, 0.966666638851166], [0.74066150188446, 0.532437741756439, 0.480882078409195, 0.435436576604843, 0.310187846422195, 0.234515085816383, 0.247250944375992, 0.107902131974697, 0.136675015091896, 0.12465588003397], [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]),\n",
" (9, 2, u\"optimizer='RMSprop(lr=0.005441362966347114)',metrics=['accuracy'],loss='categorical_crossentropy'\", u'epochs=1,batch_size=8', u'madlib_keras', 1.18359375, [109.630754947662, 112.341638088226, 114.763943910599, 117.389002084732, 119.991095066071, 122.593973875046, 125.238317966461, 127.8488509655, 130.375853061676, 133.020073890686], [u'accuracy'], u'categorical_crossentropy', 0.916666686534882, 0.216380029916763, [0.641666650772095, 0.733333349227905, 0.649999976158142, 0.858333349227905, 0.958333313465118, 0.699999988079071, 0.916666686534882, 0.858333349227905, 0.966666638851166, 0.916666686534882], [0.73615950345993, 0.489604264497757, 0.45263683795929, 0.37542662024498, 0.334106951951981, 0.419453173875809, 0.284875482320786, 0.27151495218277, 0.185230866074562, 0.216380029916763], 0.966666638851166, 0.127150848507881, [0.766666650772095, 0.699999988079071, 0.800000011920929, 0.933333337306976, 0.966666638851166, 0.666666686534882, 0.899999976158142, 0.933333337306976, 0.966666638851166, 0.966666638851166], [0.631976008415222, 0.448555260896683, 0.323729306459427, 0.28750941157341, 0.281407296657562, 0.421543717384338, 0.259464651346207, 0.158164814114571, 0.135125860571861, 0.127150848507881], [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]),\n",
" (1, 1, u\"optimizer='Adam(lr=0.04966544234738768)',metrics=['accuracy'],loss='categorical_crossentropy'\", u'epochs=1,batch_size=8', u'madlib_keras', 0.75390625, [2.26167011260986, 4.64152717590332, 7.38891315460205, 10.1575191020966, 12.6948411464691, 15.5193021297455, 17.8266370296478, 20.364767074585, 23.1241211891174, 25.6702241897583], [u'accuracy'], u'categorical_crossentropy', 0.949999988079071, 0.183234125375748, [0.641666650772095, 0.666666686534882, 0.966666638851166, 0.958333313465118, 0.716666638851166, 0.983333349227905, 0.966666638851166, 0.983333349227905, 0.975000023841858, 0.949999988079071], [0.829066038131714, 0.490932732820511, 0.341925740242004, 0.215810611844063, 0.400910943746567, 0.107548490166664, 0.0985226780176163, 0.0732712596654892, 0.070111908018589, 0.183234125375748], 0.966666638851166, 0.137178555130959, [0.866666674613953, 0.666666686534882, 0.966666638851166, 0.966666638851166, 0.699999988079071, 0.966666638851166, 0.966666638851166, 0.933333337306976, 1.0, 0.966666638851166], [0.843752980232239, 0.435137718915939, 0.26888644695282, 0.157842606306076, 0.406648069620132, 0.0976309478282928, 0.0788726136088371, 0.0751720294356346, 0.0686705932021141, 0.137178555130959], [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]),\n",
" (3, 1, u\"optimizer='Adam(lr=0.0023223781742022285)',metrics=['accuracy'],loss='categorical_crossentropy'\", u'epochs=1,batch_size=4', u'madlib_keras', 0.75390625, [29.5305609703064, 31.8714768886566, 34.5841488838196, 37.194139957428, 40.0518889427185, 42.6473689079285, 44.9830038547516, 47.734827041626, 50.3327059745789, 52.9546790122986], [u'accuracy'], u'categorical_crossentropy', 0.966666638851166, 0.247659549117088, [0.641666650772095, 0.691666662693024, 0.641666650772095, 0.966666638851166, 0.941666662693024, 0.958333313465118, 0.933333337306976, 0.925000011920929, 0.966666638851166, 0.966666638851166], [0.949797213077545, 0.797480285167694, 0.672827661037445, 0.523928940296173, 0.444453626871109, 0.386174380779266, 0.347499698400497, 0.321201831102371, 0.278330504894257, 0.247659549117088], 0.966666638851166, 0.198830261826515, [0.766666650772095, 0.833333313465118, 0.766666650772095, 0.966666638851166, 0.966666638851166, 0.933333337306976, 0.966666638851166, 0.899999976158142, 0.966666638851166, 0.966666638851166], [0.931245148181915, 0.763193428516388, 0.600658059120178, 0.456866592168808, 0.373299777507782, 0.326453566551208, 0.275230079889297, 0.284671515226364, 0.221188083291054, 0.198830261826515], [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]),\n",
" (7, 1, u\"optimizer='RMSprop(lr=0.0014467801648012073)',metrics=['accuracy'],loss='categorical_crossentropy'\", u'epochs=1,batch_size=4', u'madlib_keras', 0.75390625, [84.6684620380402, 86.9988820552826, 89.4947271347046, 91.8522582054138, 93.9668672084808, 96.3584721088409, 98.7448561191559, 101.170181035995, 103.282526016235, 105.678196191788], [u'accuracy'], u'categorical_crossentropy', 0.966666638851166, 0.395356565713882, [0.625, 0.641666650772095, 0.741666674613953, 0.883333325386047, 0.833333313465118, 0.941666662693024, 0.949999988079071, 0.983333349227905, 0.875, 0.966666638851166], [0.941141128540039, 0.820547699928284, 0.723011374473572, 0.646571576595306, 0.57060444355011, 0.514499425888062, 0.46852970123291, 0.439025938510895, 0.416335105895996, 0.395356565713882], 0.966666638851166, 0.326709568500519, [0.766666650772095, 0.766666650772095, 0.899999976158142, 0.933333337306976, 0.933333337306976, 0.966666638851166, 0.966666638851166, 0.966666638851166, 0.933333337306976, 0.966666638851166], [0.941896796226501, 0.816571235656738, 0.707062959671021, 0.61734527349472, 0.521940350532532, 0.45942959189415, 0.405136495828629, 0.374987095594406, 0.33730074763298, 0.326709568500519], [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]),\n",
" (19, 2, u\"optimizer='Adam(lr=0.0011757973913283008)',metrics=['accuracy'],loss='categorical_crossentropy'\", u'epochs=1,batch_size=8', u'madlib_keras', 1.18359375, [237.369596242905, 240.072783231735, 242.490661382675, 245.210073232651, 247.916568279266, 250.679228305817, 253.465747356415, 256.328309297562, 259.131007194519, 262.085569381714], [u'accuracy'], u'categorical_crossentropy', 0.916666686534882, 0.567601382732391, [0.333333343267441, 0.441666662693024, 0.433333337306976, 0.349999994039536, 0.349999994039536, 0.675000011920929, 0.683333337306976, 0.800000011920929, 0.774999976158142, 0.916666686534882], [1.14459049701691, 1.08465170860291, 1.02045607566833, 0.952999651432037, 0.883513271808624, 0.809052526950836, 0.748401284217834, 0.682490110397339, 0.620046377182007, 0.567601382732391], 0.966666638851166, 0.512901842594147, [0.333333343267441, 0.400000005960464, 0.400000005960464, 0.366666674613953, 0.366666674613953, 0.800000011920929, 0.800000011920929, 0.866666674613953, 0.866666674613953, 0.966666638851166], [1.21284127235413, 1.13662087917328, 1.04775261878967, 0.957895994186401, 0.871163666248322, 0.780500650405884, 0.705705106258392, 0.636253237724304, 0.558390736579895, 0.512901842594147], [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]),\n",
" (17, 1, u\"optimizer='RMSprop(lr=0.003695186053629043)',metrics=['accuracy'],loss='categorical_crossentropy'\", u'epochs=1,batch_size=8', u'madlib_keras', 0.75390625, [211.166339159012, 213.628123044968, 216.070516109467, 218.28012919426, 220.77138209343, 223.166202068329, 225.899930000305, 228.167545080185, 230.690491199493, 233.073115110397], [u'accuracy'], u'categorical_crossentropy', 0.966666638851166, 0.114436306059361, [0.641666650772095, 0.875, 0.824999988079071, 0.824999988079071, 0.958333313465118, 0.866666674613953, 0.966666638851166, 0.941666662693024, 0.958333313465118, 0.966666638851166], [0.718437075614929, 0.535359025001526, 0.403026401996613, 0.348048120737076, 0.244051590561867, 0.264052510261536, 0.1720110476017, 0.164029255509377, 0.154526039958, 0.114436306059361], 0.933333337306976, 0.107093170285225, [0.766666650772095, 0.933333337306976, 0.899999976158142, 0.833333313465118, 0.933333337306976, 0.933333337306976, 0.966666638851166, 0.933333337306976, 0.966666638851166, 0.933333337306976], [0.647899329662323, 0.474290877580643, 0.308415770530701, 0.318869024515152, 0.206334576010704, 0.250639617443085, 0.129751890897751, 0.156522572040558, 0.112601205706596, 0.107093170285225], [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]),\n",
" (11, 1, u\"optimizer='Adam(lr=0.03271173767396424)',metrics=['accuracy'],loss='categorical_crossentropy'\", u'epochs=1,batch_size=4', u'madlib_keras', 0.75390625, [136.810528039932, 139.271977186203, 141.348733186722, 143.678931236267, 146.042705059052, 148.659409046173, 150.713799238205, 153.240673065186, 155.618861198425, 158.003229141235], [u'accuracy'], u'categorical_crossentropy', 0.899999976158142, 0.200596183538437, [0.341666668653488, 0.925000011920929, 0.958333313465118, 0.675000011920929, 0.966666638851166, 0.766666650772095, 0.975000023841858, 0.75, 0.975000023841858, 0.899999976158142], [1.04381895065308, 0.384325951337814, 0.263480663299561, 0.593676149845123, 0.141404688358307, 0.362050473690033, 0.0923048332333565, 0.351189643144608, 0.0946881100535393, 0.200596183538437], 0.899999976158142, 0.257636517286301, [0.533333361148834, 0.866666674613953, 0.966666638851166, 0.800000011920929, 0.966666638851166, 0.833333313465118, 0.966666638851166, 0.866666674613953, 0.966666638851166, 0.899999976158142], [0.91362202167511, 0.340268641710281, 0.21289549767971, 0.362329840660095, 0.136535987257957, 0.327440768480301, 0.111000411212444, 0.227803841233253, 0.111130490899086, 0.257636517286301], [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]),\n",
" (13, 1, u\"optimizer='RMSprop(lr=0.0027814197503322115)',metrics=['accuracy'],loss='categorical_crossentropy'\", u'epochs=1,batch_size=8', u'madlib_keras', 0.75390625, [161.464279174805, 163.823823213577, 166.230634212494, 168.657960176468, 170.846117019653, 173.335704088211, 175.715650081635, 178.106207132339, 180.278338193893, 182.815184116364], [u'accuracy'], u'categorical_crossentropy', 0.933333337306976, 0.351116120815277, [0.600000023841858, 0.558333337306976, 0.541666686534882, 0.600000023841858, 0.899999976158142, 0.916666686534882, 0.850000023841858, 0.925000011920929, 0.933333337306976, 0.933333337306976], [0.9764444231987, 0.860457479953766, 0.76110851764679, 0.688599288463593, 0.623845517635345, 0.558117687702179, 0.516568541526794, 0.438872784376144, 0.389935582876205, 0.351116120815277], 0.899999976158142, 0.326276868581772, [0.433333337306976, 0.433333337306976, 0.5, 0.433333337306976, 0.899999976158142, 0.866666674613953, 0.933333337306976, 0.866666674613953, 0.899999976158142, 0.899999976158142], [1.03803777694702, 0.913994610309601, 0.794906616210938, 0.723303020000458, 0.652373254299164, 0.566653609275818, 0.481746405363083, 0.454111516475677, 0.379933565855026, 0.326276868581772], [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]),\n",
" (2, 2, u\"optimizer='Adam(lr=0.035340389425615855)',metrics=['accuracy'],loss='categorical_crossentropy'\", u'epochs=1,batch_size=8', u'madlib_keras', 1.18359375, [2.53016018867493, 5.03768014907837, 7.64597201347351, 10.4127900600433, 13.0584251880646, 15.7928349971771, 18.0860531330109, 20.625785112381, 23.3826050758362, 25.9297461509705], [u'accuracy'], u'categorical_crossentropy', 0.875, 0.28657540678978, [0.850000023841858, 0.491666674613953, 0.941666662693024, 0.783333361148834, 0.925000011920929, 0.850000023841858, 0.966666638851166, 0.958333313465118, 0.908333361148834, 0.875], [0.313798636198044, 0.746647894382477, 0.232485517859459, 0.384049296379089, 0.201492115855217, 0.276773244142532, 0.144450753927231, 0.116710871458054, 0.210491970181465, 0.28657540678978], 0.899999976158142, 0.334158778190613, [0.833333313465118, 0.533333361148834, 0.833333313465118, 0.899999976158142, 0.899999976158142, 0.833333313465118, 0.966666638851166, 1.0, 0.899999976158142, 0.899999976158142], [0.281513780355453, 0.781840145587921, 0.252955704927444, 0.219736546278, 0.268592208623886, 0.332309901714325, 0.131899908185005, 0.0595534667372704, 0.255705177783966, 0.334158778190613], [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]),\n",
" (8, 1, u\"optimizer='Adam(lr=0.08208550087461897)',metrics=['accuracy'],loss='categorical_crossentropy'\", u'epochs=1,batch_size=8', u'madlib_keras', 0.75390625, [84.8872451782227, 87.2208690643311, 89.7248260974884, 92.1014380455017, 94.1999170780182, 96.5836410522461, 98.9723200798035, 101.409075021744, 103.511981010437, 105.902093172073], [u'accuracy'], u'categorical_crossentropy', 0.766666650772095, 0.59165495634079, [0.333333343267441, 0.641666650772095, 0.566666662693024, 0.591666638851166, 0.758333325386047, 0.666666686534882, 0.966666638851166, 0.916666686534882, 0.949999988079071, 0.766666650772095], [1.02616000175476, 0.486202239990234, 0.636112213134766, 0.692184090614319, 0.505898773670197, 0.467963546514511, 0.268672525882721, 0.176122322678566, 0.122547559440136, 0.59165495634079], 0.899999976158142, 0.33915963768959, [0.333333343267441, 0.766666650772095, 0.733333349227905, 0.766666650772095, 0.733333349227905, 0.666666686534882, 0.966666638851166, 0.899999976158142, 0.899999976158142, 0.899999976158142], [1.12080752849579, 0.381140530109406, 0.5174320936203, 0.473030716180801, 0.607473373413086, 0.409501492977142, 0.212725415825844, 0.296080023050308, 0.18353745341301, 0.33915963768959], [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]),\n",
" (16, 1, u\"optimizer='Adam(lr=0.0025753473010720596)',metrics=['accuracy'],loss='categorical_crossentropy'\", u'epochs=1,batch_size=8', u'madlib_keras', 0.75390625, [186.835414171219, 189.195631027222, 191.254861116409, 193.619318246841, 195.966614246368, 198.311106204987, 200.407158136368, 202.908673048019, 205.313441038132, 207.438939094543], [u'accuracy'], u'categorical_crossentropy', 0.891666650772095, 0.950204193592072, [0.358333319425583, 0.358333319425583, 0.358333319425583, 0.449999988079071, 0.400000005960464, 0.516666650772095, 0.583333313465118, 0.608333349227905, 0.899999976158142, 0.891666650772095], [1.09640550613403, 1.08471190929413, 1.0751405954361, 1.06720495223999, 1.06165635585785, 1.0469172000885, 1.0301650762558, 1.00463593006134, 0.979537725448608, 0.950204193592072], 0.866666674613953, 0.931918859481812, [0.233333334326744, 0.233333334326744, 0.233333334326744, 0.366666674613953, 0.266666680574417, 0.400000005960464, 0.400000005960464, 0.433333337306976, 0.833333313465118, 0.866666674613953], [1.10118973255157, 1.08938491344452, 1.07863283157349, 1.06669425964355, 1.06701147556305, 1.04324889183044, 1.02750730514526, 0.996739327907562, 0.966157376766205, 0.931918859481812], [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]),\n",
" (20, 2, u\"optimizer='RMSprop(lr=0.056702169442788934)',metrics=['accuracy'],loss='categorical_crossentropy'\", u'epochs=1,batch_size=8', u'madlib_keras', 1.18359375, [237.640507221222, 240.350925207138, 243.027331352234, 245.468372344971, 248.176068305969, 250.940598249435, 253.720994234085, 256.680767297745, 259.394066333771, 262.358667373657], [u'accuracy'], u'categorical_crossentropy', 0.649999976158142, 0.545458972454071, [0.658333361148834, 0.649999976158142, 0.641666650772095, 0.641666650772095, 0.641666650772095, 0.666666686534882, 0.666666686534882, 0.666666686534882, 0.666666686534882, 0.649999976158142], [0.616556286811829, 0.493021905422211, 0.488242834806442, 0.486079841852188, 0.479775160551071, 0.482189744710922, 0.496939599514008, 0.479279518127441, 0.543927192687988, 0.545458972454071], 0.800000011920929, 0.362693428993225, [0.633333325386047, 0.800000011920929, 0.766666650772095, 0.766666650772095, 0.766666650772095, 0.666666686534882, 0.666666686534882, 0.666666686534882, 0.666666686534882, 0.800000011920929], [0.53449285030365, 0.394388288259506, 0.390281409025192, 0.385460764169693, 0.392662823200226, 0.410547375679016, 0.439140349626541, 0.395850986242294, 0.503270268440247, 0.362693428993225], [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]),\n",
" (4, 2, u\"optimizer='Adam(lr=0.06312207575548352)',metrics=['accuracy'],loss='categorical_crossentropy'\", u'epochs=1,batch_size=8', u'madlib_keras', 1.18359375, [29.8041570186615, 32.351331949234, 34.8423700332642, 37.4489560127258, 40.3089909553528, 42.915864944458, 45.6521019935608, 47.9889349937439, 50.5978739261627, 53.2138829231262], [u'accuracy'], u'categorical_crossentropy', 0.641666650772095, 0.471347987651825, [0.666666686534882, 0.641666650772095, 0.641666650772095, 0.366666674613953, 0.666666686534882, 0.966666638851166, 0.483333319425583, 0.641666650772095, 0.941666662693024, 0.641666650772095], [0.520724713802338, 0.578253924846649, 0.518827021121979, 1.67398142814636, 0.512235522270203, 0.131752595305443, 1.25291848182678, 0.453146934509277, 0.185879185795784, 0.471347987651825], 0.766666650772095, 0.337222576141357, [0.666666686534882, 0.766666650772095, 0.766666650772095, 0.333333343267441, 0.666666686534882, 0.933333337306976, 0.566666662693024, 0.766666650772095, 0.899999976158142, 0.766666650772095], [0.462848216295242, 0.38900101184845, 0.356701970100403, 1.92939758300781, 0.458910882472992, 0.14183434844017, 0.83171159029007, 0.332331091165543, 0.311882764101028, 0.337222576141357], [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]),\n",
" (18, 1, u\"optimizer='RMSprop(lr=0.0658839037116738)',metrics=['accuracy'],loss='categorical_crossentropy'\", u'epochs=1,batch_size=8', u'madlib_keras', 0.75390625, [211.389490127563, 213.85792016983, 216.39094209671, 218.503707170486, 220.992606163025, 223.471295118332, 226.145341157913, 228.394971132278, 230.912840127945, 233.303599119186], [u'accuracy'], u'categorical_crossentropy', 0.641666650772095, 0.482037603855133, [0.800000011920929, 0.666666686534882, 0.666666686534882, 0.808333337306976, 0.683333337306976, 0.666666686534882, 0.875, 0.666666686534882, 0.666666686534882, 0.641666650772095], [0.508525788784027, 0.431755125522614, 0.435203284025192, 0.344938695430756, 0.478766769170761, 0.330143094062805, 0.273075610399246, 0.479535788297653, 0.48390719294548, 0.482037603855133], 0.766666650772095, 0.392028629779816, [0.833333313465118, 0.666666686534882, 0.666666686534882, 0.899999976158142, 0.666666686534882, 0.666666686534882, 0.933333337306976, 0.666666686534882, 0.666666686534882, 0.766666650772095], [0.443316102027893, 0.401963800191879, 0.399077832698822, 0.240811541676521, 0.410095393657684, 0.290450870990753, 0.254536032676697, 0.396871030330658, 0.413692444562912, 0.392028629779816], [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]),\n",
" (10, 1, u\"optimizer='RMSprop(lr=0.0020197253642543623)',metrics=['accuracy'],loss='categorical_crossentropy'\", u'epochs=1,batch_size=8', u'madlib_keras', 0.75390625, [109.946217060089, 112.64745092392, 115.244435071945, 117.609509944916, 120.211313962936, 122.821636915207, 125.485604047775, 128.088088035583, 130.593991041183, 133.237344026566], [u'accuracy'], u'categorical_crossentropy', 0.725000023841858, 0.55353456735611, [0.358333319425583, 0.358333319425583, 0.508333325386047, 0.916666686534882, 0.658333361148834, 0.633333325386047, 0.633333325386047, 0.641666650772095, 0.649999976158142, 0.725000023841858], [1.44853103160858, 1.05627000331879, 0.960374653339386, 0.903020858764648, 0.811912178993225, 0.744573473930359, 0.693612813949585, 0.683376550674438, 0.593345999717712, 0.55353456735611], 0.766666650772095, 0.458936661481857, [0.233333334326744, 0.233333334326744, 0.433333337306976, 0.933333337306976, 0.733333349227905, 0.733333349227905, 0.733333349227905, 0.766666650772095, 0.766666650772095, 0.766666650772095], [1.5010712146759, 1.05707538127899, 0.939342617988586, 0.863560140132904, 0.760088205337524, 0.681271374225616, 0.617161631584167, 0.568128407001495, 0.501981496810913, 0.458936661481857], [1, 2, 3, 4, 5, 6, 7, 8, 9, 10])]"
]
},
"execution_count": 24,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"%%sql\n",
"SELECT * FROM automl_output_info ORDER BY validation_metrics_final DESC, validation_loss_final;"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Plot results"
]
},
{
"cell_type": "code",
"execution_count": 25,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"20 rows affected.\n",
"1 rows affected.\n"
]
},
{
"data": {
"application/javascript": [
"/* Put everything inside the global mpl namespace */\n",
"window.mpl = {};\n",
"\n",
"\n",
"mpl.get_websocket_type = function() {\n",
" if (typeof(WebSocket) !== 'undefined') {\n",
" return WebSocket;\n",
" } else if (typeof(MozWebSocket) !== 'undefined') {\n",
" return MozWebSocket;\n",
" } else {\n",
" alert('Your browser does not have WebSocket support.' +\n",
" 'Please try Chrome, Safari or Firefox ≥ 6. ' +\n",
" 'Firefox 4 and 5 are also supported but you ' +\n",
" 'have to enable WebSockets in about:config.');\n",
" };\n",
"}\n",
"\n",
"mpl.figure = function(figure_id, websocket, ondownload, parent_element) {\n",
" this.id = figure_id;\n",
"\n",
" this.ws = websocket;\n",
"\n",
" this.supports_binary = (this.ws.binaryType != undefined);\n",
"\n",
" if (!this.supports_binary) {\n",
" var warnings = document.getElementById(\"mpl-warnings\");\n",
" if (warnings) {\n",
" warnings.style.display = 'block';\n",
" warnings.textContent = (\n",
" \"This browser does not support binary websocket messages. \" +\n",
" \"Performance may be slow.\");\n",
" }\n",
" }\n",
"\n",
" this.imageObj = new Image();\n",
"\n",
" this.context = undefined;\n",
" this.message = undefined;\n",
" this.canvas = undefined;\n",
" this.rubberband_canvas = undefined;\n",
" this.rubberband_context = undefined;\n",
" this.format_dropdown = undefined;\n",
"\n",
" this.image_mode = 'full';\n",
"\n",
" this.root = $('<div/>');\n",
" this._root_extra_style(this.root)\n",
" this.root.attr('style', 'display: inline-block');\n",
"\n",
" $(parent_element).append(this.root);\n",
"\n",
" this._init_header(this);\n",
" this._init_canvas(this);\n",
" this._init_toolbar(this);\n",
"\n",
" var fig = this;\n",
"\n",
" this.waiting = false;\n",
"\n",
" this.ws.onopen = function () {\n",
" fig.send_message(\"supports_binary\", {value: fig.supports_binary});\n",
" fig.send_message(\"send_image_mode\", {});\n",
" if (mpl.ratio != 1) {\n",
" fig.send_message(\"set_dpi_ratio\", {'dpi_ratio': mpl.ratio});\n",
" }\n",
" fig.send_message(\"refresh\", {});\n",
" }\n",
"\n",
" this.imageObj.onload = function() {\n",
" if (fig.image_mode == 'full') {\n",
" // Full images could contain transparency (where diff images\n",
" // almost always do), so we need to clear the canvas so that\n",
" // there is no ghosting.\n",
" fig.context.clearRect(0, 0, fig.canvas.width, fig.canvas.height);\n",
" }\n",
" fig.context.drawImage(fig.imageObj, 0, 0);\n",
" };\n",
"\n",
" this.imageObj.onunload = function() {\n",
" fig.ws.close();\n",
" }\n",
"\n",
" this.ws.onmessage = this._make_on_message_function(this);\n",
"\n",
" this.ondownload = ondownload;\n",
"}\n",
"\n",
"mpl.figure.prototype._init_header = function() {\n",
" var titlebar = $(\n",
" '<div class=\"ui-dialog-titlebar ui-widget-header ui-corner-all ' +\n",
" 'ui-helper-clearfix\"/>');\n",
" var titletext = $(\n",
" '<div class=\"ui-dialog-title\" style=\"width: 100%; ' +\n",
" 'text-align: center; padding: 3px;\"/>');\n",
" titlebar.append(titletext)\n",
" this.root.append(titlebar);\n",
" this.header = titletext[0];\n",
"}\n",
"\n",
"\n",
"\n",
"mpl.figure.prototype._canvas_extra_style = function(canvas_div) {\n",
"\n",
"}\n",
"\n",
"\n",
"mpl.figure.prototype._root_extra_style = function(canvas_div) {\n",
"\n",
"}\n",
"\n",
"mpl.figure.prototype._init_canvas = function() {\n",
" var fig = this;\n",
"\n",
" var canvas_div = $('<div/>');\n",
"\n",
" canvas_div.attr('style', 'position: relative; clear: both; outline: 0');\n",
"\n",
" function canvas_keyboard_event(event) {\n",
" return fig.key_event(event, event['data']);\n",
" }\n",
"\n",
" canvas_div.keydown('key_press', canvas_keyboard_event);\n",
" canvas_div.keyup('key_release', canvas_keyboard_event);\n",
" this.canvas_div = canvas_div\n",
" this._canvas_extra_style(canvas_div)\n",
" this.root.append(canvas_div);\n",
"\n",
" var canvas = $('<canvas/>');\n",
" canvas.addClass('mpl-canvas');\n",
" canvas.attr('style', \"left: 0; top: 0; z-index: 0; outline: 0\")\n",
"\n",
" this.canvas = canvas[0];\n",
" this.context = canvas[0].getContext(\"2d\");\n",
"\n",
" var backingStore = this.context.backingStorePixelRatio ||\n",
"\tthis.context.webkitBackingStorePixelRatio ||\n",
"\tthis.context.mozBackingStorePixelRatio ||\n",
"\tthis.context.msBackingStorePixelRatio ||\n",
"\tthis.context.oBackingStorePixelRatio ||\n",
"\tthis.context.backingStorePixelRatio || 1;\n",
"\n",
" mpl.ratio = (window.devicePixelRatio || 1) / backingStore;\n",
"\n",
" var rubberband = $('<canvas/>');\n",
" rubberband.attr('style', \"position: absolute; left: 0; top: 0; z-index: 1;\")\n",
"\n",
" var pass_mouse_events = true;\n",
"\n",
" canvas_div.resizable({\n",
" start: function(event, ui) {\n",
" pass_mouse_events = false;\n",
" },\n",
" resize: function(event, ui) {\n",
" fig.request_resize(ui.size.width, ui.size.height);\n",
" },\n",
" stop: function(event, ui) {\n",
" pass_mouse_events = true;\n",
" fig.request_resize(ui.size.width, ui.size.height);\n",
" },\n",
" });\n",
"\n",
" function mouse_event_fn(event) {\n",
" if (pass_mouse_events)\n",
" return fig.mouse_event(event, event['data']);\n",
" }\n",
"\n",
" rubberband.mousedown('button_press', mouse_event_fn);\n",
" rubberband.mouseup('button_release', mouse_event_fn);\n",
" // Throttle sequential mouse events to 1 every 20ms.\n",
" rubberband.mousemove('motion_notify', mouse_event_fn);\n",
"\n",
" rubberband.mouseenter('figure_enter', mouse_event_fn);\n",
" rubberband.mouseleave('figure_leave', mouse_event_fn);\n",
"\n",
" canvas_div.on(\"wheel\", function (event) {\n",
" event = event.originalEvent;\n",
" event['data'] = 'scroll'\n",
" if (event.deltaY < 0) {\n",
" event.step = 1;\n",
" } else {\n",
" event.step = -1;\n",
" }\n",
" mouse_event_fn(event);\n",
" });\n",
"\n",
" canvas_div.append(canvas);\n",
" canvas_div.append(rubberband);\n",
"\n",
" this.rubberband = rubberband;\n",
" this.rubberband_canvas = rubberband[0];\n",
" this.rubberband_context = rubberband[0].getContext(\"2d\");\n",
" this.rubberband_context.strokeStyle = \"#000000\";\n",
"\n",
" this._resize_canvas = function(width, height) {\n",
" // Keep the size of the canvas, canvas container, and rubber band\n",
" // canvas in synch.\n",
" canvas_div.css('width', width)\n",
" canvas_div.css('height', height)\n",
"\n",
" canvas.attr('width', width * mpl.ratio);\n",
" canvas.attr('height', height * mpl.ratio);\n",
" canvas.attr('style', 'width: ' + width + 'px; height: ' + height + 'px;');\n",
"\n",
" rubberband.attr('width', width);\n",
" rubberband.attr('height', height);\n",
" }\n",
"\n",
" // Set the figure to an initial 600x600px, this will subsequently be updated\n",
" // upon first draw.\n",
" this._resize_canvas(600, 600);\n",
"\n",
" // Disable right mouse context menu.\n",
" $(this.rubberband_canvas).bind(\"contextmenu\",function(e){\n",
" return false;\n",
" });\n",
"\n",
" function set_focus () {\n",
" canvas.focus();\n",
" canvas_div.focus();\n",
" }\n",
"\n",
" window.setTimeout(set_focus, 100);\n",
"}\n",
"\n",
"mpl.figure.prototype._init_toolbar = function() {\n",
" var fig = this;\n",
"\n",
" var nav_element = $('<div/>')\n",
" nav_element.attr('style', 'width: 100%');\n",
" this.root.append(nav_element);\n",
"\n",
" // Define a callback function for later on.\n",
" function toolbar_event(event) {\n",
" return fig.toolbar_button_onclick(event['data']);\n",
" }\n",
" function toolbar_mouse_event(event) {\n",
" return fig.toolbar_button_onmouseover(event['data']);\n",
" }\n",
"\n",
" for(var toolbar_ind in mpl.toolbar_items) {\n",
" var name = mpl.toolbar_items[toolbar_ind][0];\n",
" var tooltip = mpl.toolbar_items[toolbar_ind][1];\n",
" var image = mpl.toolbar_items[toolbar_ind][2];\n",
" var method_name = mpl.toolbar_items[toolbar_ind][3];\n",
"\n",
" if (!name) {\n",
" // put a spacer in here.\n",
" continue;\n",
" }\n",
" var button = $('<button/>');\n",
" button.addClass('ui-button ui-widget ui-state-default ui-corner-all ' +\n",
" 'ui-button-icon-only');\n",
" button.attr('role', 'button');\n",
" button.attr('aria-disabled', 'false');\n",
" button.click(method_name, toolbar_event);\n",
" button.mouseover(tooltip, toolbar_mouse_event);\n",
"\n",
" var icon_img = $('<span/>');\n",
" icon_img.addClass('ui-button-icon-primary ui-icon');\n",
" icon_img.addClass(image);\n",
" icon_img.addClass('ui-corner-all');\n",
"\n",
" var tooltip_span = $('<span/>');\n",
" tooltip_span.addClass('ui-button-text');\n",
" tooltip_span.html(tooltip);\n",
"\n",
" button.append(icon_img);\n",
" button.append(tooltip_span);\n",
"\n",
" nav_element.append(button);\n",
" }\n",
"\n",
" var fmt_picker_span = $('<span/>');\n",
"\n",
" var fmt_picker = $('<select/>');\n",
" fmt_picker.addClass('mpl-toolbar-option ui-widget ui-widget-content');\n",
" fmt_picker_span.append(fmt_picker);\n",
" nav_element.append(fmt_picker_span);\n",
" this.format_dropdown = fmt_picker[0];\n",
"\n",
" for (var ind in mpl.extensions) {\n",
" var fmt = mpl.extensions[ind];\n",
" var option = $(\n",
" '<option/>', {selected: fmt === mpl.default_extension}).html(fmt);\n",
" fmt_picker.append(option)\n",
" }\n",
"\n",
" // Add hover states to the ui-buttons\n",
" $( \".ui-button\" ).hover(\n",
" function() { $(this).addClass(\"ui-state-hover\");},\n",
" function() { $(this).removeClass(\"ui-state-hover\");}\n",
" );\n",
"\n",
" var status_bar = $('<span class=\"mpl-message\"/>');\n",
" nav_element.append(status_bar);\n",
" this.message = status_bar[0];\n",
"}\n",
"\n",
"mpl.figure.prototype.request_resize = function(x_pixels, y_pixels) {\n",
" // Request matplotlib to resize the figure. Matplotlib will then trigger a resize in the client,\n",
" // which will in turn request a refresh of the image.\n",
" this.send_message('resize', {'width': x_pixels, 'height': y_pixels});\n",
"}\n",
"\n",
"mpl.figure.prototype.send_message = function(type, properties) {\n",
" properties['type'] = type;\n",
" properties['figure_id'] = this.id;\n",
" this.ws.send(JSON.stringify(properties));\n",
"}\n",
"\n",
"mpl.figure.prototype.send_draw_message = function() {\n",
" if (!this.waiting) {\n",
" this.waiting = true;\n",
" this.ws.send(JSON.stringify({type: \"draw\", figure_id: this.id}));\n",
" }\n",
"}\n",
"\n",
"\n",
"mpl.figure.prototype.handle_save = function(fig, msg) {\n",
" var format_dropdown = fig.format_dropdown;\n",
" var format = format_dropdown.options[format_dropdown.selectedIndex].value;\n",
" fig.ondownload(fig, format);\n",
"}\n",
"\n",
"\n",
"mpl.figure.prototype.handle_resize = function(fig, msg) {\n",
" var size = msg['size'];\n",
" if (size[0] != fig.canvas.width || size[1] != fig.canvas.height) {\n",
" fig._resize_canvas(size[0], size[1]);\n",
" fig.send_message(\"refresh\", {});\n",
" };\n",
"}\n",
"\n",
"mpl.figure.prototype.handle_rubberband = function(fig, msg) {\n",
" var x0 = msg['x0'] / mpl.ratio;\n",
" var y0 = (fig.canvas.height - msg['y0']) / mpl.ratio;\n",
" var x1 = msg['x1'] / mpl.ratio;\n",
" var y1 = (fig.canvas.height - msg['y1']) / mpl.ratio;\n",
" x0 = Math.floor(x0) + 0.5;\n",
" y0 = Math.floor(y0) + 0.5;\n",
" x1 = Math.floor(x1) + 0.5;\n",
" y1 = Math.floor(y1) + 0.5;\n",
" var min_x = Math.min(x0, x1);\n",
" var min_y = Math.min(y0, y1);\n",
" var width = Math.abs(x1 - x0);\n",
" var height = Math.abs(y1 - y0);\n",
"\n",
" fig.rubberband_context.clearRect(\n",
" 0, 0, fig.canvas.width, fig.canvas.height);\n",
"\n",
" fig.rubberband_context.strokeRect(min_x, min_y, width, height);\n",
"}\n",
"\n",
"mpl.figure.prototype.handle_figure_label = function(fig, msg) {\n",
" // Updates the figure title.\n",
" fig.header.textContent = msg['label'];\n",
"}\n",
"\n",
"mpl.figure.prototype.handle_cursor = function(fig, msg) {\n",
" var cursor = msg['cursor'];\n",
" switch(cursor)\n",
" {\n",
" case 0:\n",
" cursor = 'pointer';\n",
" break;\n",
" case 1:\n",
" cursor = 'default';\n",
" break;\n",
" case 2:\n",
" cursor = 'crosshair';\n",
" break;\n",
" case 3:\n",
" cursor = 'move';\n",
" break;\n",
" }\n",
" fig.rubberband_canvas.style.cursor = cursor;\n",
"}\n",
"\n",
"mpl.figure.prototype.handle_message = function(fig, msg) {\n",
" fig.message.textContent = msg['message'];\n",
"}\n",
"\n",
"mpl.figure.prototype.handle_draw = function(fig, msg) {\n",
" // Request the server to send over a new figure.\n",
" fig.send_draw_message();\n",
"}\n",
"\n",
"mpl.figure.prototype.handle_image_mode = function(fig, msg) {\n",
" fig.image_mode = msg['mode'];\n",
"}\n",
"\n",
"mpl.figure.prototype.updated_canvas_event = function() {\n",
" // Called whenever the canvas gets updated.\n",
" this.send_message(\"ack\", {});\n",
"}\n",
"\n",
"// A function to construct a web socket function for onmessage handling.\n",
"// Called in the figure constructor.\n",
"mpl.figure.prototype._make_on_message_function = function(fig) {\n",
" return function socket_on_message(evt) {\n",
" if (evt.data instanceof Blob) {\n",
" /* FIXME: We get \"Resource interpreted as Image but\n",
" * transferred with MIME type text/plain:\" errors on\n",
" * Chrome. But how to set the MIME type? It doesn't seem\n",
" * to be part of the websocket stream */\n",
" evt.data.type = \"image/png\";\n",
"\n",
" /* Free the memory for the previous frames */\n",
" if (fig.imageObj.src) {\n",
" (window.URL || window.webkitURL).revokeObjectURL(\n",
" fig.imageObj.src);\n",
" }\n",
"\n",
" fig.imageObj.src = (window.URL || window.webkitURL).createObjectURL(\n",
" evt.data);\n",
" fig.updated_canvas_event();\n",
" fig.waiting = false;\n",
" return;\n",
" }\n",
" else if (typeof evt.data === 'string' && evt.data.slice(0, 21) == \"data:image/png;base64\") {\n",
" fig.imageObj.src = evt.data;\n",
" fig.updated_canvas_event();\n",
" fig.waiting = false;\n",
" return;\n",
" }\n",
"\n",
" var msg = JSON.parse(evt.data);\n",
" var msg_type = msg['type'];\n",
"\n",
" // Call the \"handle_{type}\" callback, which takes\n",
" // the figure and JSON message as its only arguments.\n",
" try {\n",
" var callback = fig[\"handle_\" + msg_type];\n",
" } catch (e) {\n",
" console.log(\"No handler for the '\" + msg_type + \"' message type: \", msg);\n",
" return;\n",
" }\n",
"\n",
" if (callback) {\n",
" try {\n",
" // console.log(\"Handling '\" + msg_type + \"' message: \", msg);\n",
" callback(fig, msg);\n",
" } catch (e) {\n",
" console.log(\"Exception inside the 'handler_\" + msg_type + \"' callback:\", e, e.stack, msg);\n",
" }\n",
" }\n",
" };\n",
"}\n",
"\n",
"// from http://stackoverflow.com/questions/1114465/getting-mouse-location-in-canvas\n",
"mpl.findpos = function(e) {\n",
" //this section is from http://www.quirksmode.org/js/events_properties.html\n",
" var targ;\n",
" if (!e)\n",
" e = window.event;\n",
" if (e.target)\n",
" targ = e.target;\n",
" else if (e.srcElement)\n",
" targ = e.srcElement;\n",
" if (targ.nodeType == 3) // defeat Safari bug\n",
" targ = targ.parentNode;\n",
"\n",
" // jQuery normalizes the pageX and pageY\n",
" // pageX,Y are the mouse positions relative to the document\n",
" // offset() returns the position of the element relative to the document\n",
" var x = e.pageX - $(targ).offset().left;\n",
" var y = e.pageY - $(targ).offset().top;\n",
"\n",
" return {\"x\": x, \"y\": y};\n",
"};\n",
"\n",
"/*\n",
" * return a copy of an object with only non-object keys\n",
" * we need this to avoid circular references\n",
" * http://stackoverflow.com/a/24161582/3208463\n",
" */\n",
"function simpleKeys (original) {\n",
" return Object.keys(original).reduce(function (obj, key) {\n",
" if (typeof original[key] !== 'object')\n",
" obj[key] = original[key]\n",
" return obj;\n",
" }, {});\n",
"}\n",
"\n",
"mpl.figure.prototype.mouse_event = function(event, name) {\n",
" var canvas_pos = mpl.findpos(event)\n",
"\n",
" if (name === 'button_press')\n",
" {\n",
" this.canvas.focus();\n",
" this.canvas_div.focus();\n",
" }\n",
"\n",
" var x = canvas_pos.x * mpl.ratio;\n",
" var y = canvas_pos.y * mpl.ratio;\n",
"\n",
" this.send_message(name, {x: x, y: y, button: event.button,\n",
" step: event.step,\n",
" guiEvent: simpleKeys(event)});\n",
"\n",
" /* This prevents the web browser from automatically changing to\n",
" * the text insertion cursor when the button is pressed. We want\n",
" * to control all of the cursor setting manually through the\n",
" * 'cursor' event from matplotlib */\n",
" event.preventDefault();\n",
" return false;\n",
"}\n",
"\n",
"mpl.figure.prototype._key_event_extra = function(event, name) {\n",
" // Handle any extra behaviour associated with a key event\n",
"}\n",
"\n",
"mpl.figure.prototype.key_event = function(event, name) {\n",
"\n",
" // Prevent repeat events\n",
" if (name == 'key_press')\n",
" {\n",
" if (event.which === this._key)\n",
" return;\n",
" else\n",
" this._key = event.which;\n",
" }\n",
" if (name == 'key_release')\n",
" this._key = null;\n",
"\n",
" var value = '';\n",
" if (event.ctrlKey && event.which != 17)\n",
" value += \"ctrl+\";\n",
" if (event.altKey && event.which != 18)\n",
" value += \"alt+\";\n",
" if (event.shiftKey && event.which != 16)\n",
" value += \"shift+\";\n",
"\n",
" value += 'k';\n",
" value += event.which.toString();\n",
"\n",
" this._key_event_extra(event, name);\n",
"\n",
" this.send_message(name, {key: value,\n",
" guiEvent: simpleKeys(event)});\n",
" return false;\n",
"}\n",
"\n",
"mpl.figure.prototype.toolbar_button_onclick = function(name) {\n",
" if (name == 'download') {\n",
" this.handle_save(this, null);\n",
" } else {\n",
" this.send_message(\"toolbar_button\", {name: name});\n",
" }\n",
"};\n",
"\n",
"mpl.figure.prototype.toolbar_button_onmouseover = function(tooltip) {\n",
" this.message.textContent = tooltip;\n",
"};\n",
"mpl.toolbar_items = [[\"Home\", \"Reset original view\", \"fa fa-home icon-home\", \"home\"], [\"Back\", \"Back to previous view\", \"fa fa-arrow-left icon-arrow-left\", \"back\"], [\"Forward\", \"Forward to next view\", \"fa fa-arrow-right icon-arrow-right\", \"forward\"], [\"\", \"\", \"\", \"\"], [\"Pan\", \"Pan axes with left mouse, zoom with right\", \"fa fa-arrows icon-move\", \"pan\"], [\"Zoom\", \"Zoom to rectangle\", \"fa fa-square-o icon-check-empty\", \"zoom\"], [\"\", \"\", \"\", \"\"], [\"Download\", \"Download plot\", \"fa fa-floppy-o icon-save\", \"download\"]];\n",
"\n",
"mpl.extensions = [\"eps\", \"jpeg\", \"pdf\", \"png\", \"ps\", \"raw\", \"svg\", \"tif\"];\n",
"\n",
"mpl.default_extension = \"png\";var comm_websocket_adapter = function(comm) {\n",
" // Create a \"websocket\"-like object which calls the given IPython comm\n",
" // object with the appropriate methods. Currently this is a non binary\n",
" // socket, so there is still some room for performance tuning.\n",
" var ws = {};\n",
"\n",
" ws.close = function() {\n",
" comm.close()\n",
" };\n",
" ws.send = function(m) {\n",
" //console.log('sending', m);\n",
" comm.send(m);\n",
" };\n",
" // Register the callback with on_msg.\n",
" comm.on_msg(function(msg) {\n",
" //console.log('receiving', msg['content']['data'], msg);\n",
" // Pass the mpl event to the overridden (by mpl) onmessage function.\n",
" ws.onmessage(msg['content']['data'])\n",
" });\n",
" return ws;\n",
"}\n",
"\n",
"mpl.mpl_figure_comm = function(comm, msg) {\n",
" // This is the function which gets called when the mpl process\n",
" // starts-up an IPython Comm through the \"matplotlib\" channel.\n",
"\n",
" var id = msg.content.data.id;\n",
" // Get hold of the div created by the display call when the Comm\n",
" // socket was opened in Python.\n",
" var element = $(\"#\" + id);\n",
" var ws_proxy = comm_websocket_adapter(comm)\n",
"\n",
" function ondownload(figure, format) {\n",
" window.open(figure.imageObj.src);\n",
" }\n",
"\n",
" var fig = new mpl.figure(id, ws_proxy,\n",
" ondownload,\n",
" element.get(0));\n",
"\n",
" // Call onopen now - mpl needs it, as it is assuming we've passed it a real\n",
" // web socket which is closed, not our websocket->open comm proxy.\n",
" ws_proxy.onopen();\n",
"\n",
" fig.parent_element = element.get(0);\n",
" fig.cell_info = mpl.find_output_cell(\"<div id='\" + id + \"'></div>\");\n",
" if (!fig.cell_info) {\n",
" console.error(\"Failed to find cell for figure\", id, fig);\n",
" return;\n",
" }\n",
"\n",
" var output_index = fig.cell_info[2]\n",
" var cell = fig.cell_info[0];\n",
"\n",
"};\n",
"\n",
"mpl.figure.prototype.handle_close = function(fig, msg) {\n",
" var width = fig.canvas.width/mpl.ratio\n",
" fig.root.unbind('remove')\n",
"\n",
" // Update the output cell to use the data from the current canvas.\n",
" fig.push_to_output();\n",
" var dataURL = fig.canvas.toDataURL();\n",
" // Re-enable the keyboard manager in IPython - without this line, in FF,\n",
" // the notebook keyboard shortcuts fail.\n",
" IPython.keyboard_manager.enable()\n",
" $(fig.parent_element).html('<img src=\"' + dataURL + '\" width=\"' + width + '\">');\n",
" fig.close_ws(fig, msg);\n",
"}\n",
"\n",
"mpl.figure.prototype.close_ws = function(fig, msg){\n",
" fig.send_message('closing', msg);\n",
" // fig.ws.close()\n",
"}\n",
"\n",
"mpl.figure.prototype.push_to_output = function(remove_interactive) {\n",
" // Turn the data on the canvas into data in the output cell.\n",
" var width = this.canvas.width/mpl.ratio\n",
" var dataURL = this.canvas.toDataURL();\n",
" this.cell_info[1]['text/html'] = '<img src=\"' + dataURL + '\" width=\"' + width + '\">';\n",
"}\n",
"\n",
"mpl.figure.prototype.updated_canvas_event = function() {\n",
" // Tell IPython that the notebook contents must change.\n",
" IPython.notebook.set_dirty(true);\n",
" this.send_message(\"ack\", {});\n",
" var fig = this;\n",
" // Wait a second, then push the new image to the DOM so\n",
" // that it is saved nicely (might be nice to debounce this).\n",
" setTimeout(function () { fig.push_to_output() }, 1000);\n",
"}\n",
"\n",
"mpl.figure.prototype._init_toolbar = function() {\n",
" var fig = this;\n",
"\n",
" var nav_element = $('<div/>')\n",
" nav_element.attr('style', 'width: 100%');\n",
" this.root.append(nav_element);\n",
"\n",
" // Define a callback function for later on.\n",
" function toolbar_event(event) {\n",
" return fig.toolbar_button_onclick(event['data']);\n",
" }\n",
" function toolbar_mouse_event(event) {\n",
" return fig.toolbar_button_onmouseover(event['data']);\n",
" }\n",
"\n",
" for(var toolbar_ind in mpl.toolbar_items){\n",
" var name = mpl.toolbar_items[toolbar_ind][0];\n",
" var tooltip = mpl.toolbar_items[toolbar_ind][1];\n",
" var image = mpl.toolbar_items[toolbar_ind][2];\n",
" var method_name = mpl.toolbar_items[toolbar_ind][3];\n",
"\n",
" if (!name) { continue; };\n",
"\n",
" var button = $('<button class=\"btn btn-default\" href=\"#\" title=\"' + name + '\"><i class=\"fa ' + image + ' fa-lg\"></i></button>');\n",
" button.click(method_name, toolbar_event);\n",
" button.mouseover(tooltip, toolbar_mouse_event);\n",
" nav_element.append(button);\n",
" }\n",
"\n",
" // Add the status bar.\n",
" var status_bar = $('<span class=\"mpl-message\" style=\"text-align:right; float: right;\"/>');\n",
" nav_element.append(status_bar);\n",
" this.message = status_bar[0];\n",
"\n",
" // Add the close button to the window.\n",
" var buttongrp = $('<div class=\"btn-group inline pull-right\"></div>');\n",
" var button = $('<button class=\"btn btn-mini btn-primary\" href=\"#\" title=\"Stop Interaction\"><i class=\"fa fa-power-off icon-remove icon-large\"></i></button>');\n",
" button.click(function (evt) { fig.handle_close(fig, {}); } );\n",
" button.mouseover('Stop Interaction', toolbar_mouse_event);\n",
" buttongrp.append(button);\n",
" var titlebar = this.root.find($('.ui-dialog-titlebar'));\n",
" titlebar.prepend(buttongrp);\n",
"}\n",
"\n",
"mpl.figure.prototype._root_extra_style = function(el){\n",
" var fig = this\n",
" el.on(\"remove\", function(){\n",
"\tfig.close_ws(fig, {});\n",
" });\n",
"}\n",
"\n",
"mpl.figure.prototype._canvas_extra_style = function(el){\n",
" // this is important to make the div 'focusable\n",
" el.attr('tabindex', 0)\n",
" // reach out to IPython and tell the keyboard manager to turn it's self\n",
" // off when our div gets focus\n",
"\n",
" // location in version 3\n",
" if (IPython.notebook.keyboard_manager) {\n",
" IPython.notebook.keyboard_manager.register_events(el);\n",
" }\n",
" else {\n",
" // location in version 2\n",
" IPython.keyboard_manager.register_events(el);\n",
" }\n",
"\n",
"}\n",
"\n",
"mpl.figure.prototype._key_event_extra = function(event, name) {\n",
" var manager = IPython.notebook.keyboard_manager;\n",
" if (!manager)\n",
" manager = IPython.keyboard_manager;\n",
"\n",
" // Check for shift+enter\n",
" if (event.shiftKey && event.which == 13) {\n",
" this.canvas_div.blur();\n",
" // select the cell after this one\n",
" var index = IPython.notebook.find_cell_index(this.cell_info[0]);\n",
" IPython.notebook.select(index + 1);\n",
" }\n",
"}\n",
"\n",
"mpl.figure.prototype.handle_save = function(fig, msg) {\n",
" fig.ondownload(fig, null);\n",
"}\n",
"\n",
"\n",
"mpl.find_output_cell = function(html_output) {\n",
" // Return the cell and output element which can be found *uniquely* in the notebook.\n",
" // Note - this is a bit hacky, but it is done because the \"notebook_saving.Notebook\"\n",
" // IPython event is triggered only after the cells have been serialised, which for\n",
" // our purposes (turning an active figure into a static one), is too late.\n",
" var cells = IPython.notebook.get_cells();\n",
" var ncells = cells.length;\n",
" for (var i=0; i<ncells; i++) {\n",
" var cell = cells[i];\n",
" if (cell.cell_type === 'code'){\n",
" for (var j=0; j<cell.output_area.outputs.length; j++) {\n",
" var data = cell.output_area.outputs[j];\n",
" if (data.data) {\n",
" // IPython >= 3 moved mimebundle to data attribute of output\n",
" data = data.data;\n",
" }\n",
" if (data['text/html'] == html_output) {\n",
" return [cell, data, j];\n",
" }\n",
" }\n",
" }\n",
" }\n",
"}\n",
"\n",
"// Register the function which deals with the matplotlib target/channel.\n",
"// The kernel may be null if the page has been refreshed.\n",
"if (IPython.notebook.kernel != null) {\n",
" IPython.notebook.kernel.comm_manager.register_target('matplotlib', mpl.mpl_figure_comm);\n",
"}\n"
],
"text/plain": [
"<IPython.core.display.Javascript object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<img src=\"data:image/png;base64,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\" width=\"720\">"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"1 rows affected.\n",
"1 rows affected.\n",
"1 rows affected.\n",
"1 rows affected.\n",
"1 rows affected.\n",
"1 rows affected.\n",
"1 rows affected.\n",
"1 rows affected.\n",
"1 rows affected.\n",
"1 rows affected.\n",
"1 rows affected.\n",
"1 rows affected.\n",
"1 rows affected.\n",
"1 rows affected.\n",
"1 rows affected.\n",
"1 rows affected.\n",
"1 rows affected.\n",
"1 rows affected.\n",
"1 rows affected.\n",
"1 rows affected.\n"
]
}
],
"source": [
"df_results = %sql SELECT * FROM automl_output_info;\n",
"df_results = df_results.DataFrame()\n",
"\n",
"df_summary = %sql SELECT * FROM automl_output_summary;\n",
"df_summary = df_summary.DataFrame()\n",
"\n",
"#set up plots\n",
"fig, axs = plt.subplots(nrows=1, ncols=2, figsize=(10,5))\n",
"fig.legend(ncol=4)\n",
"fig.tight_layout()\n",
"\n",
"ax_metric = axs[0]\n",
"ax_loss = axs[1]\n",
"\n",
"ax_metric.xaxis.set_major_locator(MaxNLocator(integer=True))\n",
"ax_metric.set_xlabel('Iteration')\n",
"ax_metric.set_ylabel('Metric')\n",
"ax_metric.set_title('Validation metric curve')\n",
"\n",
"ax_loss.xaxis.set_major_locator(MaxNLocator(integer=True))\n",
"ax_loss.set_xlabel('Iteration')\n",
"ax_loss.set_ylabel('Loss')\n",
"ax_loss.set_title('Validation loss curve')\n",
"\n",
"for mst_key in df_results['mst_key']:\n",
" df_output_info = %sql SELECT validation_metrics,validation_loss,metrics_iters FROM automl_output_info WHERE mst_key = $mst_key;\n",
" df_output_info = df_output_info.DataFrame()\n",
" validation_metrics = df_output_info['validation_metrics'][0]\n",
" validation_loss = df_output_info['validation_loss'][0]\n",
" iters = df_output_info['metrics_iters'][0]\n",
" \n",
" #ax_metric.plot(iters, validation_metrics, label=mst_key, marker='o')\n",
" ax_metric.plot(iters, validation_metrics)\n",
" #ax_loss.plot(iters, validation_loss, label=mst_key, marker='o')\n",
" ax_loss.plot(iters, validation_loss)\n",
"\n",
"plt.legend();\n",
"# fig.savefig('./lc_keras_fit.png', dpi = 300)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Show each trial"
]
},
{
"cell_type": "code",
"execution_count": 26,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"20 rows affected.\n"
]
},
{
"data": {
"application/javascript": [
"/* Put everything inside the global mpl namespace */\n",
"window.mpl = {};\n",
"\n",
"\n",
"mpl.get_websocket_type = function() {\n",
" if (typeof(WebSocket) !== 'undefined') {\n",
" return WebSocket;\n",
" } else if (typeof(MozWebSocket) !== 'undefined') {\n",
" return MozWebSocket;\n",
" } else {\n",
" alert('Your browser does not have WebSocket support.' +\n",
" 'Please try Chrome, Safari or Firefox ≥ 6. ' +\n",
" 'Firefox 4 and 5 are also supported but you ' +\n",
" 'have to enable WebSockets in about:config.');\n",
" };\n",
"}\n",
"\n",
"mpl.figure = function(figure_id, websocket, ondownload, parent_element) {\n",
" this.id = figure_id;\n",
"\n",
" this.ws = websocket;\n",
"\n",
" this.supports_binary = (this.ws.binaryType != undefined);\n",
"\n",
" if (!this.supports_binary) {\n",
" var warnings = document.getElementById(\"mpl-warnings\");\n",
" if (warnings) {\n",
" warnings.style.display = 'block';\n",
" warnings.textContent = (\n",
" \"This browser does not support binary websocket messages. \" +\n",
" \"Performance may be slow.\");\n",
" }\n",
" }\n",
"\n",
" this.imageObj = new Image();\n",
"\n",
" this.context = undefined;\n",
" this.message = undefined;\n",
" this.canvas = undefined;\n",
" this.rubberband_canvas = undefined;\n",
" this.rubberband_context = undefined;\n",
" this.format_dropdown = undefined;\n",
"\n",
" this.image_mode = 'full';\n",
"\n",
" this.root = $('<div/>');\n",
" this._root_extra_style(this.root)\n",
" this.root.attr('style', 'display: inline-block');\n",
"\n",
" $(parent_element).append(this.root);\n",
"\n",
" this._init_header(this);\n",
" this._init_canvas(this);\n",
" this._init_toolbar(this);\n",
"\n",
" var fig = this;\n",
"\n",
" this.waiting = false;\n",
"\n",
" this.ws.onopen = function () {\n",
" fig.send_message(\"supports_binary\", {value: fig.supports_binary});\n",
" fig.send_message(\"send_image_mode\", {});\n",
" if (mpl.ratio != 1) {\n",
" fig.send_message(\"set_dpi_ratio\", {'dpi_ratio': mpl.ratio});\n",
" }\n",
" fig.send_message(\"refresh\", {});\n",
" }\n",
"\n",
" this.imageObj.onload = function() {\n",
" if (fig.image_mode == 'full') {\n",
" // Full images could contain transparency (where diff images\n",
" // almost always do), so we need to clear the canvas so that\n",
" // there is no ghosting.\n",
" fig.context.clearRect(0, 0, fig.canvas.width, fig.canvas.height);\n",
" }\n",
" fig.context.drawImage(fig.imageObj, 0, 0);\n",
" };\n",
"\n",
" this.imageObj.onunload = function() {\n",
" fig.ws.close();\n",
" }\n",
"\n",
" this.ws.onmessage = this._make_on_message_function(this);\n",
"\n",
" this.ondownload = ondownload;\n",
"}\n",
"\n",
"mpl.figure.prototype._init_header = function() {\n",
" var titlebar = $(\n",
" '<div class=\"ui-dialog-titlebar ui-widget-header ui-corner-all ' +\n",
" 'ui-helper-clearfix\"/>');\n",
" var titletext = $(\n",
" '<div class=\"ui-dialog-title\" style=\"width: 100%; ' +\n",
" 'text-align: center; padding: 3px;\"/>');\n",
" titlebar.append(titletext)\n",
" this.root.append(titlebar);\n",
" this.header = titletext[0];\n",
"}\n",
"\n",
"\n",
"\n",
"mpl.figure.prototype._canvas_extra_style = function(canvas_div) {\n",
"\n",
"}\n",
"\n",
"\n",
"mpl.figure.prototype._root_extra_style = function(canvas_div) {\n",
"\n",
"}\n",
"\n",
"mpl.figure.prototype._init_canvas = function() {\n",
" var fig = this;\n",
"\n",
" var canvas_div = $('<div/>');\n",
"\n",
" canvas_div.attr('style', 'position: relative; clear: both; outline: 0');\n",
"\n",
" function canvas_keyboard_event(event) {\n",
" return fig.key_event(event, event['data']);\n",
" }\n",
"\n",
" canvas_div.keydown('key_press', canvas_keyboard_event);\n",
" canvas_div.keyup('key_release', canvas_keyboard_event);\n",
" this.canvas_div = canvas_div\n",
" this._canvas_extra_style(canvas_div)\n",
" this.root.append(canvas_div);\n",
"\n",
" var canvas = $('<canvas/>');\n",
" canvas.addClass('mpl-canvas');\n",
" canvas.attr('style', \"left: 0; top: 0; z-index: 0; outline: 0\")\n",
"\n",
" this.canvas = canvas[0];\n",
" this.context = canvas[0].getContext(\"2d\");\n",
"\n",
" var backingStore = this.context.backingStorePixelRatio ||\n",
"\tthis.context.webkitBackingStorePixelRatio ||\n",
"\tthis.context.mozBackingStorePixelRatio ||\n",
"\tthis.context.msBackingStorePixelRatio ||\n",
"\tthis.context.oBackingStorePixelRatio ||\n",
"\tthis.context.backingStorePixelRatio || 1;\n",
"\n",
" mpl.ratio = (window.devicePixelRatio || 1) / backingStore;\n",
"\n",
" var rubberband = $('<canvas/>');\n",
" rubberband.attr('style', \"position: absolute; left: 0; top: 0; z-index: 1;\")\n",
"\n",
" var pass_mouse_events = true;\n",
"\n",
" canvas_div.resizable({\n",
" start: function(event, ui) {\n",
" pass_mouse_events = false;\n",
" },\n",
" resize: function(event, ui) {\n",
" fig.request_resize(ui.size.width, ui.size.height);\n",
" },\n",
" stop: function(event, ui) {\n",
" pass_mouse_events = true;\n",
" fig.request_resize(ui.size.width, ui.size.height);\n",
" },\n",
" });\n",
"\n",
" function mouse_event_fn(event) {\n",
" if (pass_mouse_events)\n",
" return fig.mouse_event(event, event['data']);\n",
" }\n",
"\n",
" rubberband.mousedown('button_press', mouse_event_fn);\n",
" rubberband.mouseup('button_release', mouse_event_fn);\n",
" // Throttle sequential mouse events to 1 every 20ms.\n",
" rubberband.mousemove('motion_notify', mouse_event_fn);\n",
"\n",
" rubberband.mouseenter('figure_enter', mouse_event_fn);\n",
" rubberband.mouseleave('figure_leave', mouse_event_fn);\n",
"\n",
" canvas_div.on(\"wheel\", function (event) {\n",
" event = event.originalEvent;\n",
" event['data'] = 'scroll'\n",
" if (event.deltaY < 0) {\n",
" event.step = 1;\n",
" } else {\n",
" event.step = -1;\n",
" }\n",
" mouse_event_fn(event);\n",
" });\n",
"\n",
" canvas_div.append(canvas);\n",
" canvas_div.append(rubberband);\n",
"\n",
" this.rubberband = rubberband;\n",
" this.rubberband_canvas = rubberband[0];\n",
" this.rubberband_context = rubberband[0].getContext(\"2d\");\n",
" this.rubberband_context.strokeStyle = \"#000000\";\n",
"\n",
" this._resize_canvas = function(width, height) {\n",
" // Keep the size of the canvas, canvas container, and rubber band\n",
" // canvas in synch.\n",
" canvas_div.css('width', width)\n",
" canvas_div.css('height', height)\n",
"\n",
" canvas.attr('width', width * mpl.ratio);\n",
" canvas.attr('height', height * mpl.ratio);\n",
" canvas.attr('style', 'width: ' + width + 'px; height: ' + height + 'px;');\n",
"\n",
" rubberband.attr('width', width);\n",
" rubberband.attr('height', height);\n",
" }\n",
"\n",
" // Set the figure to an initial 600x600px, this will subsequently be updated\n",
" // upon first draw.\n",
" this._resize_canvas(600, 600);\n",
"\n",
" // Disable right mouse context menu.\n",
" $(this.rubberband_canvas).bind(\"contextmenu\",function(e){\n",
" return false;\n",
" });\n",
"\n",
" function set_focus () {\n",
" canvas.focus();\n",
" canvas_div.focus();\n",
" }\n",
"\n",
" window.setTimeout(set_focus, 100);\n",
"}\n",
"\n",
"mpl.figure.prototype._init_toolbar = function() {\n",
" var fig = this;\n",
"\n",
" var nav_element = $('<div/>')\n",
" nav_element.attr('style', 'width: 100%');\n",
" this.root.append(nav_element);\n",
"\n",
" // Define a callback function for later on.\n",
" function toolbar_event(event) {\n",
" return fig.toolbar_button_onclick(event['data']);\n",
" }\n",
" function toolbar_mouse_event(event) {\n",
" return fig.toolbar_button_onmouseover(event['data']);\n",
" }\n",
"\n",
" for(var toolbar_ind in mpl.toolbar_items) {\n",
" var name = mpl.toolbar_items[toolbar_ind][0];\n",
" var tooltip = mpl.toolbar_items[toolbar_ind][1];\n",
" var image = mpl.toolbar_items[toolbar_ind][2];\n",
" var method_name = mpl.toolbar_items[toolbar_ind][3];\n",
"\n",
" if (!name) {\n",
" // put a spacer in here.\n",
" continue;\n",
" }\n",
" var button = $('<button/>');\n",
" button.addClass('ui-button ui-widget ui-state-default ui-corner-all ' +\n",
" 'ui-button-icon-only');\n",
" button.attr('role', 'button');\n",
" button.attr('aria-disabled', 'false');\n",
" button.click(method_name, toolbar_event);\n",
" button.mouseover(tooltip, toolbar_mouse_event);\n",
"\n",
" var icon_img = $('<span/>');\n",
" icon_img.addClass('ui-button-icon-primary ui-icon');\n",
" icon_img.addClass(image);\n",
" icon_img.addClass('ui-corner-all');\n",
"\n",
" var tooltip_span = $('<span/>');\n",
" tooltip_span.addClass('ui-button-text');\n",
" tooltip_span.html(tooltip);\n",
"\n",
" button.append(icon_img);\n",
" button.append(tooltip_span);\n",
"\n",
" nav_element.append(button);\n",
" }\n",
"\n",
" var fmt_picker_span = $('<span/>');\n",
"\n",
" var fmt_picker = $('<select/>');\n",
" fmt_picker.addClass('mpl-toolbar-option ui-widget ui-widget-content');\n",
" fmt_picker_span.append(fmt_picker);\n",
" nav_element.append(fmt_picker_span);\n",
" this.format_dropdown = fmt_picker[0];\n",
"\n",
" for (var ind in mpl.extensions) {\n",
" var fmt = mpl.extensions[ind];\n",
" var option = $(\n",
" '<option/>', {selected: fmt === mpl.default_extension}).html(fmt);\n",
" fmt_picker.append(option)\n",
" }\n",
"\n",
" // Add hover states to the ui-buttons\n",
" $( \".ui-button\" ).hover(\n",
" function() { $(this).addClass(\"ui-state-hover\");},\n",
" function() { $(this).removeClass(\"ui-state-hover\");}\n",
" );\n",
"\n",
" var status_bar = $('<span class=\"mpl-message\"/>');\n",
" nav_element.append(status_bar);\n",
" this.message = status_bar[0];\n",
"}\n",
"\n",
"mpl.figure.prototype.request_resize = function(x_pixels, y_pixels) {\n",
" // Request matplotlib to resize the figure. Matplotlib will then trigger a resize in the client,\n",
" // which will in turn request a refresh of the image.\n",
" this.send_message('resize', {'width': x_pixels, 'height': y_pixels});\n",
"}\n",
"\n",
"mpl.figure.prototype.send_message = function(type, properties) {\n",
" properties['type'] = type;\n",
" properties['figure_id'] = this.id;\n",
" this.ws.send(JSON.stringify(properties));\n",
"}\n",
"\n",
"mpl.figure.prototype.send_draw_message = function() {\n",
" if (!this.waiting) {\n",
" this.waiting = true;\n",
" this.ws.send(JSON.stringify({type: \"draw\", figure_id: this.id}));\n",
" }\n",
"}\n",
"\n",
"\n",
"mpl.figure.prototype.handle_save = function(fig, msg) {\n",
" var format_dropdown = fig.format_dropdown;\n",
" var format = format_dropdown.options[format_dropdown.selectedIndex].value;\n",
" fig.ondownload(fig, format);\n",
"}\n",
"\n",
"\n",
"mpl.figure.prototype.handle_resize = function(fig, msg) {\n",
" var size = msg['size'];\n",
" if (size[0] != fig.canvas.width || size[1] != fig.canvas.height) {\n",
" fig._resize_canvas(size[0], size[1]);\n",
" fig.send_message(\"refresh\", {});\n",
" };\n",
"}\n",
"\n",
"mpl.figure.prototype.handle_rubberband = function(fig, msg) {\n",
" var x0 = msg['x0'] / mpl.ratio;\n",
" var y0 = (fig.canvas.height - msg['y0']) / mpl.ratio;\n",
" var x1 = msg['x1'] / mpl.ratio;\n",
" var y1 = (fig.canvas.height - msg['y1']) / mpl.ratio;\n",
" x0 = Math.floor(x0) + 0.5;\n",
" y0 = Math.floor(y0) + 0.5;\n",
" x1 = Math.floor(x1) + 0.5;\n",
" y1 = Math.floor(y1) + 0.5;\n",
" var min_x = Math.min(x0, x1);\n",
" var min_y = Math.min(y0, y1);\n",
" var width = Math.abs(x1 - x0);\n",
" var height = Math.abs(y1 - y0);\n",
"\n",
" fig.rubberband_context.clearRect(\n",
" 0, 0, fig.canvas.width, fig.canvas.height);\n",
"\n",
" fig.rubberband_context.strokeRect(min_x, min_y, width, height);\n",
"}\n",
"\n",
"mpl.figure.prototype.handle_figure_label = function(fig, msg) {\n",
" // Updates the figure title.\n",
" fig.header.textContent = msg['label'];\n",
"}\n",
"\n",
"mpl.figure.prototype.handle_cursor = function(fig, msg) {\n",
" var cursor = msg['cursor'];\n",
" switch(cursor)\n",
" {\n",
" case 0:\n",
" cursor = 'pointer';\n",
" break;\n",
" case 1:\n",
" cursor = 'default';\n",
" break;\n",
" case 2:\n",
" cursor = 'crosshair';\n",
" break;\n",
" case 3:\n",
" cursor = 'move';\n",
" break;\n",
" }\n",
" fig.rubberband_canvas.style.cursor = cursor;\n",
"}\n",
"\n",
"mpl.figure.prototype.handle_message = function(fig, msg) {\n",
" fig.message.textContent = msg['message'];\n",
"}\n",
"\n",
"mpl.figure.prototype.handle_draw = function(fig, msg) {\n",
" // Request the server to send over a new figure.\n",
" fig.send_draw_message();\n",
"}\n",
"\n",
"mpl.figure.prototype.handle_image_mode = function(fig, msg) {\n",
" fig.image_mode = msg['mode'];\n",
"}\n",
"\n",
"mpl.figure.prototype.updated_canvas_event = function() {\n",
" // Called whenever the canvas gets updated.\n",
" this.send_message(\"ack\", {});\n",
"}\n",
"\n",
"// A function to construct a web socket function for onmessage handling.\n",
"// Called in the figure constructor.\n",
"mpl.figure.prototype._make_on_message_function = function(fig) {\n",
" return function socket_on_message(evt) {\n",
" if (evt.data instanceof Blob) {\n",
" /* FIXME: We get \"Resource interpreted as Image but\n",
" * transferred with MIME type text/plain:\" errors on\n",
" * Chrome. But how to set the MIME type? It doesn't seem\n",
" * to be part of the websocket stream */\n",
" evt.data.type = \"image/png\";\n",
"\n",
" /* Free the memory for the previous frames */\n",
" if (fig.imageObj.src) {\n",
" (window.URL || window.webkitURL).revokeObjectURL(\n",
" fig.imageObj.src);\n",
" }\n",
"\n",
" fig.imageObj.src = (window.URL || window.webkitURL).createObjectURL(\n",
" evt.data);\n",
" fig.updated_canvas_event();\n",
" fig.waiting = false;\n",
" return;\n",
" }\n",
" else if (typeof evt.data === 'string' && evt.data.slice(0, 21) == \"data:image/png;base64\") {\n",
" fig.imageObj.src = evt.data;\n",
" fig.updated_canvas_event();\n",
" fig.waiting = false;\n",
" return;\n",
" }\n",
"\n",
" var msg = JSON.parse(evt.data);\n",
" var msg_type = msg['type'];\n",
"\n",
" // Call the \"handle_{type}\" callback, which takes\n",
" // the figure and JSON message as its only arguments.\n",
" try {\n",
" var callback = fig[\"handle_\" + msg_type];\n",
" } catch (e) {\n",
" console.log(\"No handler for the '\" + msg_type + \"' message type: \", msg);\n",
" return;\n",
" }\n",
"\n",
" if (callback) {\n",
" try {\n",
" // console.log(\"Handling '\" + msg_type + \"' message: \", msg);\n",
" callback(fig, msg);\n",
" } catch (e) {\n",
" console.log(\"Exception inside the 'handler_\" + msg_type + \"' callback:\", e, e.stack, msg);\n",
" }\n",
" }\n",
" };\n",
"}\n",
"\n",
"// from http://stackoverflow.com/questions/1114465/getting-mouse-location-in-canvas\n",
"mpl.findpos = function(e) {\n",
" //this section is from http://www.quirksmode.org/js/events_properties.html\n",
" var targ;\n",
" if (!e)\n",
" e = window.event;\n",
" if (e.target)\n",
" targ = e.target;\n",
" else if (e.srcElement)\n",
" targ = e.srcElement;\n",
" if (targ.nodeType == 3) // defeat Safari bug\n",
" targ = targ.parentNode;\n",
"\n",
" // jQuery normalizes the pageX and pageY\n",
" // pageX,Y are the mouse positions relative to the document\n",
" // offset() returns the position of the element relative to the document\n",
" var x = e.pageX - $(targ).offset().left;\n",
" var y = e.pageY - $(targ).offset().top;\n",
"\n",
" return {\"x\": x, \"y\": y};\n",
"};\n",
"\n",
"/*\n",
" * return a copy of an object with only non-object keys\n",
" * we need this to avoid circular references\n",
" * http://stackoverflow.com/a/24161582/3208463\n",
" */\n",
"function simpleKeys (original) {\n",
" return Object.keys(original).reduce(function (obj, key) {\n",
" if (typeof original[key] !== 'object')\n",
" obj[key] = original[key]\n",
" return obj;\n",
" }, {});\n",
"}\n",
"\n",
"mpl.figure.prototype.mouse_event = function(event, name) {\n",
" var canvas_pos = mpl.findpos(event)\n",
"\n",
" if (name === 'button_press')\n",
" {\n",
" this.canvas.focus();\n",
" this.canvas_div.focus();\n",
" }\n",
"\n",
" var x = canvas_pos.x * mpl.ratio;\n",
" var y = canvas_pos.y * mpl.ratio;\n",
"\n",
" this.send_message(name, {x: x, y: y, button: event.button,\n",
" step: event.step,\n",
" guiEvent: simpleKeys(event)});\n",
"\n",
" /* This prevents the web browser from automatically changing to\n",
" * the text insertion cursor when the button is pressed. We want\n",
" * to control all of the cursor setting manually through the\n",
" * 'cursor' event from matplotlib */\n",
" event.preventDefault();\n",
" return false;\n",
"}\n",
"\n",
"mpl.figure.prototype._key_event_extra = function(event, name) {\n",
" // Handle any extra behaviour associated with a key event\n",
"}\n",
"\n",
"mpl.figure.prototype.key_event = function(event, name) {\n",
"\n",
" // Prevent repeat events\n",
" if (name == 'key_press')\n",
" {\n",
" if (event.which === this._key)\n",
" return;\n",
" else\n",
" this._key = event.which;\n",
" }\n",
" if (name == 'key_release')\n",
" this._key = null;\n",
"\n",
" var value = '';\n",
" if (event.ctrlKey && event.which != 17)\n",
" value += \"ctrl+\";\n",
" if (event.altKey && event.which != 18)\n",
" value += \"alt+\";\n",
" if (event.shiftKey && event.which != 16)\n",
" value += \"shift+\";\n",
"\n",
" value += 'k';\n",
" value += event.which.toString();\n",
"\n",
" this._key_event_extra(event, name);\n",
"\n",
" this.send_message(name, {key: value,\n",
" guiEvent: simpleKeys(event)});\n",
" return false;\n",
"}\n",
"\n",
"mpl.figure.prototype.toolbar_button_onclick = function(name) {\n",
" if (name == 'download') {\n",
" this.handle_save(this, null);\n",
" } else {\n",
" this.send_message(\"toolbar_button\", {name: name});\n",
" }\n",
"};\n",
"\n",
"mpl.figure.prototype.toolbar_button_onmouseover = function(tooltip) {\n",
" this.message.textContent = tooltip;\n",
"};\n",
"mpl.toolbar_items = [[\"Home\", \"Reset original view\", \"fa fa-home icon-home\", \"home\"], [\"Back\", \"Back to previous view\", \"fa fa-arrow-left icon-arrow-left\", \"back\"], [\"Forward\", \"Forward to next view\", \"fa fa-arrow-right icon-arrow-right\", \"forward\"], [\"\", \"\", \"\", \"\"], [\"Pan\", \"Pan axes with left mouse, zoom with right\", \"fa fa-arrows icon-move\", \"pan\"], [\"Zoom\", \"Zoom to rectangle\", \"fa fa-square-o icon-check-empty\", \"zoom\"], [\"\", \"\", \"\", \"\"], [\"Download\", \"Download plot\", \"fa fa-floppy-o icon-save\", \"download\"]];\n",
"\n",
"mpl.extensions = [\"eps\", \"jpeg\", \"pdf\", \"png\", \"ps\", \"raw\", \"svg\", \"tif\"];\n",
"\n",
"mpl.default_extension = \"png\";var comm_websocket_adapter = function(comm) {\n",
" // Create a \"websocket\"-like object which calls the given IPython comm\n",
" // object with the appropriate methods. Currently this is a non binary\n",
" // socket, so there is still some room for performance tuning.\n",
" var ws = {};\n",
"\n",
" ws.close = function() {\n",
" comm.close()\n",
" };\n",
" ws.send = function(m) {\n",
" //console.log('sending', m);\n",
" comm.send(m);\n",
" };\n",
" // Register the callback with on_msg.\n",
" comm.on_msg(function(msg) {\n",
" //console.log('receiving', msg['content']['data'], msg);\n",
" // Pass the mpl event to the overridden (by mpl) onmessage function.\n",
" ws.onmessage(msg['content']['data'])\n",
" });\n",
" return ws;\n",
"}\n",
"\n",
"mpl.mpl_figure_comm = function(comm, msg) {\n",
" // This is the function which gets called when the mpl process\n",
" // starts-up an IPython Comm through the \"matplotlib\" channel.\n",
"\n",
" var id = msg.content.data.id;\n",
" // Get hold of the div created by the display call when the Comm\n",
" // socket was opened in Python.\n",
" var element = $(\"#\" + id);\n",
" var ws_proxy = comm_websocket_adapter(comm)\n",
"\n",
" function ondownload(figure, format) {\n",
" window.open(figure.imageObj.src);\n",
" }\n",
"\n",
" var fig = new mpl.figure(id, ws_proxy,\n",
" ondownload,\n",
" element.get(0));\n",
"\n",
" // Call onopen now - mpl needs it, as it is assuming we've passed it a real\n",
" // web socket which is closed, not our websocket->open comm proxy.\n",
" ws_proxy.onopen();\n",
"\n",
" fig.parent_element = element.get(0);\n",
" fig.cell_info = mpl.find_output_cell(\"<div id='\" + id + \"'></div>\");\n",
" if (!fig.cell_info) {\n",
" console.error(\"Failed to find cell for figure\", id, fig);\n",
" return;\n",
" }\n",
"\n",
" var output_index = fig.cell_info[2]\n",
" var cell = fig.cell_info[0];\n",
"\n",
"};\n",
"\n",
"mpl.figure.prototype.handle_close = function(fig, msg) {\n",
" var width = fig.canvas.width/mpl.ratio\n",
" fig.root.unbind('remove')\n",
"\n",
" // Update the output cell to use the data from the current canvas.\n",
" fig.push_to_output();\n",
" var dataURL = fig.canvas.toDataURL();\n",
" // Re-enable the keyboard manager in IPython - without this line, in FF,\n",
" // the notebook keyboard shortcuts fail.\n",
" IPython.keyboard_manager.enable()\n",
" $(fig.parent_element).html('<img src=\"' + dataURL + '\" width=\"' + width + '\">');\n",
" fig.close_ws(fig, msg);\n",
"}\n",
"\n",
"mpl.figure.prototype.close_ws = function(fig, msg){\n",
" fig.send_message('closing', msg);\n",
" // fig.ws.close()\n",
"}\n",
"\n",
"mpl.figure.prototype.push_to_output = function(remove_interactive) {\n",
" // Turn the data on the canvas into data in the output cell.\n",
" var width = this.canvas.width/mpl.ratio\n",
" var dataURL = this.canvas.toDataURL();\n",
" this.cell_info[1]['text/html'] = '<img src=\"' + dataURL + '\" width=\"' + width + '\">';\n",
"}\n",
"\n",
"mpl.figure.prototype.updated_canvas_event = function() {\n",
" // Tell IPython that the notebook contents must change.\n",
" IPython.notebook.set_dirty(true);\n",
" this.send_message(\"ack\", {});\n",
" var fig = this;\n",
" // Wait a second, then push the new image to the DOM so\n",
" // that it is saved nicely (might be nice to debounce this).\n",
" setTimeout(function () { fig.push_to_output() }, 1000);\n",
"}\n",
"\n",
"mpl.figure.prototype._init_toolbar = function() {\n",
" var fig = this;\n",
"\n",
" var nav_element = $('<div/>')\n",
" nav_element.attr('style', 'width: 100%');\n",
" this.root.append(nav_element);\n",
"\n",
" // Define a callback function for later on.\n",
" function toolbar_event(event) {\n",
" return fig.toolbar_button_onclick(event['data']);\n",
" }\n",
" function toolbar_mouse_event(event) {\n",
" return fig.toolbar_button_onmouseover(event['data']);\n",
" }\n",
"\n",
" for(var toolbar_ind in mpl.toolbar_items){\n",
" var name = mpl.toolbar_items[toolbar_ind][0];\n",
" var tooltip = mpl.toolbar_items[toolbar_ind][1];\n",
" var image = mpl.toolbar_items[toolbar_ind][2];\n",
" var method_name = mpl.toolbar_items[toolbar_ind][3];\n",
"\n",
" if (!name) { continue; };\n",
"\n",
" var button = $('<button class=\"btn btn-default\" href=\"#\" title=\"' + name + '\"><i class=\"fa ' + image + ' fa-lg\"></i></button>');\n",
" button.click(method_name, toolbar_event);\n",
" button.mouseover(tooltip, toolbar_mouse_event);\n",
" nav_element.append(button);\n",
" }\n",
"\n",
" // Add the status bar.\n",
" var status_bar = $('<span class=\"mpl-message\" style=\"text-align:right; float: right;\"/>');\n",
" nav_element.append(status_bar);\n",
" this.message = status_bar[0];\n",
"\n",
" // Add the close button to the window.\n",
" var buttongrp = $('<div class=\"btn-group inline pull-right\"></div>');\n",
" var button = $('<button class=\"btn btn-mini btn-primary\" href=\"#\" title=\"Stop Interaction\"><i class=\"fa fa-power-off icon-remove icon-large\"></i></button>');\n",
" button.click(function (evt) { fig.handle_close(fig, {}); } );\n",
" button.mouseover('Stop Interaction', toolbar_mouse_event);\n",
" buttongrp.append(button);\n",
" var titlebar = this.root.find($('.ui-dialog-titlebar'));\n",
" titlebar.prepend(buttongrp);\n",
"}\n",
"\n",
"mpl.figure.prototype._root_extra_style = function(el){\n",
" var fig = this\n",
" el.on(\"remove\", function(){\n",
"\tfig.close_ws(fig, {});\n",
" });\n",
"}\n",
"\n",
"mpl.figure.prototype._canvas_extra_style = function(el){\n",
" // this is important to make the div 'focusable\n",
" el.attr('tabindex', 0)\n",
" // reach out to IPython and tell the keyboard manager to turn it's self\n",
" // off when our div gets focus\n",
"\n",
" // location in version 3\n",
" if (IPython.notebook.keyboard_manager) {\n",
" IPython.notebook.keyboard_manager.register_events(el);\n",
" }\n",
" else {\n",
" // location in version 2\n",
" IPython.keyboard_manager.register_events(el);\n",
" }\n",
"\n",
"}\n",
"\n",
"mpl.figure.prototype._key_event_extra = function(event, name) {\n",
" var manager = IPython.notebook.keyboard_manager;\n",
" if (!manager)\n",
" manager = IPython.keyboard_manager;\n",
"\n",
" // Check for shift+enter\n",
" if (event.shiftKey && event.which == 13) {\n",
" this.canvas_div.blur();\n",
" // select the cell after this one\n",
" var index = IPython.notebook.find_cell_index(this.cell_info[0]);\n",
" IPython.notebook.select(index + 1);\n",
" }\n",
"}\n",
"\n",
"mpl.figure.prototype.handle_save = function(fig, msg) {\n",
" fig.ondownload(fig, null);\n",
"}\n",
"\n",
"\n",
"mpl.find_output_cell = function(html_output) {\n",
" // Return the cell and output element which can be found *uniquely* in the notebook.\n",
" // Note - this is a bit hacky, but it is done because the \"notebook_saving.Notebook\"\n",
" // IPython event is triggered only after the cells have been serialised, which for\n",
" // our purposes (turning an active figure into a static one), is too late.\n",
" var cells = IPython.notebook.get_cells();\n",
" var ncells = cells.length;\n",
" for (var i=0; i<ncells; i++) {\n",
" var cell = cells[i];\n",
" if (cell.cell_type === 'code'){\n",
" for (var j=0; j<cell.output_area.outputs.length; j++) {\n",
" var data = cell.output_area.outputs[j];\n",
" if (data.data) {\n",
" // IPython >= 3 moved mimebundle to data attribute of output\n",
" data = data.data;\n",
" }\n",
" if (data['text/html'] == html_output) {\n",
" return [cell, data, j];\n",
" }\n",
" }\n",
" }\n",
" }\n",
"}\n",
"\n",
"// Register the function which deals with the matplotlib target/channel.\n",
"// The kernel may be null if the page has been refreshed.\n",
"if (IPython.notebook.kernel != null) {\n",
" IPython.notebook.kernel.comm_manager.register_target('matplotlib', mpl.mpl_figure_comm);\n",
"}\n"
],
"text/plain": [
"<IPython.core.display.Javascript object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<img src=\"data:image/png;base64,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\" width=\"720\">"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"df_results = %sql SELECT * FROM automl_output_info;\n",
"df_results = df_results.DataFrame()\n",
"\n",
"#set up plots\n",
"fig, axs = plt.subplots(nrows=1, ncols=2, figsize=(10,5))\n",
"fig.legend(ncol=4)\n",
"fig.tight_layout()\n",
"\n",
"ax_metric = axs[0]\n",
"ax_loss = axs[1]\n",
"\n",
"ax_metric.xaxis.set_major_locator(MaxNLocator(integer=True))\n",
"ax_metric.set_xlabel('Trial')\n",
"#ax_metric.set_ylabel('Accuracy')\n",
"ax_metric.set_title('Validation Accuracy')\n",
"#ax_metric.lines.remove(ax_metric.lines)\n",
"\n",
"ax_loss.xaxis.set_major_locator(MaxNLocator(integer=True))\n",
"ax_loss.set_xlabel('Trial')\n",
"#ax_loss.set_ylabel('Cross Entropy Loss')\n",
"ax_loss.set_title('Validation Loss (Cross Entropy)')\n",
"\n",
"validation_metrics_final = df_results['validation_metrics_final']\n",
"validation_loss_final = df_results['validation_loss_final']\n",
"iters = df_results['mst_key']\n",
"#iters = [x - (iters[0]-1) for x in iters]\n",
"\n",
"#ax_metric.plot(iters, training_metrics_final, label=mst_key, marker='o')\n",
"ax_metric.plot(iters, validation_metrics_final, marker='o', linestyle='None', markersize=4)\n",
"#ax_metric.plot(iters, training_metrics)\n",
" \n",
"#ax_loss.plot(iters, training_loss_final, label=mst_key, marker='o')\n",
"ax_loss.plot(iters, validation_loss_final, marker='o', linestyle='None', markersize=4)\n",
"#ax_loss.plot(iters, training_loss)\n",
"\n",
"plt.legend();\n",
"# fig.savefig('./lc_keras_fit.png', dpi = 300)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Show best by trial"
]
},
{
"cell_type": "code",
"execution_count": 27,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"20 rows affected.\n",
"1 rows affected.\n",
"2 rows affected.\n",
"3 rows affected.\n",
"4 rows affected.\n",
"5 rows affected.\n",
"6 rows affected.\n",
"7 rows affected.\n",
"8 rows affected.\n",
"9 rows affected.\n",
"10 rows affected.\n",
"11 rows affected.\n",
"12 rows affected.\n",
"13 rows affected.\n",
"14 rows affected.\n",
"15 rows affected.\n",
"16 rows affected.\n",
"17 rows affected.\n",
"18 rows affected.\n",
"19 rows affected.\n",
"20 rows affected.\n"
]
},
{
"data": {
"application/javascript": [
"/* Put everything inside the global mpl namespace */\n",
"window.mpl = {};\n",
"\n",
"\n",
"mpl.get_websocket_type = function() {\n",
" if (typeof(WebSocket) !== 'undefined') {\n",
" return WebSocket;\n",
" } else if (typeof(MozWebSocket) !== 'undefined') {\n",
" return MozWebSocket;\n",
" } else {\n",
" alert('Your browser does not have WebSocket support.' +\n",
" 'Please try Chrome, Safari or Firefox ≥ 6. ' +\n",
" 'Firefox 4 and 5 are also supported but you ' +\n",
" 'have to enable WebSockets in about:config.');\n",
" };\n",
"}\n",
"\n",
"mpl.figure = function(figure_id, websocket, ondownload, parent_element) {\n",
" this.id = figure_id;\n",
"\n",
" this.ws = websocket;\n",
"\n",
" this.supports_binary = (this.ws.binaryType != undefined);\n",
"\n",
" if (!this.supports_binary) {\n",
" var warnings = document.getElementById(\"mpl-warnings\");\n",
" if (warnings) {\n",
" warnings.style.display = 'block';\n",
" warnings.textContent = (\n",
" \"This browser does not support binary websocket messages. \" +\n",
" \"Performance may be slow.\");\n",
" }\n",
" }\n",
"\n",
" this.imageObj = new Image();\n",
"\n",
" this.context = undefined;\n",
" this.message = undefined;\n",
" this.canvas = undefined;\n",
" this.rubberband_canvas = undefined;\n",
" this.rubberband_context = undefined;\n",
" this.format_dropdown = undefined;\n",
"\n",
" this.image_mode = 'full';\n",
"\n",
" this.root = $('<div/>');\n",
" this._root_extra_style(this.root)\n",
" this.root.attr('style', 'display: inline-block');\n",
"\n",
" $(parent_element).append(this.root);\n",
"\n",
" this._init_header(this);\n",
" this._init_canvas(this);\n",
" this._init_toolbar(this);\n",
"\n",
" var fig = this;\n",
"\n",
" this.waiting = false;\n",
"\n",
" this.ws.onopen = function () {\n",
" fig.send_message(\"supports_binary\", {value: fig.supports_binary});\n",
" fig.send_message(\"send_image_mode\", {});\n",
" if (mpl.ratio != 1) {\n",
" fig.send_message(\"set_dpi_ratio\", {'dpi_ratio': mpl.ratio});\n",
" }\n",
" fig.send_message(\"refresh\", {});\n",
" }\n",
"\n",
" this.imageObj.onload = function() {\n",
" if (fig.image_mode == 'full') {\n",
" // Full images could contain transparency (where diff images\n",
" // almost always do), so we need to clear the canvas so that\n",
" // there is no ghosting.\n",
" fig.context.clearRect(0, 0, fig.canvas.width, fig.canvas.height);\n",
" }\n",
" fig.context.drawImage(fig.imageObj, 0, 0);\n",
" };\n",
"\n",
" this.imageObj.onunload = function() {\n",
" fig.ws.close();\n",
" }\n",
"\n",
" this.ws.onmessage = this._make_on_message_function(this);\n",
"\n",
" this.ondownload = ondownload;\n",
"}\n",
"\n",
"mpl.figure.prototype._init_header = function() {\n",
" var titlebar = $(\n",
" '<div class=\"ui-dialog-titlebar ui-widget-header ui-corner-all ' +\n",
" 'ui-helper-clearfix\"/>');\n",
" var titletext = $(\n",
" '<div class=\"ui-dialog-title\" style=\"width: 100%; ' +\n",
" 'text-align: center; padding: 3px;\"/>');\n",
" titlebar.append(titletext)\n",
" this.root.append(titlebar);\n",
" this.header = titletext[0];\n",
"}\n",
"\n",
"\n",
"\n",
"mpl.figure.prototype._canvas_extra_style = function(canvas_div) {\n",
"\n",
"}\n",
"\n",
"\n",
"mpl.figure.prototype._root_extra_style = function(canvas_div) {\n",
"\n",
"}\n",
"\n",
"mpl.figure.prototype._init_canvas = function() {\n",
" var fig = this;\n",
"\n",
" var canvas_div = $('<div/>');\n",
"\n",
" canvas_div.attr('style', 'position: relative; clear: both; outline: 0');\n",
"\n",
" function canvas_keyboard_event(event) {\n",
" return fig.key_event(event, event['data']);\n",
" }\n",
"\n",
" canvas_div.keydown('key_press', canvas_keyboard_event);\n",
" canvas_div.keyup('key_release', canvas_keyboard_event);\n",
" this.canvas_div = canvas_div\n",
" this._canvas_extra_style(canvas_div)\n",
" this.root.append(canvas_div);\n",
"\n",
" var canvas = $('<canvas/>');\n",
" canvas.addClass('mpl-canvas');\n",
" canvas.attr('style', \"left: 0; top: 0; z-index: 0; outline: 0\")\n",
"\n",
" this.canvas = canvas[0];\n",
" this.context = canvas[0].getContext(\"2d\");\n",
"\n",
" var backingStore = this.context.backingStorePixelRatio ||\n",
"\tthis.context.webkitBackingStorePixelRatio ||\n",
"\tthis.context.mozBackingStorePixelRatio ||\n",
"\tthis.context.msBackingStorePixelRatio ||\n",
"\tthis.context.oBackingStorePixelRatio ||\n",
"\tthis.context.backingStorePixelRatio || 1;\n",
"\n",
" mpl.ratio = (window.devicePixelRatio || 1) / backingStore;\n",
"\n",
" var rubberband = $('<canvas/>');\n",
" rubberband.attr('style', \"position: absolute; left: 0; top: 0; z-index: 1;\")\n",
"\n",
" var pass_mouse_events = true;\n",
"\n",
" canvas_div.resizable({\n",
" start: function(event, ui) {\n",
" pass_mouse_events = false;\n",
" },\n",
" resize: function(event, ui) {\n",
" fig.request_resize(ui.size.width, ui.size.height);\n",
" },\n",
" stop: function(event, ui) {\n",
" pass_mouse_events = true;\n",
" fig.request_resize(ui.size.width, ui.size.height);\n",
" },\n",
" });\n",
"\n",
" function mouse_event_fn(event) {\n",
" if (pass_mouse_events)\n",
" return fig.mouse_event(event, event['data']);\n",
" }\n",
"\n",
" rubberband.mousedown('button_press', mouse_event_fn);\n",
" rubberband.mouseup('button_release', mouse_event_fn);\n",
" // Throttle sequential mouse events to 1 every 20ms.\n",
" rubberband.mousemove('motion_notify', mouse_event_fn);\n",
"\n",
" rubberband.mouseenter('figure_enter', mouse_event_fn);\n",
" rubberband.mouseleave('figure_leave', mouse_event_fn);\n",
"\n",
" canvas_div.on(\"wheel\", function (event) {\n",
" event = event.originalEvent;\n",
" event['data'] = 'scroll'\n",
" if (event.deltaY < 0) {\n",
" event.step = 1;\n",
" } else {\n",
" event.step = -1;\n",
" }\n",
" mouse_event_fn(event);\n",
" });\n",
"\n",
" canvas_div.append(canvas);\n",
" canvas_div.append(rubberband);\n",
"\n",
" this.rubberband = rubberband;\n",
" this.rubberband_canvas = rubberband[0];\n",
" this.rubberband_context = rubberband[0].getContext(\"2d\");\n",
" this.rubberband_context.strokeStyle = \"#000000\";\n",
"\n",
" this._resize_canvas = function(width, height) {\n",
" // Keep the size of the canvas, canvas container, and rubber band\n",
" // canvas in synch.\n",
" canvas_div.css('width', width)\n",
" canvas_div.css('height', height)\n",
"\n",
" canvas.attr('width', width * mpl.ratio);\n",
" canvas.attr('height', height * mpl.ratio);\n",
" canvas.attr('style', 'width: ' + width + 'px; height: ' + height + 'px;');\n",
"\n",
" rubberband.attr('width', width);\n",
" rubberband.attr('height', height);\n",
" }\n",
"\n",
" // Set the figure to an initial 600x600px, this will subsequently be updated\n",
" // upon first draw.\n",
" this._resize_canvas(600, 600);\n",
"\n",
" // Disable right mouse context menu.\n",
" $(this.rubberband_canvas).bind(\"contextmenu\",function(e){\n",
" return false;\n",
" });\n",
"\n",
" function set_focus () {\n",
" canvas.focus();\n",
" canvas_div.focus();\n",
" }\n",
"\n",
" window.setTimeout(set_focus, 100);\n",
"}\n",
"\n",
"mpl.figure.prototype._init_toolbar = function() {\n",
" var fig = this;\n",
"\n",
" var nav_element = $('<div/>')\n",
" nav_element.attr('style', 'width: 100%');\n",
" this.root.append(nav_element);\n",
"\n",
" // Define a callback function for later on.\n",
" function toolbar_event(event) {\n",
" return fig.toolbar_button_onclick(event['data']);\n",
" }\n",
" function toolbar_mouse_event(event) {\n",
" return fig.toolbar_button_onmouseover(event['data']);\n",
" }\n",
"\n",
" for(var toolbar_ind in mpl.toolbar_items) {\n",
" var name = mpl.toolbar_items[toolbar_ind][0];\n",
" var tooltip = mpl.toolbar_items[toolbar_ind][1];\n",
" var image = mpl.toolbar_items[toolbar_ind][2];\n",
" var method_name = mpl.toolbar_items[toolbar_ind][3];\n",
"\n",
" if (!name) {\n",
" // put a spacer in here.\n",
" continue;\n",
" }\n",
" var button = $('<button/>');\n",
" button.addClass('ui-button ui-widget ui-state-default ui-corner-all ' +\n",
" 'ui-button-icon-only');\n",
" button.attr('role', 'button');\n",
" button.attr('aria-disabled', 'false');\n",
" button.click(method_name, toolbar_event);\n",
" button.mouseover(tooltip, toolbar_mouse_event);\n",
"\n",
" var icon_img = $('<span/>');\n",
" icon_img.addClass('ui-button-icon-primary ui-icon');\n",
" icon_img.addClass(image);\n",
" icon_img.addClass('ui-corner-all');\n",
"\n",
" var tooltip_span = $('<span/>');\n",
" tooltip_span.addClass('ui-button-text');\n",
" tooltip_span.html(tooltip);\n",
"\n",
" button.append(icon_img);\n",
" button.append(tooltip_span);\n",
"\n",
" nav_element.append(button);\n",
" }\n",
"\n",
" var fmt_picker_span = $('<span/>');\n",
"\n",
" var fmt_picker = $('<select/>');\n",
" fmt_picker.addClass('mpl-toolbar-option ui-widget ui-widget-content');\n",
" fmt_picker_span.append(fmt_picker);\n",
" nav_element.append(fmt_picker_span);\n",
" this.format_dropdown = fmt_picker[0];\n",
"\n",
" for (var ind in mpl.extensions) {\n",
" var fmt = mpl.extensions[ind];\n",
" var option = $(\n",
" '<option/>', {selected: fmt === mpl.default_extension}).html(fmt);\n",
" fmt_picker.append(option)\n",
" }\n",
"\n",
" // Add hover states to the ui-buttons\n",
" $( \".ui-button\" ).hover(\n",
" function() { $(this).addClass(\"ui-state-hover\");},\n",
" function() { $(this).removeClass(\"ui-state-hover\");}\n",
" );\n",
"\n",
" var status_bar = $('<span class=\"mpl-message\"/>');\n",
" nav_element.append(status_bar);\n",
" this.message = status_bar[0];\n",
"}\n",
"\n",
"mpl.figure.prototype.request_resize = function(x_pixels, y_pixels) {\n",
" // Request matplotlib to resize the figure. Matplotlib will then trigger a resize in the client,\n",
" // which will in turn request a refresh of the image.\n",
" this.send_message('resize', {'width': x_pixels, 'height': y_pixels});\n",
"}\n",
"\n",
"mpl.figure.prototype.send_message = function(type, properties) {\n",
" properties['type'] = type;\n",
" properties['figure_id'] = this.id;\n",
" this.ws.send(JSON.stringify(properties));\n",
"}\n",
"\n",
"mpl.figure.prototype.send_draw_message = function() {\n",
" if (!this.waiting) {\n",
" this.waiting = true;\n",
" this.ws.send(JSON.stringify({type: \"draw\", figure_id: this.id}));\n",
" }\n",
"}\n",
"\n",
"\n",
"mpl.figure.prototype.handle_save = function(fig, msg) {\n",
" var format_dropdown = fig.format_dropdown;\n",
" var format = format_dropdown.options[format_dropdown.selectedIndex].value;\n",
" fig.ondownload(fig, format);\n",
"}\n",
"\n",
"\n",
"mpl.figure.prototype.handle_resize = function(fig, msg) {\n",
" var size = msg['size'];\n",
" if (size[0] != fig.canvas.width || size[1] != fig.canvas.height) {\n",
" fig._resize_canvas(size[0], size[1]);\n",
" fig.send_message(\"refresh\", {});\n",
" };\n",
"}\n",
"\n",
"mpl.figure.prototype.handle_rubberband = function(fig, msg) {\n",
" var x0 = msg['x0'] / mpl.ratio;\n",
" var y0 = (fig.canvas.height - msg['y0']) / mpl.ratio;\n",
" var x1 = msg['x1'] / mpl.ratio;\n",
" var y1 = (fig.canvas.height - msg['y1']) / mpl.ratio;\n",
" x0 = Math.floor(x0) + 0.5;\n",
" y0 = Math.floor(y0) + 0.5;\n",
" x1 = Math.floor(x1) + 0.5;\n",
" y1 = Math.floor(y1) + 0.5;\n",
" var min_x = Math.min(x0, x1);\n",
" var min_y = Math.min(y0, y1);\n",
" var width = Math.abs(x1 - x0);\n",
" var height = Math.abs(y1 - y0);\n",
"\n",
" fig.rubberband_context.clearRect(\n",
" 0, 0, fig.canvas.width, fig.canvas.height);\n",
"\n",
" fig.rubberband_context.strokeRect(min_x, min_y, width, height);\n",
"}\n",
"\n",
"mpl.figure.prototype.handle_figure_label = function(fig, msg) {\n",
" // Updates the figure title.\n",
" fig.header.textContent = msg['label'];\n",
"}\n",
"\n",
"mpl.figure.prototype.handle_cursor = function(fig, msg) {\n",
" var cursor = msg['cursor'];\n",
" switch(cursor)\n",
" {\n",
" case 0:\n",
" cursor = 'pointer';\n",
" break;\n",
" case 1:\n",
" cursor = 'default';\n",
" break;\n",
" case 2:\n",
" cursor = 'crosshair';\n",
" break;\n",
" case 3:\n",
" cursor = 'move';\n",
" break;\n",
" }\n",
" fig.rubberband_canvas.style.cursor = cursor;\n",
"}\n",
"\n",
"mpl.figure.prototype.handle_message = function(fig, msg) {\n",
" fig.message.textContent = msg['message'];\n",
"}\n",
"\n",
"mpl.figure.prototype.handle_draw = function(fig, msg) {\n",
" // Request the server to send over a new figure.\n",
" fig.send_draw_message();\n",
"}\n",
"\n",
"mpl.figure.prototype.handle_image_mode = function(fig, msg) {\n",
" fig.image_mode = msg['mode'];\n",
"}\n",
"\n",
"mpl.figure.prototype.updated_canvas_event = function() {\n",
" // Called whenever the canvas gets updated.\n",
" this.send_message(\"ack\", {});\n",
"}\n",
"\n",
"// A function to construct a web socket function for onmessage handling.\n",
"// Called in the figure constructor.\n",
"mpl.figure.prototype._make_on_message_function = function(fig) {\n",
" return function socket_on_message(evt) {\n",
" if (evt.data instanceof Blob) {\n",
" /* FIXME: We get \"Resource interpreted as Image but\n",
" * transferred with MIME type text/plain:\" errors on\n",
" * Chrome. But how to set the MIME type? It doesn't seem\n",
" * to be part of the websocket stream */\n",
" evt.data.type = \"image/png\";\n",
"\n",
" /* Free the memory for the previous frames */\n",
" if (fig.imageObj.src) {\n",
" (window.URL || window.webkitURL).revokeObjectURL(\n",
" fig.imageObj.src);\n",
" }\n",
"\n",
" fig.imageObj.src = (window.URL || window.webkitURL).createObjectURL(\n",
" evt.data);\n",
" fig.updated_canvas_event();\n",
" fig.waiting = false;\n",
" return;\n",
" }\n",
" else if (typeof evt.data === 'string' && evt.data.slice(0, 21) == \"data:image/png;base64\") {\n",
" fig.imageObj.src = evt.data;\n",
" fig.updated_canvas_event();\n",
" fig.waiting = false;\n",
" return;\n",
" }\n",
"\n",
" var msg = JSON.parse(evt.data);\n",
" var msg_type = msg['type'];\n",
"\n",
" // Call the \"handle_{type}\" callback, which takes\n",
" // the figure and JSON message as its only arguments.\n",
" try {\n",
" var callback = fig[\"handle_\" + msg_type];\n",
" } catch (e) {\n",
" console.log(\"No handler for the '\" + msg_type + \"' message type: \", msg);\n",
" return;\n",
" }\n",
"\n",
" if (callback) {\n",
" try {\n",
" // console.log(\"Handling '\" + msg_type + \"' message: \", msg);\n",
" callback(fig, msg);\n",
" } catch (e) {\n",
" console.log(\"Exception inside the 'handler_\" + msg_type + \"' callback:\", e, e.stack, msg);\n",
" }\n",
" }\n",
" };\n",
"}\n",
"\n",
"// from http://stackoverflow.com/questions/1114465/getting-mouse-location-in-canvas\n",
"mpl.findpos = function(e) {\n",
" //this section is from http://www.quirksmode.org/js/events_properties.html\n",
" var targ;\n",
" if (!e)\n",
" e = window.event;\n",
" if (e.target)\n",
" targ = e.target;\n",
" else if (e.srcElement)\n",
" targ = e.srcElement;\n",
" if (targ.nodeType == 3) // defeat Safari bug\n",
" targ = targ.parentNode;\n",
"\n",
" // jQuery normalizes the pageX and pageY\n",
" // pageX,Y are the mouse positions relative to the document\n",
" // offset() returns the position of the element relative to the document\n",
" var x = e.pageX - $(targ).offset().left;\n",
" var y = e.pageY - $(targ).offset().top;\n",
"\n",
" return {\"x\": x, \"y\": y};\n",
"};\n",
"\n",
"/*\n",
" * return a copy of an object with only non-object keys\n",
" * we need this to avoid circular references\n",
" * http://stackoverflow.com/a/24161582/3208463\n",
" */\n",
"function simpleKeys (original) {\n",
" return Object.keys(original).reduce(function (obj, key) {\n",
" if (typeof original[key] !== 'object')\n",
" obj[key] = original[key]\n",
" return obj;\n",
" }, {});\n",
"}\n",
"\n",
"mpl.figure.prototype.mouse_event = function(event, name) {\n",
" var canvas_pos = mpl.findpos(event)\n",
"\n",
" if (name === 'button_press')\n",
" {\n",
" this.canvas.focus();\n",
" this.canvas_div.focus();\n",
" }\n",
"\n",
" var x = canvas_pos.x * mpl.ratio;\n",
" var y = canvas_pos.y * mpl.ratio;\n",
"\n",
" this.send_message(name, {x: x, y: y, button: event.button,\n",
" step: event.step,\n",
" guiEvent: simpleKeys(event)});\n",
"\n",
" /* This prevents the web browser from automatically changing to\n",
" * the text insertion cursor when the button is pressed. We want\n",
" * to control all of the cursor setting manually through the\n",
" * 'cursor' event from matplotlib */\n",
" event.preventDefault();\n",
" return false;\n",
"}\n",
"\n",
"mpl.figure.prototype._key_event_extra = function(event, name) {\n",
" // Handle any extra behaviour associated with a key event\n",
"}\n",
"\n",
"mpl.figure.prototype.key_event = function(event, name) {\n",
"\n",
" // Prevent repeat events\n",
" if (name == 'key_press')\n",
" {\n",
" if (event.which === this._key)\n",
" return;\n",
" else\n",
" this._key = event.which;\n",
" }\n",
" if (name == 'key_release')\n",
" this._key = null;\n",
"\n",
" var value = '';\n",
" if (event.ctrlKey && event.which != 17)\n",
" value += \"ctrl+\";\n",
" if (event.altKey && event.which != 18)\n",
" value += \"alt+\";\n",
" if (event.shiftKey && event.which != 16)\n",
" value += \"shift+\";\n",
"\n",
" value += 'k';\n",
" value += event.which.toString();\n",
"\n",
" this._key_event_extra(event, name);\n",
"\n",
" this.send_message(name, {key: value,\n",
" guiEvent: simpleKeys(event)});\n",
" return false;\n",
"}\n",
"\n",
"mpl.figure.prototype.toolbar_button_onclick = function(name) {\n",
" if (name == 'download') {\n",
" this.handle_save(this, null);\n",
" } else {\n",
" this.send_message(\"toolbar_button\", {name: name});\n",
" }\n",
"};\n",
"\n",
"mpl.figure.prototype.toolbar_button_onmouseover = function(tooltip) {\n",
" this.message.textContent = tooltip;\n",
"};\n",
"mpl.toolbar_items = [[\"Home\", \"Reset original view\", \"fa fa-home icon-home\", \"home\"], [\"Back\", \"Back to previous view\", \"fa fa-arrow-left icon-arrow-left\", \"back\"], [\"Forward\", \"Forward to next view\", \"fa fa-arrow-right icon-arrow-right\", \"forward\"], [\"\", \"\", \"\", \"\"], [\"Pan\", \"Pan axes with left mouse, zoom with right\", \"fa fa-arrows icon-move\", \"pan\"], [\"Zoom\", \"Zoom to rectangle\", \"fa fa-square-o icon-check-empty\", \"zoom\"], [\"\", \"\", \"\", \"\"], [\"Download\", \"Download plot\", \"fa fa-floppy-o icon-save\", \"download\"]];\n",
"\n",
"mpl.extensions = [\"eps\", \"jpeg\", \"pdf\", \"png\", \"ps\", \"raw\", \"svg\", \"tif\"];\n",
"\n",
"mpl.default_extension = \"png\";var comm_websocket_adapter = function(comm) {\n",
" // Create a \"websocket\"-like object which calls the given IPython comm\n",
" // object with the appropriate methods. Currently this is a non binary\n",
" // socket, so there is still some room for performance tuning.\n",
" var ws = {};\n",
"\n",
" ws.close = function() {\n",
" comm.close()\n",
" };\n",
" ws.send = function(m) {\n",
" //console.log('sending', m);\n",
" comm.send(m);\n",
" };\n",
" // Register the callback with on_msg.\n",
" comm.on_msg(function(msg) {\n",
" //console.log('receiving', msg['content']['data'], msg);\n",
" // Pass the mpl event to the overridden (by mpl) onmessage function.\n",
" ws.onmessage(msg['content']['data'])\n",
" });\n",
" return ws;\n",
"}\n",
"\n",
"mpl.mpl_figure_comm = function(comm, msg) {\n",
" // This is the function which gets called when the mpl process\n",
" // starts-up an IPython Comm through the \"matplotlib\" channel.\n",
"\n",
" var id = msg.content.data.id;\n",
" // Get hold of the div created by the display call when the Comm\n",
" // socket was opened in Python.\n",
" var element = $(\"#\" + id);\n",
" var ws_proxy = comm_websocket_adapter(comm)\n",
"\n",
" function ondownload(figure, format) {\n",
" window.open(figure.imageObj.src);\n",
" }\n",
"\n",
" var fig = new mpl.figure(id, ws_proxy,\n",
" ondownload,\n",
" element.get(0));\n",
"\n",
" // Call onopen now - mpl needs it, as it is assuming we've passed it a real\n",
" // web socket which is closed, not our websocket->open comm proxy.\n",
" ws_proxy.onopen();\n",
"\n",
" fig.parent_element = element.get(0);\n",
" fig.cell_info = mpl.find_output_cell(\"<div id='\" + id + \"'></div>\");\n",
" if (!fig.cell_info) {\n",
" console.error(\"Failed to find cell for figure\", id, fig);\n",
" return;\n",
" }\n",
"\n",
" var output_index = fig.cell_info[2]\n",
" var cell = fig.cell_info[0];\n",
"\n",
"};\n",
"\n",
"mpl.figure.prototype.handle_close = function(fig, msg) {\n",
" var width = fig.canvas.width/mpl.ratio\n",
" fig.root.unbind('remove')\n",
"\n",
" // Update the output cell to use the data from the current canvas.\n",
" fig.push_to_output();\n",
" var dataURL = fig.canvas.toDataURL();\n",
" // Re-enable the keyboard manager in IPython - without this line, in FF,\n",
" // the notebook keyboard shortcuts fail.\n",
" IPython.keyboard_manager.enable()\n",
" $(fig.parent_element).html('<img src=\"' + dataURL + '\" width=\"' + width + '\">');\n",
" fig.close_ws(fig, msg);\n",
"}\n",
"\n",
"mpl.figure.prototype.close_ws = function(fig, msg){\n",
" fig.send_message('closing', msg);\n",
" // fig.ws.close()\n",
"}\n",
"\n",
"mpl.figure.prototype.push_to_output = function(remove_interactive) {\n",
" // Turn the data on the canvas into data in the output cell.\n",
" var width = this.canvas.width/mpl.ratio\n",
" var dataURL = this.canvas.toDataURL();\n",
" this.cell_info[1]['text/html'] = '<img src=\"' + dataURL + '\" width=\"' + width + '\">';\n",
"}\n",
"\n",
"mpl.figure.prototype.updated_canvas_event = function() {\n",
" // Tell IPython that the notebook contents must change.\n",
" IPython.notebook.set_dirty(true);\n",
" this.send_message(\"ack\", {});\n",
" var fig = this;\n",
" // Wait a second, then push the new image to the DOM so\n",
" // that it is saved nicely (might be nice to debounce this).\n",
" setTimeout(function () { fig.push_to_output() }, 1000);\n",
"}\n",
"\n",
"mpl.figure.prototype._init_toolbar = function() {\n",
" var fig = this;\n",
"\n",
" var nav_element = $('<div/>')\n",
" nav_element.attr('style', 'width: 100%');\n",
" this.root.append(nav_element);\n",
"\n",
" // Define a callback function for later on.\n",
" function toolbar_event(event) {\n",
" return fig.toolbar_button_onclick(event['data']);\n",
" }\n",
" function toolbar_mouse_event(event) {\n",
" return fig.toolbar_button_onmouseover(event['data']);\n",
" }\n",
"\n",
" for(var toolbar_ind in mpl.toolbar_items){\n",
" var name = mpl.toolbar_items[toolbar_ind][0];\n",
" var tooltip = mpl.toolbar_items[toolbar_ind][1];\n",
" var image = mpl.toolbar_items[toolbar_ind][2];\n",
" var method_name = mpl.toolbar_items[toolbar_ind][3];\n",
"\n",
" if (!name) { continue; };\n",
"\n",
" var button = $('<button class=\"btn btn-default\" href=\"#\" title=\"' + name + '\"><i class=\"fa ' + image + ' fa-lg\"></i></button>');\n",
" button.click(method_name, toolbar_event);\n",
" button.mouseover(tooltip, toolbar_mouse_event);\n",
" nav_element.append(button);\n",
" }\n",
"\n",
" // Add the status bar.\n",
" var status_bar = $('<span class=\"mpl-message\" style=\"text-align:right; float: right;\"/>');\n",
" nav_element.append(status_bar);\n",
" this.message = status_bar[0];\n",
"\n",
" // Add the close button to the window.\n",
" var buttongrp = $('<div class=\"btn-group inline pull-right\"></div>');\n",
" var button = $('<button class=\"btn btn-mini btn-primary\" href=\"#\" title=\"Stop Interaction\"><i class=\"fa fa-power-off icon-remove icon-large\"></i></button>');\n",
" button.click(function (evt) { fig.handle_close(fig, {}); } );\n",
" button.mouseover('Stop Interaction', toolbar_mouse_event);\n",
" buttongrp.append(button);\n",
" var titlebar = this.root.find($('.ui-dialog-titlebar'));\n",
" titlebar.prepend(buttongrp);\n",
"}\n",
"\n",
"mpl.figure.prototype._root_extra_style = function(el){\n",
" var fig = this\n",
" el.on(\"remove\", function(){\n",
"\tfig.close_ws(fig, {});\n",
" });\n",
"}\n",
"\n",
"mpl.figure.prototype._canvas_extra_style = function(el){\n",
" // this is important to make the div 'focusable\n",
" el.attr('tabindex', 0)\n",
" // reach out to IPython and tell the keyboard manager to turn it's self\n",
" // off when our div gets focus\n",
"\n",
" // location in version 3\n",
" if (IPython.notebook.keyboard_manager) {\n",
" IPython.notebook.keyboard_manager.register_events(el);\n",
" }\n",
" else {\n",
" // location in version 2\n",
" IPython.keyboard_manager.register_events(el);\n",
" }\n",
"\n",
"}\n",
"\n",
"mpl.figure.prototype._key_event_extra = function(event, name) {\n",
" var manager = IPython.notebook.keyboard_manager;\n",
" if (!manager)\n",
" manager = IPython.keyboard_manager;\n",
"\n",
" // Check for shift+enter\n",
" if (event.shiftKey && event.which == 13) {\n",
" this.canvas_div.blur();\n",
" // select the cell after this one\n",
" var index = IPython.notebook.find_cell_index(this.cell_info[0]);\n",
" IPython.notebook.select(index + 1);\n",
" }\n",
"}\n",
"\n",
"mpl.figure.prototype.handle_save = function(fig, msg) {\n",
" fig.ondownload(fig, null);\n",
"}\n",
"\n",
"\n",
"mpl.find_output_cell = function(html_output) {\n",
" // Return the cell and output element which can be found *uniquely* in the notebook.\n",
" // Note - this is a bit hacky, but it is done because the \"notebook_saving.Notebook\"\n",
" // IPython event is triggered only after the cells have been serialised, which for\n",
" // our purposes (turning an active figure into a static one), is too late.\n",
" var cells = IPython.notebook.get_cells();\n",
" var ncells = cells.length;\n",
" for (var i=0; i<ncells; i++) {\n",
" var cell = cells[i];\n",
" if (cell.cell_type === 'code'){\n",
" for (var j=0; j<cell.output_area.outputs.length; j++) {\n",
" var data = cell.output_area.outputs[j];\n",
" if (data.data) {\n",
" // IPython >= 3 moved mimebundle to data attribute of output\n",
" data = data.data;\n",
" }\n",
" if (data['text/html'] == html_output) {\n",
" return [cell, data, j];\n",
" }\n",
" }\n",
" }\n",
" }\n",
"}\n",
"\n",
"// Register the function which deals with the matplotlib target/channel.\n",
"// The kernel may be null if the page has been refreshed.\n",
"if (IPython.notebook.kernel != null) {\n",
" IPython.notebook.kernel.comm_manager.register_target('matplotlib', mpl.mpl_figure_comm);\n",
"}\n"
],
"text/plain": [
"<IPython.core.display.Javascript object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<img src=\"data:image/png;base64,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\" width=\"720\">"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"df_results = %sql SELECT * FROM automl_output_info ORDER BY mst_key;\n",
"df_results = df_results.DataFrame()\n",
"\n",
"best_so_far_acc = []\n",
"best_so_far_loss = []\n",
"\n",
"for mst_key in df_results['mst_key']:\n",
" df_output_info = %sql SELECT mst_key, validation_metrics_final, validation_loss_final FROM automl_output_info WHERE mst_key <= $mst_key; \n",
" df_output_info = df_output_info.DataFrame()\n",
" best_so_far_acc.append([mst_key, df_output_info['validation_metrics_final'].max()])\n",
" best_so_far_loss.append([mst_key, df_output_info['validation_loss_final'].min()])\n",
"\n",
"df1 = pd.DataFrame(best_so_far_acc,columns=['Trial','Validation Accuracy'])\n",
"df2 = pd.DataFrame(best_so_far_loss,columns=['Trial','Validation Loss'])\n",
"\n",
"#set up plots\n",
"fig, axs = plt.subplots(nrows=1, ncols=2, figsize=(10,5))\n",
"fig.legend(ncol=4)\n",
"fig.tight_layout()\n",
"\n",
"ax_metric = axs[0]\n",
"ax_loss = axs[1]\n",
"\n",
"ax_metric.xaxis.set_major_locator(MaxNLocator(integer=True))\n",
"ax_metric.set_xlabel('Trial')\n",
"#ax_metric.set_ylabel('Accuracy')\n",
"ax_metric.set_title('Best Validation Accuracy')\n",
"#ax_metric.lines.remove(ax_metric.lines)\n",
"\n",
"ax_loss.xaxis.set_major_locator(MaxNLocator(integer=True))\n",
"ax_loss.set_xlabel('Trial')\n",
"#ax_loss.set_ylabel('Cross Entropy Loss')\n",
"ax_loss.set_title('Best Validation Loss (Cross Entropy)')\n",
"\n",
"validation_metrics_final = df1['Validation Accuracy']\n",
"validation_loss_final = df2['Validation Loss']\n",
"iters1 = df1['Trial']\n",
"iters2 = df2['Trial']\n",
"\n",
"#ax_metric.plot(iters1, training_metrics_final, label=mst_key, marker='o')\n",
"#ax_metric.plot(iters1, validation_metrics_final, marker='o', linestyle='None', markersize=4)\n",
"#ax_metric.plot(iters1, validation_metrics_final, marker='o', markersize=0.5)\n",
"ax_metric.plot(iters1, validation_metrics_final)\n",
" \n",
"#ax_loss.plot(iters2, training_loss_final, label=mst_key, marker='o')\n",
"#ax_loss.plot(iters2, validation_loss_final, marker='o', linestyle='None', markersize=4)\n",
"ax_loss.plot(iters2, validation_loss_final)\n",
"\n",
"plt.legend();\n",
"# fig.savefig('./lc_keras_fit.png', dpi = 300)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"<a id=\"pred\"></a>\n",
"# 6. Predict\n",
"\n",
"Now predict using model we built. We will use the validation data set for prediction as well, which is not usual but serves to show the syntax:"
]
},
{
"cell_type": "code",
"execution_count": 28,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Done.\n",
"1 rows affected.\n",
"30 rows affected.\n"
]
},
{
"data": {
"text/html": [
"<table>\n",
" <tr>\n",
" <th>id</th>\n",
" <th>class_name</th>\n",
" <th>class_value</th>\n",
" <th>prob</th>\n",
" </tr>\n",
" <tr>\n",
" <td>1</td>\n",
" <td>class_text</td>\n",
" <td>Iris-setosa</td>\n",
" <td>0.77083427</td>\n",
" </tr>\n",
" <tr>\n",
" <td>2</td>\n",
" <td>class_text</td>\n",
" <td>Iris-setosa</td>\n",
" <td>0.76736474</td>\n",
" </tr>\n",
" <tr>\n",
" <td>3</td>\n",
" <td>class_text</td>\n",
" <td>Iris-setosa</td>\n",
" <td>0.7637215</td>\n",
" </tr>\n",
" <tr>\n",
" <td>4</td>\n",
" <td>class_text</td>\n",
" <td>Iris-setosa</td>\n",
" <td>0.76102996</td>\n",
" </tr>\n",
" <tr>\n",
" <td>6</td>\n",
" <td>class_text</td>\n",
" <td>Iris-setosa</td>\n",
" <td>0.7710857</td>\n",
" </tr>\n",
" <tr>\n",
" <td>7</td>\n",
" <td>class_text</td>\n",
" <td>Iris-setosa</td>\n",
" <td>0.7592268</td>\n",
" </tr>\n",
" <tr>\n",
" <td>8</td>\n",
" <td>class_text</td>\n",
" <td>Iris-setosa</td>\n",
" <td>0.7686342</td>\n",
" </tr>\n",
" <tr>\n",
" <td>10</td>\n",
" <td>class_text</td>\n",
" <td>Iris-setosa</td>\n",
" <td>0.76880336</td>\n",
" </tr>\n",
" <tr>\n",
" <td>18</td>\n",
" <td>class_text</td>\n",
" <td>Iris-setosa</td>\n",
" <td>0.7689748</td>\n",
" </tr>\n",
" <tr>\n",
" <td>19</td>\n",
" <td>class_text</td>\n",
" <td>Iris-setosa</td>\n",
" <td>0.77831817</td>\n",
" </tr>\n",
" <tr>\n",
" <td>28</td>\n",
" <td>class_text</td>\n",
" <td>Iris-setosa</td>\n",
" <td>0.7722787</td>\n",
" </tr>\n",
" <tr>\n",
" <td>47</td>\n",
" <td>class_text</td>\n",
" <td>Iris-setosa</td>\n",
" <td>0.76963973</td>\n",
" </tr>\n",
" <tr>\n",
" <td>50</td>\n",
" <td>class_text</td>\n",
" <td>Iris-setosa</td>\n",
" <td>0.7690843</td>\n",
" </tr>\n",
" <tr>\n",
" <td>60</td>\n",
" <td>class_text</td>\n",
" <td>Iris-virginica</td>\n",
" <td>0.5698719</td>\n",
" </tr>\n",
" <tr>\n",
" <td>65</td>\n",
" <td>class_text</td>\n",
" <td>Iris-versicolor</td>\n",
" <td>0.71937233</td>\n",
" </tr>\n",
" <tr>\n",
" <td>69</td>\n",
" <td>class_text</td>\n",
" <td>Iris-versicolor</td>\n",
" <td>0.7692964</td>\n",
" </tr>\n",
" <tr>\n",
" <td>75</td>\n",
" <td>class_text</td>\n",
" <td>Iris-versicolor</td>\n",
" <td>0.8146459</td>\n",
" </tr>\n",
" <tr>\n",
" <td>79</td>\n",
" <td>class_text</td>\n",
" <td>Iris-versicolor</td>\n",
" <td>0.5106894</td>\n",
" </tr>\n",
" <tr>\n",
" <td>80</td>\n",
" <td>class_text</td>\n",
" <td>Iris-versicolor</td>\n",
" <td>0.7508131</td>\n",
" </tr>\n",
" <tr>\n",
" <td>82</td>\n",
" <td>class_text</td>\n",
" <td>Iris-versicolor</td>\n",
" <td>0.77062976</td>\n",
" </tr>\n",
" <tr>\n",
" <td>105</td>\n",
" <td>class_text</td>\n",
" <td>Iris-virginica</td>\n",
" <td>0.9310901</td>\n",
" </tr>\n",
" <tr>\n",
" <td>107</td>\n",
" <td>class_text</td>\n",
" <td>Iris-virginica</td>\n",
" <td>0.9202143</td>\n",
" </tr>\n",
" <tr>\n",
" <td>110</td>\n",
" <td>class_text</td>\n",
" <td>Iris-virginica</td>\n",
" <td>0.9461502</td>\n",
" </tr>\n",
" <tr>\n",
" <td>120</td>\n",
" <td>class_text</td>\n",
" <td>Iris-versicolor</td>\n",
" <td>0.53245807</td>\n",
" </tr>\n",
" <tr>\n",
" <td>130</td>\n",
" <td>class_text</td>\n",
" <td>Iris-versicolor</td>\n",
" <td>0.5506391</td>\n",
" </tr>\n",
" <tr>\n",
" <td>136</td>\n",
" <td>class_text</td>\n",
" <td>Iris-virginica</td>\n",
" <td>0.58871216</td>\n",
" </tr>\n",
" <tr>\n",
" <td>139</td>\n",
" <td>class_text</td>\n",
" <td>Iris-virginica</td>\n",
" <td>0.76892227</td>\n",
" </tr>\n",
" <tr>\n",
" <td>145</td>\n",
" <td>class_text</td>\n",
" <td>Iris-virginica</td>\n",
" <td>0.94731</td>\n",
" </tr>\n",
" <tr>\n",
" <td>146</td>\n",
" <td>class_text</td>\n",
" <td>Iris-virginica</td>\n",
" <td>0.7525016</td>\n",
" </tr>\n",
" <tr>\n",
" <td>147</td>\n",
" <td>class_text</td>\n",
" <td>Iris-virginica</td>\n",
" <td>0.5657851</td>\n",
" </tr>\n",
"</table>"
],
"text/plain": [
"[(1, u'class_text', u'Iris-setosa', 0.77083427),\n",
" (2, u'class_text', u'Iris-setosa', 0.76736474),\n",
" (3, u'class_text', u'Iris-setosa', 0.7637215),\n",
" (4, u'class_text', u'Iris-setosa', 0.76102996),\n",
" (6, u'class_text', u'Iris-setosa', 0.7710857),\n",
" (7, u'class_text', u'Iris-setosa', 0.7592268),\n",
" (8, u'class_text', u'Iris-setosa', 0.7686342),\n",
" (10, u'class_text', u'Iris-setosa', 0.76880336),\n",
" (18, u'class_text', u'Iris-setosa', 0.7689748),\n",
" (19, u'class_text', u'Iris-setosa', 0.77831817),\n",
" (28, u'class_text', u'Iris-setosa', 0.7722787),\n",
" (47, u'class_text', u'Iris-setosa', 0.76963973),\n",
" (50, u'class_text', u'Iris-setosa', 0.7690843),\n",
" (60, u'class_text', u'Iris-virginica', 0.5698719),\n",
" (65, u'class_text', u'Iris-versicolor', 0.71937233),\n",
" (69, u'class_text', u'Iris-versicolor', 0.7692964),\n",
" (75, u'class_text', u'Iris-versicolor', 0.8146459),\n",
" (79, u'class_text', u'Iris-versicolor', 0.5106894),\n",
" (80, u'class_text', u'Iris-versicolor', 0.7508131),\n",
" (82, u'class_text', u'Iris-versicolor', 0.77062976),\n",
" (105, u'class_text', u'Iris-virginica', 0.9310901),\n",
" (107, u'class_text', u'Iris-virginica', 0.9202143),\n",
" (110, u'class_text', u'Iris-virginica', 0.9461502),\n",
" (120, u'class_text', u'Iris-versicolor', 0.53245807),\n",
" (130, u'class_text', u'Iris-versicolor', 0.5506391),\n",
" (136, u'class_text', u'Iris-virginica', 0.58871216),\n",
" (139, u'class_text', u'Iris-virginica', 0.76892227),\n",
" (145, u'class_text', u'Iris-virginica', 0.94731),\n",
" (146, u'class_text', u'Iris-virginica', 0.7525016),\n",
" (147, u'class_text', u'Iris-virginica', 0.5657851)]"
]
},
"execution_count": 28,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"%%sql\n",
"DROP TABLE IF EXISTS iris_predict;\n",
"\n",
"SELECT madlib.madlib_keras_predict('automl_output', -- model\n",
" 'iris_test', -- test_table\n",
" 'id', -- id column\n",
" 'attributes', -- independent var\n",
" 'iris_predict', -- output table\n",
" 'response', -- prediction type\n",
" FALSE, -- use gpus\n",
" 13 -- MST key\n",
" );\n",
"\n",
"SELECT * FROM iris_predict ORDER BY id;"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Count missclassifications"
]
},
{
"cell_type": "code",
"execution_count": 31,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"1 rows affected.\n"
]
},
{
"data": {
"text/html": [
"<table>\n",
" <tr>\n",
" <th>count</th>\n",
" </tr>\n",
" <tr>\n",
" <td>3</td>\n",
" </tr>\n",
"</table>"
],
"text/plain": [
"[(3L,)]"
]
},
"execution_count": 31,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"%%sql\n",
"SELECT COUNT(*) FROM iris_predict JOIN iris_test USING (id) \n",
"WHERE iris_predict.class_value != iris_test.class_text;"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Percent missclassifications"
]
},
{
"cell_type": "code",
"execution_count": 32,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"1 rows affected.\n"
]
},
{
"data": {
"text/html": [
"<table>\n",
" <tr>\n",
" <th>test_accuracy_percent</th>\n",
" </tr>\n",
" <tr>\n",
" <td>90.00</td>\n",
" </tr>\n",
"</table>"
],
"text/plain": [
"[(Decimal('90.00'),)]"
]
},
"execution_count": 32,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"%%sql\n",
"SELECT round(count(*)*100/(150*0.2),2) as test_accuracy_percent from\n",
" (select iris_test.class_text as actual, iris_predict.class_value as estimated\n",
" from iris_predict inner join iris_test\n",
" on iris_test.id=iris_predict.id) q\n",
"WHERE q.actual=q.estimated;"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 2",
"language": "python",
"name": "python2"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 2
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython2",
"version": "2.7.16"
}
},
"nbformat": 4,
"nbformat_minor": 1
}