Google Git
Sign in
apache / madlib-site / 388c4b34a08c96e059baca60f17350db327491ca / . / community-artifacts / Deep-learning / MADlib-Keras-MLP-v1.ipynb
blob: aa610654db32afad041f21a568297a05ef5ed46c [file] [log] [blame]
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Multilayer Perceptron Using Keras and MADlib\n",
"\n",
"E2E classification example using MADlib calling a Keras MLP.\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 with images 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=\"#class\">Classification</a>\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=\"#train\">4. Train</a>\n",
"\n",
"* <a href=\"#eval\">5. Evaluate</a>\n",
"\n",
"* <a href=\"#pred\">6. Predict</a>\n",
"\n",
"<a href=\"#class2\">Classification with Other Parameters</a>\n",
"\n",
"* <a href=\"#val_dataset\">1. Validation dataset</a>\n",
"\n",
"* <a href=\"#pred_prob\">2. Predict probabilities</a>\n",
"\n",
"* <a href=\"#warm_start\">3. Warm start</a>\n",
"\n",
"<a href=\"#transfer_learn\">Transfer learning</a>\n",
"\n",
"* <a href=\"#load2\">1. Define and load model architecture with some layers frozen</a>\n",
"\n",
"* <a href=\"#train2\">2. Train transfer model</a>"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"scrolled": false
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/Users/fmcquillan/anaconda/lib/python2.7/site-packages/IPython/config.py:13: ShimWarning: The `IPython.config` package has been deprecated since IPython 4.0. You should import from traitlets.config instead.\n",
" \"You should import from traitlets.config instead.\", ShimWarning)\n",
"/Users/fmcquillan/anaconda/lib/python2.7/site-packages/IPython/utils/traitlets.py:5: UserWarning: IPython.utils.traitlets has moved to a top-level traitlets package.\n",
" warn(\"IPython.utils.traitlets has moved to a top-level traitlets package.\")\n"
]
}
],
"source": [
"%load_ext sql"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"u'Connected: fmcquillan@madlib'"
]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Greenplum Database 5.x on GCP (PM demo machine)\n",
"#%sql postgresql://gpadmin@35.184.232.200:5432/madlib\n",
" \n",
"# Greenplum Database 5.x on GCP for deep learning (PM demo machine)\n",
"#%sql postgresql://gpadmin@35.239.240.26:5432/madlib\n",
" \n",
"# PostgreSQL local\n",
"%sql postgresql://fmcquillan@localhost:5432/madlib"
]
},
{
"cell_type": "code",
"execution_count": 30,
"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>PostgreSQL 11.4 on x86_64-apple-darwin16.7.0, compiled by gcc (Homebrew gcc 5.2.0) 5.2.0, 64-bit</td>\n",
" </tr>\n",
"</table>"
],
"text/plain": [
"[(u'PostgreSQL 11.4 on x86_64-apple-darwin16.7.0, compiled by gcc (Homebrew gcc 5.2.0) 5.2.0, 64-bit',)]"
]
},
"execution_count": 30,
"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",
"1 rows affected.\n"
]
},
{
"data": {
"text/html": [
"<table>\n",
" <tr>\n",
" <th>independent_var</th>\n",
" <th>dependent_var</th>\n",
" <th>buffer_id</th>\n",
" </tr>\n",
" <tr>\n",
" <td>[[5.3, 3.7, 1.5, 0.2], [6.3, 3.4, 5.6, 2.4], [7.2, 3.2, 6.0, 1.8], [5.7, 4.4, 1.5, 0.4], [5.4, 3.7, 1.5, 0.2], [5.0, 3.0, 1.6, 0.2], [4.7, 3.2, 1.3, 0.2], [5.0, 2.3, 3.3, 1.0], [5.7, 2.8, 4.5, 1.3], [4.8, 3.0, 1.4, 0.1], [5.7, 3.8, 1.7, 0.3], [5.5, 4.2, 1.4, 0.2], [7.7, 3.8, 6.7, 2.2], [6.0, 2.2, 5.0, 1.5], [6.5, 3.0, 5.2, 2.0], [4.6, 3.6, 1.0, 0.2], [6.9, 3.1, 4.9, 1.5], [5.1, 3.8, 1.9, 0.4], [6.7, 2.5, 5.8, 1.8], [6.0, 2.7, 5.1, 1.6], [6.3, 3.3, 4.7, 1.6], [6.7, 3.1, 4.7, 1.5], [6.1, 3.0, 4.9, 1.8], [5.6, 2.9, 3.6, 1.3], [4.9, 3.1, 1.5, 0.1], [5.7, 2.6, 3.5, 1.0], [5.6, 2.8, 4.9, 2.0], [5.2, 2.7, 3.9, 1.4], [6.1, 2.8, 4.0, 1.3], [5.0, 3.2, 1.2, 0.2], [7.1, 3.0, 5.9, 2.1], [5.8, 2.7, 5.1, 1.9], [6.7, 3.0, 5.0, 1.7], [5.7, 2.9, 4.2, 1.3], [6.4, 2.9, 4.3, 1.3], [5.6, 3.0, 4.1, 1.3], [7.4, 2.8, 6.1, 1.9], [6.3, 2.7, 4.9, 1.8], [4.6, 3.4, 1.4, 0.3], [7.7, 2.6, 6.9, 2.3], [4.9, 3.1, 1.5, 0.1], [5.2, 3.5, 1.5, 0.2], [7.7, 2.8, 6.7, 2.0], [4.8, 3.0, 1.4, 0.3], [6.3, 2.5, 4.9, 1.5], [5.7, 2.5, 5.0, 2.0], [5.8, 4.0, 1.2, 0.2], [5.2, 3.4, 1.4, 0.2], [5.8, 2.7, 4.1, 1.0], [4.5, 2.3, 1.3, 0.3], [6.2, 2.9, 4.3, 1.3], [7.9, 3.8, 6.4, 2.0], [5.0, 3.4, 1.6, 0.4], [5.6, 2.5, 3.9, 1.1], [5.5, 2.4, 3.7, 1.0], [5.1, 3.7, 1.5, 0.4], [5.9, 3.0, 4.2, 1.5], [5.0, 3.4, 1.5, 0.2], [4.6, 3.2, 1.4, 0.2], [5.5, 2.5, 4.0, 1.3], [5.1, 3.5, 1.4, 0.3], [4.8, 3.1, 1.6, 0.2], [5.4, 3.9, 1.7, 0.4], [5.5, 3.5, 1.3, 0.2], [7.6, 3.0, 6.6, 2.1], [5.0, 3.5, 1.3, 0.3], [5.7, 3.0, 4.2, 1.2], [4.9, 2.4, 3.3, 1.0], [6.3, 2.5, 5.0, 1.9], [6.7, 3.1, 5.6, 2.4], [6.4, 3.1, 5.5, 1.8], [6.8, 2.8, 4.8, 1.4], [5.1, 3.8, 1.6, 0.2], [6.4, 2.7, 5.3, 1.9], [6.1, 2.9, 4.7, 1.4], [6.4, 2.8, 5.6, 2.2], [5.5, 2.6, 4.4, 1.2], [4.9, 3.1, 1.5, 0.1], [6.0, 3.0, 4.8, 1.8], [6.7, 3.1, 4.4, 1.4], [6.2, 2.8, 4.8, 1.8], [4.8, 3.4, 1.6, 0.2], [5.4, 3.4, 1.7, 0.2], [7.2, 3.0, 5.8, 1.6], [6.2, 3.4, 5.4, 2.3], [4.4, 2.9, 1.4, 0.2], [4.9, 3.0, 1.4, 0.2], [5.8, 2.8, 5.1, 2.4], [6.7, 3.3, 5.7, 2.5], [6.9, 3.1, 5.1, 2.3], [7.3, 2.9, 6.3, 1.8], [6.8, 3.2, 5.9, 2.3], [5.4, 3.4, 1.5, 0.4], [5.2, 4.1, 1.5, 0.1], [7.2, 3.6, 6.1, 2.5], [6.5, 3.0, 5.8, 2.2], [6.0, 2.2, 4.0, 1.0], [6.4, 3.2, 5.3, 2.3], [6.2, 2.2, 4.5, 1.5], [6.9, 3.2, 5.7, 2.3], [6.7, 3.0, 5.2, 2.3], [6.1, 2.8, 4.7, 1.2], [5.4, 3.0, 4.5, 1.5], [4.8, 3.4, 1.9, 0.2], [6.7, 3.3, 5.7, 2.1], [5.1, 2.5, 3.0, 1.1], [6.0, 2.9, 4.5, 1.5], [5.1, 3.8, 1.5, 0.3], [6.3, 3.3, 6.0, 2.5], [6.8, 3.0, 5.5, 2.1], [6.1, 2.6, 5.6, 1.4], [5.0, 3.5, 1.6, 0.6], [4.3, 3.0, 1.1, 0.1], [5.1, 3.5, 1.4, 0.2], [6.4, 2.8, 5.6, 2.1], [7.0, 3.2, 4.7, 1.4], [5.6, 3.0, 4.5, 1.5], [5.0, 3.6, 1.4, 0.2], [7.7, 3.0, 6.1, 2.3], [5.9, 3.2, 4.8, 1.8]]</td>\n",
" <td>[[1, 0, 0], [0, 0, 1], [0, 0, 1], [1, 0, 0], [1, 0, 0], [1, 0, 0], [1, 0, 0], [0, 1, 0], [0, 1, 0], [1, 0, 0], [1, 0, 0], [1, 0, 0], [0, 0, 1], [0, 0, 1], [0, 0, 1], [1, 0, 0], [0, 1, 0], [1, 0, 0], [0, 0, 1], [0, 1, 0], [0, 1, 0], [0, 1, 0], [0, 0, 1], [0, 1, 0], [1, 0, 0], [0, 1, 0], [0, 0, 1], [0, 1, 0], [0, 1, 0], [1, 0, 0], [0, 0, 1], [0, 0, 1], [0, 1, 0], [0, 1, 0], [0, 1, 0], [0, 1, 0], [0, 0, 1], [0, 0, 1], [1, 0, 0], [0, 0, 1], [1, 0, 0], [1, 0, 0], [0, 0, 1], [1, 0, 0], [0, 1, 0], [0, 0, 1], [1, 0, 0], [1, 0, 0], [0, 1, 0], [1, 0, 0], [0, 1, 0], [0, 0, 1], [1, 0, 0], [0, 1, 0], [0, 1, 0], [1, 0, 0], [0, 1, 0], [1, 0, 0], [1, 0, 0], [0, 1, 0], [1, 0, 0], [1, 0, 0], [1, 0, 0], [1, 0, 0], [0, 0, 1], [1, 0, 0], [0, 1, 0], [0, 1, 0], [0, 0, 1], [0, 0, 1], [0, 0, 1], [0, 1, 0], [1, 0, 0], [0, 0, 1], [0, 1, 0], [0, 0, 1], [0, 1, 0], [1, 0, 0], [0, 0, 1], [0, 1, 0], [0, 0, 1], [1, 0, 0], [1, 0, 0], [0, 0, 1], [0, 0, 1], [1, 0, 0], [1, 0, 0], [0, 0, 1], [0, 0, 1], [0, 0, 1], [0, 0, 1], [0, 0, 1], [1, 0, 0], [1, 0, 0], [0, 0, 1], [0, 0, 1], [0, 1, 0], [0, 0, 1], [0, 1, 0], [0, 0, 1], [0, 0, 1], [0, 1, 0], [0, 1, 0], [1, 0, 0], [0, 0, 1], [0, 1, 0], [0, 1, 0], [1, 0, 0], [0, 0, 1], [0, 0, 1], [0, 0, 1], [1, 0, 0], [1, 0, 0], [1, 0, 0], [0, 0, 1], [0, 1, 0], [0, 1, 0], [1, 0, 0], [0, 0, 1], [0, 1, 0]]</td>\n",
" <td>0</td>\n",
" </tr>\n",
"</table>"
],
"text/plain": [
"[([[5.3, 3.7, 1.5, 0.2], [6.3, 3.4, 5.6, 2.4], [7.2, 3.2, 6.0, 1.8], [5.7, 4.4, 1.5, 0.4], [5.4, 3.7, 1.5, 0.2], [5.0, 3.0, 1.6, 0.2], [4.7, 3.2, 1.3, 0.2], [5.0, 2.3, 3.3, 1.0], [5.7, 2.8, 4.5, 1.3], [4.8, 3.0, 1.4, 0.1], [5.7, 3.8, 1.7, 0.3], [5.5, 4.2, 1.4, 0.2], [7.7, 3.8, 6.7, 2.2], [6.0, 2.2, 5.0, 1.5], [6.5, 3.0, 5.2, 2.0], [4.6, 3.6, 1.0, 0.2], [6.9, 3.1, 4.9, 1.5], [5.1, 3.8, 1.9, 0.4], [6.7, 2.5, 5.8, 1.8], [6.0, 2.7, 5.1, 1.6], [6.3, 3.3, 4.7, 1.6], [6.7, 3.1, 4.7, 1.5], [6.1, 3.0, 4.9, 1.8], [5.6, 2.9, 3.6, 1.3], [4.9, 3.1, 1.5, 0.1], [5.7, 2.6, 3.5, 1.0], [5.6, 2.8, 4.9, 2.0], [5.2, 2.7, 3.9, 1.4], [6.1, 2.8, 4.0, 1.3], [5.0, 3.2, 1.2, 0.2], [7.1, 3.0, 5.9, 2.1], [5.8, 2.7, 5.1, 1.9], [6.7, 3.0, 5.0, 1.7], [5.7, 2.9, 4.2, 1.3], [6.4, 2.9, 4.3, 1.3], [5.6, 3.0, 4.1, 1.3], [7.4, 2.8, 6.1, 1.9], [6.3, 2.7, 4.9, 1.8], [4.6, 3.4, 1.4, 0.3], [7.7, 2.6, 6.9, 2.3], [4.9, 3.1, 1.5, 0.1], [5.2, 3.5, 1.5, 0.2], [7.7, 2.8, 6.7, 2.0], [4.8, 3.0, 1.4, 0.3], [6.3, 2.5, 4.9, 1.5], [5.7, 2.5, 5.0, 2.0], [5.8, 4.0, 1.2, 0.2], [5.2, 3.4, 1.4, 0.2], [5.8, 2.7, 4.1, 1.0], [4.5, 2.3, 1.3, 0.3], [6.2, 2.9, 4.3, 1.3], [7.9, 3.8, 6.4, 2.0], [5.0, 3.4, 1.6, 0.4], [5.6, 2.5, 3.9, 1.1], [5.5, 2.4, 3.7, 1.0], [5.1, 3.7, 1.5, 0.4], [5.9, 3.0, 4.2, 1.5], [5.0, 3.4, 1.5, 0.2], [4.6, 3.2, 1.4, 0.2], [5.5, 2.5, 4.0, 1.3], [5.1, 3.5, 1.4, 0.3], [4.8, 3.1, 1.6, 0.2], [5.4, 3.9, 1.7, 0.4], [5.5, 3.5, 1.3, 0.2], [7.6, 3.0, 6.6, 2.1], [5.0, 3.5, 1.3, 0.3], [5.7, 3.0, 4.2, 1.2], [4.9, 2.4, 3.3, 1.0], [6.3, 2.5, 5.0, 1.9], [6.7, 3.1, 5.6, 2.4], [6.4, 3.1, 5.5, 1.8], [6.8, 2.8, 4.8, 1.4], [5.1, 3.8, 1.6, 0.2], [6.4, 2.7, 5.3, 1.9], [6.1, 2.9, 4.7, 1.4], [6.4, 2.8, 5.6, 2.2], [5.5, 2.6, 4.4, 1.2], [4.9, 3.1, 1.5, 0.1], [6.0, 3.0, 4.8, 1.8], [6.7, 3.1, 4.4, 1.4], [6.2, 2.8, 4.8, 1.8], [4.8, 3.4, 1.6, 0.2], [5.4, 3.4, 1.7, 0.2], [7.2, 3.0, 5.8, 1.6], [6.2, 3.4, 5.4, 2.3], [4.4, 2.9, 1.4, 0.2], [4.9, 3.0, 1.4, 0.2], [5.8, 2.8, 5.1, 2.4], [6.7, 3.3, 5.7, 2.5], [6.9, 3.1, 5.1, 2.3], [7.3, 2.9, 6.3, 1.8], [6.8, 3.2, 5.9, 2.3], [5.4, 3.4, 1.5, 0.4], [5.2, 4.1, 1.5, 0.1], [7.2, 3.6, 6.1, 2.5], [6.5, 3.0, 5.8, 2.2], [6.0, 2.2, 4.0, 1.0], [6.4, 3.2, 5.3, 2.3], [6.2, 2.2, 4.5, 1.5], [6.9, 3.2, 5.7, 2.3], [6.7, 3.0, 5.2, 2.3], [6.1, 2.8, 4.7, 1.2], [5.4, 3.0, 4.5, 1.5], [4.8, 3.4, 1.9, 0.2], [6.7, 3.3, 5.7, 2.1], [5.1, 2.5, 3.0, 1.1], [6.0, 2.9, 4.5, 1.5], [5.1, 3.8, 1.5, 0.3], [6.3, 3.3, 6.0, 2.5], [6.8, 3.0, 5.5, 2.1], [6.1, 2.6, 5.6, 1.4], [5.0, 3.5, 1.6, 0.6], [4.3, 3.0, 1.1, 0.1], [5.1, 3.5, 1.4, 0.2], [6.4, 2.8, 5.6, 2.1], [7.0, 3.2, 4.7, 1.4], [5.6, 3.0, 4.5, 1.5], [5.0, 3.6, 1.4, 0.2], [7.7, 3.0, 6.1, 2.3], [5.9, 3.2, 4.8, 1.8]], [[1, 0, 0], [0, 0, 1], [0, 0, 1], [1, 0, 0], [1, 0, 0], [1, 0, 0], [1, 0, 0], [0, 1, 0], [0, 1, 0], [1, 0, 0], [1, 0, 0], [1, 0, 0], [0, 0, 1], [0, 0, 1], [0, 0, 1], [1, 0, 0], [0, 1, 0], [1, 0, 0], [0, 0, 1], [0, 1, 0], [0, 1, 0], [0, 1, 0], [0, 0, 1], [0, 1, 0], [1, 0, 0], [0, 1, 0], [0, 0, 1], [0, 1, 0], [0, 1, 0], [1, 0, 0], [0, 0, 1], [0, 0, 1], [0, 1, 0], [0, 1, 0], [0, 1, 0], [0, 1, 0], [0, 0, 1], [0, 0, 1], [1, 0, 0], [0, 0, 1], [1, 0, 0], [1, 0, 0], [0, 0, 1], [1, 0, 0], [0, 1, 0], [0, 0, 1], [1, 0, 0], [1, 0, 0], [0, 1, 0], [1, 0, 0], [0, 1, 0], [0, 0, 1], [1, 0, 0], [0, 1, 0], [0, 1, 0], [1, 0, 0], [0, 1, 0], [1, 0, 0], [1, 0, 0], [0, 1, 0], [1, 0, 0], [1, 0, 0], [1, 0, 0], [1, 0, 0], [0, 0, 1], [1, 0, 0], [0, 1, 0], [0, 1, 0], [0, 0, 1], [0, 0, 1], [0, 0, 1], [0, 1, 0], [1, 0, 0], [0, 0, 1], [0, 1, 0], [0, 0, 1], [0, 1, 0], [1, 0, 0], [0, 0, 1], [0, 1, 0], [0, 0, 1], [1, 0, 0], [1, 0, 0], [0, 0, 1], [0, 0, 1], [1, 0, 0], [1, 0, 0], [0, 0, 1], [0, 0, 1], [0, 0, 1], [0, 0, 1], [0, 0, 1], [1, 0, 0], [1, 0, 0], [0, 0, 1], [0, 0, 1], [0, 1, 0], [0, 0, 1], [0, 1, 0], [0, 0, 1], [0, 0, 1], [0, 1, 0], [0, 1, 0], [1, 0, 0], [0, 0, 1], [0, 1, 0], [0, 1, 0], [1, 0, 0], [0, 0, 1], [0, 0, 1], [0, 0, 1], [1, 0, 0], [1, 0, 0], [1, 0, 0], [0, 0, 1], [0, 1, 0], [0, 1, 0], [1, 0, 0], [0, 0, 1], [0, 1, 0]], 0)]"
]
},
"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 * 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_values</th>\n",
" <th>buffer_size</th>\n",
" <th>normalizing_const</th>\n",
" <th>num_classes</th>\n",
" </tr>\n",
" <tr>\n",
" <td>iris_train</td>\n",
" <td>iris_train_packed</td>\n",
" <td>class_text</td>\n",
" <td>attributes</td>\n",
" <td>character varying</td>\n",
" <td>[u'Iris-setosa', u'Iris-versicolor', u'Iris-virginica']</td>\n",
" <td>120</td>\n",
" <td>1.0</td>\n",
" <td>3</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'], 120, 1.0, 3)]"
]
},
"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",
"1 rows affected.\n"
]
},
{
"data": {
"text/html": [
"<table>\n",
" <tr>\n",
" <th>independent_var</th>\n",
" <th>dependent_var</th>\n",
" <th>buffer_id</th>\n",
" </tr>\n",
" <tr>\n",
" <td>[[5.1, 3.4, 1.5, 0.2], [5.7, 2.8, 4.1, 1.3], [6.6, 3.0, 4.4, 1.4], [5.4, 3.9, 1.3, 0.4], [5.6, 2.7, 4.2, 1.3], [6.9, 3.1, 5.4, 2.1], [6.5, 3.0, 5.5, 1.8], [6.1, 3.0, 4.6, 1.4], [4.4, 3.2, 1.3, 0.2], [4.9, 2.5, 4.5, 1.7], [6.5, 2.8, 4.6, 1.5], [4.6, 3.1, 1.5, 0.2], [6.3, 2.3, 4.4, 1.3], [5.0, 3.3, 1.4, 0.2], [6.3, 2.9, 5.6, 1.8], [6.5, 3.2, 5.1, 2.0], [6.3, 2.8, 5.1, 1.5], [5.8, 2.7, 5.1, 1.9], [5.8, 2.7, 3.9, 1.2], [6.4, 3.2, 4.5, 1.5], [6.0, 3.4, 4.5, 1.6], [5.1, 3.3, 1.7, 0.5], [5.0, 2.0, 3.5, 1.0], [5.5, 2.4, 3.8, 1.1], [4.4, 3.0, 1.3, 0.2], [5.5, 2.3, 4.0, 1.3], [5.9, 3.0, 5.1, 1.8], [6.6, 2.9, 4.6, 1.3], [5.8, 2.6, 4.0, 1.2], [4.7, 3.2, 1.6, 0.2]]</td>\n",
" <td>[[1, 0, 0], [0, 1, 0], [0, 1, 0], [1, 0, 0], [0, 1, 0], [0, 0, 1], [0, 0, 1], [0, 1, 0], [1, 0, 0], [0, 0, 1], [0, 1, 0], [1, 0, 0], [0, 1, 0], [1, 0, 0], [0, 0, 1], [0, 0, 1], [0, 0, 1], [0, 0, 1], [0, 1, 0], [0, 1, 0], [0, 1, 0], [1, 0, 0], [0, 1, 0], [0, 1, 0], [1, 0, 0], [0, 1, 0], [0, 0, 1], [0, 1, 0], [0, 1, 0], [1, 0, 0]]</td>\n",
" <td>0</td>\n",
" </tr>\n",
"</table>"
],
"text/plain": [
"[([[5.1, 3.4, 1.5, 0.2], [5.7, 2.8, 4.1, 1.3], [6.6, 3.0, 4.4, 1.4], [5.4, 3.9, 1.3, 0.4], [5.6, 2.7, 4.2, 1.3], [6.9, 3.1, 5.4, 2.1], [6.5, 3.0, 5.5, 1.8], [6.1, 3.0, 4.6, 1.4], [4.4, 3.2, 1.3, 0.2], [4.9, 2.5, 4.5, 1.7], [6.5, 2.8, 4.6, 1.5], [4.6, 3.1, 1.5, 0.2], [6.3, 2.3, 4.4, 1.3], [5.0, 3.3, 1.4, 0.2], [6.3, 2.9, 5.6, 1.8], [6.5, 3.2, 5.1, 2.0], [6.3, 2.8, 5.1, 1.5], [5.8, 2.7, 5.1, 1.9], [5.8, 2.7, 3.9, 1.2], [6.4, 3.2, 4.5, 1.5], [6.0, 3.4, 4.5, 1.6], [5.1, 3.3, 1.7, 0.5], [5.0, 2.0, 3.5, 1.0], [5.5, 2.4, 3.8, 1.1], [4.4, 3.0, 1.3, 0.2], [5.5, 2.3, 4.0, 1.3], [5.9, 3.0, 5.1, 1.8], [6.6, 2.9, 4.6, 1.3], [5.8, 2.6, 4.0, 1.2], [4.7, 3.2, 1.6, 0.2]], [[1, 0, 0], [0, 1, 0], [0, 1, 0], [1, 0, 0], [0, 1, 0], [0, 0, 1], [0, 0, 1], [0, 1, 0], [1, 0, 0], [0, 0, 1], [0, 1, 0], [1, 0, 0], [0, 1, 0], [1, 0, 0], [0, 0, 1], [0, 0, 1], [0, 0, 1], [0, 0, 1], [0, 1, 0], [0, 1, 0], [0, 1, 0], [1, 0, 0], [0, 1, 0], [0, 1, 0], [1, 0, 0], [0, 1, 0], [0, 0, 1], [0, 1, 0], [0, 1, 0], [1, 0, 0]], 0)]"
]
},
"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 * 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_values</th>\n",
" <th>buffer_size</th>\n",
" <th>normalizing_const</th>\n",
" <th>num_classes</th>\n",
" </tr>\n",
" <tr>\n",
" <td>iris_test</td>\n",
" <td>iris_test_packed</td>\n",
" <td>class_text</td>\n",
" <td>attributes</td>\n",
" <td>character varying</td>\n",
" <td>[u'Iris-setosa', u'Iris-versicolor', u'Iris-virginica']</td>\n",
" <td>30</td>\n",
" <td>1.0</td>\n",
" <td>3</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'], 30, 1.0, 3)]"
]
},
"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": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Using TensorFlow backend.\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Couldn't import dot_parser, loading of dot files will not be possible.\n"
]
}
],
"source": [
"import keras\n",
"from keras.models import Sequential\n",
"from keras.layers import Dense"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Define model architecture"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"_________________________________________________________________\n",
"Layer (type) Output Shape Param # \n",
"=================================================================\n",
"dense_1 (Dense) (None, 10) 50 \n",
"_________________________________________________________________\n",
"dense_2 (Dense) (None, 10) 110 \n",
"_________________________________________________________________\n",
"dense_3 (Dense) (None, 3) 33 \n",
"=================================================================\n",
"Total params: 193\n",
"Trainable params: 193\n",
"Non-trainable params: 0\n",
"_________________________________________________________________\n"
]
}
],
"source": [
"model_simple = Sequential()\n",
"model_simple.add(Dense(10, activation='relu', input_shape=(4,)))\n",
"model_simple.add(Dense(10, activation='relu'))\n",
"model_simple.add(Dense(3, activation='softmax'))\n",
" \n",
"model_simple.summary()"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'{\"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\"}'"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"model_simple.to_json()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Load into model architecture table"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Done.\n",
"1 rows affected.\n",
"1 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>A simple model</td>\n",
" <td>__madlib_temp_62550369_1562173248_86696923__</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'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'}, None, u'Sophie', u'A simple model', u'__madlib_temp_62550369_1562173248_86696923__')]"
]
},
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"%%sql\n",
"DROP TABLE IF EXISTS model_arch_library;\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",
" 'A simple model' -- Descr\n",
");\n",
"\n",
"SELECT * FROM model_arch_library;"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"<a id=\"train\"></a>\n",
"# 4. Train\n",
"Train the model:"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Done.\n",
"1 rows affected.\n"
]
},
{
"data": {
"text/html": [
"<table>\n",
" <tr>\n",
" <th>madlib_keras_fit</th>\n",
" </tr>\n",
" <tr>\n",
" <td></td>\n",
" </tr>\n",
"</table>"
],
"text/plain": [
"[('',)]"
]
},
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"%%sql\n",
"DROP TABLE IF EXISTS iris_model, iris_model_summary;\n",
"\n",
"SELECT madlib.madlib_keras_fit('iris_train_packed', -- source table\n",
" 'iris_model', -- model output table\n",
" 'model_arch_library', -- model arch table\n",
" 1, -- model arch id\n",
" $$ loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'] $$, -- compile_params\n",
" $$ batch_size=5, epochs=3 $$, -- fit_params\n",
" 10 -- num_iterations\n",
" );"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"View the model summary:"
]
},
{
"cell_type": "code",
"execution_count": 14,
"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>model</th>\n",
" <th>dependent_varname</th>\n",
" <th>independent_varname</th>\n",
" <th>model_arch_table</th>\n",
" <th>model_arch_id</th>\n",
" <th>compile_params</th>\n",
" <th>fit_params</th>\n",
" <th>num_iterations</th>\n",
" <th>validation_table</th>\n",
" <th>metrics_compute_frequency</th>\n",
" <th>name</th>\n",
" <th>description</th>\n",
" <th>model_type</th>\n",
" <th>model_size</th>\n",
" <th>start_training_time</th>\n",
" <th>end_training_time</th>\n",
" <th>metrics_elapsed_time</th>\n",
" <th>madlib_version</th>\n",
" <th>num_classes</th>\n",
" <th>class_values</th>\n",
" <th>dependent_vartype</th>\n",
" <th>normalizing_const</th>\n",
" <th>metrics_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>iris_train_packed</td>\n",
" <td>iris_model</td>\n",
" <td>class_text</td>\n",
" <td>attributes</td>\n",
" <td>model_arch_library</td>\n",
" <td>1</td>\n",
" <td> loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'] </td>\n",
" <td> batch_size=5, epochs=3 </td>\n",
" <td>10</td>\n",
" <td>None</td>\n",
" <td>10</td>\n",
" <td>None</td>\n",
" <td>None</td>\n",
" <td>madlib_keras</td>\n",
" <td>0.7900390625</td>\n",
" <td>2019-07-03 10:00:52.477704</td>\n",
" <td>2019-07-03 10:00:58.552077</td>\n",
" <td>[6.07431507110596]</td>\n",
" <td>1.16</td>\n",
" <td>3</td>\n",
" <td>[u'Iris-setosa', u'Iris-versicolor', u'Iris-virginica']</td>\n",
" <td>character varying</td>\n",
" <td>1.0</td>\n",
" <td>[u'accuracy']</td>\n",
" <td>0.883333325386</td>\n",
" <td>0.347580313683</td>\n",
" <td>[0.883333325386047]</td>\n",
" <td>[0.347580313682556]</td>\n",
" <td>None</td>\n",
" <td>None</td>\n",
" <td>None</td>\n",
" <td>None</td>\n",
" <td>[10]</td>\n",
" </tr>\n",
"</table>"
],
"text/plain": [
"[(u'iris_train_packed', u'iris_model', u'class_text', u'attributes', u'model_arch_library', 1, u\" loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'] \", u' batch_size=5, epochs=3 ', 10, None, 10, None, None, u'madlib_keras', 0.7900390625, datetime.datetime(2019, 7, 3, 10, 0, 52, 477704), datetime.datetime(2019, 7, 3, 10, 0, 58, 552077), [6.07431507110596], u'1.16', 3, [u'Iris-setosa', u'Iris-versicolor', u'Iris-virginica'], u'character varying', 1.0, [u'accuracy'], 0.883333325386, 0.347580313683, [0.883333325386047], [0.347580313682556], None, None, None, None, [10])]"
]
},
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"%%sql\n",
"SELECT * FROM iris_model_summary;"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"<a id=\"eval\"></a>\n",
"# 5. Evaluate\n",
"\n",
"Now run evaluate using model we built above:"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Done.\n",
"1 rows affected.\n",
"1 rows affected.\n"
]
},
{
"data": {
"text/html": [
"<table>\n",
" <tr>\n",
" <th>loss</th>\n",
" <th>metric</th>\n",
" <th>metrics_type</th>\n",
" </tr>\n",
" <tr>\n",
" <td>0.43478807807</td>\n",
" <td>0.899999976158</td>\n",
" <td>[u'accuracy']</td>\n",
" </tr>\n",
"</table>"
],
"text/plain": [
"[(0.434788078069687, 0.899999976158142, [u'accuracy'])]"
]
},
"execution_count": 15,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"%%sql\n",
"DROP TABLE IF EXISTS iris_validate;\n",
"\n",
"SELECT madlib.madlib_keras_evaluate('iris_model', -- model\n",
" 'iris_test_packed', -- test table\n",
" 'iris_validate' -- output table\n",
" );\n",
"\n",
"SELECT * FROM iris_validate;"
]
},
{
"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. The prediction is in the estimated_class_text column:"
]
},
{
"cell_type": "code",
"execution_count": 16,
"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>estimated_class_text</th>\n",
" </tr>\n",
" <tr>\n",
" <td>4</td>\n",
" <td>Iris-setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <td>17</td>\n",
" <td>Iris-setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <td>24</td>\n",
" <td>Iris-setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <td>30</td>\n",
" <td>Iris-setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <td>39</td>\n",
" <td>Iris-setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <td>40</td>\n",
" <td>Iris-setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <td>43</td>\n",
" <td>Iris-setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <td>50</td>\n",
" <td>Iris-setosa</td>\n",
" </tr>\n",
" <tr>\n",
" <td>52</td>\n",
" <td>Iris-versicolor</td>\n",
" </tr>\n",
" <tr>\n",
" <td>54</td>\n",
" <td>Iris-virginica</td>\n",
" </tr>\n",
" <tr>\n",
" <td>55</td>\n",
" <td>Iris-virginica</td>\n",
" </tr>\n",
" <tr>\n",
" <td>59</td>\n",
" <td>Iris-versicolor</td>\n",
" </tr>\n",
" <tr>\n",
" <td>61</td>\n",
" <td>Iris-versicolor</td>\n",
" </tr>\n",
" <tr>\n",
" <td>76</td>\n",
" <td>Iris-versicolor</td>\n",
" </tr>\n",
" <tr>\n",
" <td>81</td>\n",
" <td>Iris-versicolor</td>\n",
" </tr>\n",
" <tr>\n",
" <td>83</td>\n",
" <td>Iris-versicolor</td>\n",
" </tr>\n",
" <tr>\n",
" <td>86</td>\n",
" <td>Iris-versicolor</td>\n",
" </tr>\n",
" <tr>\n",
" <td>88</td>\n",
" <td>Iris-virginica</td>\n",
" </tr>\n",
" <tr>\n",
" <td>92</td>\n",
" <td>Iris-versicolor</td>\n",
" </tr>\n",
" <tr>\n",
" <td>93</td>\n",
" <td>Iris-versicolor</td>\n",
" </tr>\n",
" <tr>\n",
" <td>95</td>\n",
" <td>Iris-versicolor</td>\n",
" </tr>\n",
" <tr>\n",
" <td>100</td>\n",
" <td>Iris-versicolor</td>\n",
" </tr>\n",
" <tr>\n",
" <td>104</td>\n",
" <td>Iris-virginica</td>\n",
" </tr>\n",
" <tr>\n",
" <td>107</td>\n",
" <td>Iris-virginica</td>\n",
" </tr>\n",
" <tr>\n",
" <td>111</td>\n",
" <td>Iris-virginica</td>\n",
" </tr>\n",
" <tr>\n",
" <td>117</td>\n",
" <td>Iris-virginica</td>\n",
" </tr>\n",
" <tr>\n",
" <td>134</td>\n",
" <td>Iris-virginica</td>\n",
" </tr>\n",
" <tr>\n",
" <td>140</td>\n",
" <td>Iris-virginica</td>\n",
" </tr>\n",
" <tr>\n",
" <td>143</td>\n",
" <td>Iris-virginica</td>\n",
" </tr>\n",
" <tr>\n",
" <td>150</td>\n",
" <td>Iris-virginica</td>\n",
" </tr>\n",
"</table>"
],
"text/plain": [
"[(4, u'Iris-setosa'),\n",
" (17, u'Iris-setosa'),\n",
" (24, u'Iris-setosa'),\n",
" (30, u'Iris-setosa'),\n",
" (39, u'Iris-setosa'),\n",
" (40, u'Iris-setosa'),\n",
" (43, u'Iris-setosa'),\n",
" (50, u'Iris-setosa'),\n",
" (52, u'Iris-versicolor'),\n",
" (54, u'Iris-virginica'),\n",
" (55, u'Iris-virginica'),\n",
" (59, u'Iris-versicolor'),\n",
" (61, u'Iris-versicolor'),\n",
" (76, u'Iris-versicolor'),\n",
" (81, u'Iris-versicolor'),\n",
" (83, u'Iris-versicolor'),\n",
" (86, u'Iris-versicolor'),\n",
" (88, u'Iris-virginica'),\n",
" (92, u'Iris-versicolor'),\n",
" (93, u'Iris-versicolor'),\n",
" (95, u'Iris-versicolor'),\n",
" (100, u'Iris-versicolor'),\n",
" (104, u'Iris-virginica'),\n",
" (107, u'Iris-virginica'),\n",
" (111, u'Iris-virginica'),\n",
" (117, u'Iris-virginica'),\n",
" (134, u'Iris-virginica'),\n",
" (140, u'Iris-virginica'),\n",
" (143, u'Iris-virginica'),\n",
" (150, u'Iris-virginica')]"
]
},
"execution_count": 16,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"%%sql\n",
"DROP TABLE IF EXISTS iris_predict;\n",
"\n",
"SELECT madlib.madlib_keras_predict('iris_model', -- model\n",
" 'iris_test', -- test_table\n",
" 'id', -- id column\n",
" 'attributes', -- independent var\n",
" 'iris_predict' -- output table\n",
" );\n",
"\n",
"SELECT * FROM iris_predict ORDER BY id;"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Count missclassifications"
]
},
{
"cell_type": "code",
"execution_count": 17,
"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": 17,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"%%sql\n",
"SELECT COUNT(*) FROM iris_predict JOIN iris_test USING (id) \n",
"WHERE iris_predict.estimated_class_text != iris_test.class_text;"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Percent missclassifications"
]
},
{
"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>test_accuracy_percent</th>\n",
" </tr>\n",
" <tr>\n",
" <td>90.00</td>\n",
" </tr>\n",
"</table>"
],
"text/plain": [
"[(Decimal('90.00'),)]"
]
},
"execution_count": 18,
"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.estimated_class_text 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;"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"<a id=\"class2\"></a>\n",
"# Classification with Other Parameters\n",
"\n",
"<a id=\"val_dataset\"></a>\n",
"# 1. Validation dataset\n",
"Now use a validation dataset and compute metrics every 5th iteration using the 'metrics_compute_frequency' parameter. This can help reduce run time if you do not need metrics computed at every iteration."
]
},
{
"cell_type": "code",
"execution_count": 19,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Done.\n",
"1 rows affected.\n"
]
},
{
"data": {
"text/html": [
"<table>\n",
" <tr>\n",
" <th>madlib_keras_fit</th>\n",
" </tr>\n",
" <tr>\n",
" <td></td>\n",
" </tr>\n",
"</table>"
],
"text/plain": [
"[('',)]"
]
},
"execution_count": 19,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"%%sql\n",
"DROP TABLE IF EXISTS iris_model, iris_model_summary;\n",
"\n",
"SELECT madlib.madlib_keras_fit('iris_train_packed', -- source table\n",
" 'iris_model', -- model output table\n",
" 'model_arch_library', -- model arch table\n",
" 1, -- model arch id\n",
" $$ loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'] $$, -- compile_params\n",
" $$ batch_size=5, epochs=3 $$, -- fit_params\n",
" 10, -- num_iterations\n",
" 0, -- GPUs per host\n",
" 'iris_test_packed', -- validation dataset\n",
" 3, -- metrics compute frequency\n",
" FALSE, -- warm start\n",
" 'Sophie L.', -- name\n",
" 'Simple MLP for iris dataset' -- description\n",
" );"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"View the model summary:"
]
},
{
"cell_type": "code",
"execution_count": 20,
"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>model</th>\n",
" <th>dependent_varname</th>\n",
" <th>independent_varname</th>\n",
" <th>model_arch_table</th>\n",
" <th>model_arch_id</th>\n",
" <th>compile_params</th>\n",
" <th>fit_params</th>\n",
" <th>num_iterations</th>\n",
" <th>validation_table</th>\n",
" <th>metrics_compute_frequency</th>\n",
" <th>name</th>\n",
" <th>description</th>\n",
" <th>model_type</th>\n",
" <th>model_size</th>\n",
" <th>start_training_time</th>\n",
" <th>end_training_time</th>\n",
" <th>metrics_elapsed_time</th>\n",
" <th>madlib_version</th>\n",
" <th>num_classes</th>\n",
" <th>class_values</th>\n",
" <th>dependent_vartype</th>\n",
" <th>normalizing_const</th>\n",
" <th>metrics_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>iris_train_packed</td>\n",
" <td>iris_model</td>\n",
" <td>class_text</td>\n",
" <td>attributes</td>\n",
" <td>model_arch_library</td>\n",
" <td>1</td>\n",
" <td> loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'] </td>\n",
" <td> batch_size=5, epochs=3 </td>\n",
" <td>10</td>\n",
" <td>iris_test_packed</td>\n",
" <td>3</td>\n",
" <td>Sophie L.</td>\n",
" <td>Simple MLP for iris dataset</td>\n",
" <td>madlib_keras</td>\n",
" <td>0.7900390625</td>\n",
" <td>2019-07-03 10:01:36.883439</td>\n",
" <td>2019-07-03 10:01:43.631505</td>\n",
" <td>[2.01867508888245, 3.89846897125244, 5.95652198791504, 6.74802613258362]</td>\n",
" <td>1.16</td>\n",
" <td>3</td>\n",
" <td>[u'Iris-setosa', u'Iris-versicolor', u'Iris-virginica']</td>\n",
" <td>character varying</td>\n",
" <td>1.0</td>\n",
" <td>[u'accuracy']</td>\n",
" <td>0.941666662693</td>\n",
" <td>0.371823817492</td>\n",
" <td>[0.741666674613953, 0.800000011920929, 0.916666686534882, 0.941666662693024]</td>\n",
" <td>[0.829422652721405, 0.578483581542969, 0.405027717351913, 0.371823817491531]</td>\n",
" <td>0.866666674614</td>\n",
" <td>0.492831081152</td>\n",
" <td>[0.566666662693024, 0.566666662693024, 0.833333313465118, 0.866666674613953]</td>\n",
" <td>[0.945741951465607, 0.735191941261292, 0.535544157028198, 0.492831081151962]</td>\n",
" <td>[3, 6, 9, 10]</td>\n",
" </tr>\n",
"</table>"
],
"text/plain": [
"[(u'iris_train_packed', u'iris_model', u'class_text', u'attributes', u'model_arch_library', 1, u\" loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'] \", u' batch_size=5, epochs=3 ', 10, u'iris_test_packed', 3, u'Sophie L.', u'Simple MLP for iris dataset', u'madlib_keras', 0.7900390625, datetime.datetime(2019, 7, 3, 10, 1, 36, 883439), datetime.datetime(2019, 7, 3, 10, 1, 43, 631505), [2.01867508888245, 3.89846897125244, 5.95652198791504, 6.74802613258362], u'1.16', 3, [u'Iris-setosa', u'Iris-versicolor', u'Iris-virginica'], u'character varying', 1.0, [u'accuracy'], 0.941666662693, 0.371823817492, [0.741666674613953, 0.800000011920929, 0.916666686534882, 0.941666662693024], [0.829422652721405, 0.578483581542969, 0.405027717351913, 0.371823817491531], 0.866666674614, 0.492831081152, [0.566666662693024, 0.566666662693024, 0.833333313465118, 0.866666674613953], [0.945741951465607, 0.735191941261292, 0.535544157028198, 0.492831081151962], [3, 6, 9, 10])]"
]
},
"execution_count": 20,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"%%sql\n",
"SELECT * FROM iris_model_summary;"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"<a id=\"pred_prob\"></a>\n",
"# 2. Predict probabilities\n",
"Predict with probabilities for each class:"
]
},
{
"cell_type": "code",
"execution_count": 21,
"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>prob_Iris-setosa</th>\n",
" <th>prob_Iris-versicolor</th>\n",
" <th>prob_Iris-virginica</th>\n",
" </tr>\n",
" <tr>\n",
" <td>4</td>\n",
" <td>0.89618546</td>\n",
" <td>0.10063652</td>\n",
" <td>0.0031779788</td>\n",
" </tr>\n",
" <tr>\n",
" <td>17</td>\n",
" <td>0.9432447</td>\n",
" <td>0.055964436</td>\n",
" <td>0.00079082645</td>\n",
" </tr>\n",
" <tr>\n",
" <td>24</td>\n",
" <td>0.87476385</td>\n",
" <td>0.121528275</td>\n",
" <td>0.0037078795</td>\n",
" </tr>\n",
" <tr>\n",
" <td>30</td>\n",
" <td>0.8998875</td>\n",
" <td>0.09730224</td>\n",
" <td>0.0028102635</td>\n",
" </tr>\n",
" <tr>\n",
" <td>39</td>\n",
" <td>0.89937997</td>\n",
" <td>0.09733549</td>\n",
" <td>0.003284483</td>\n",
" </tr>\n",
" <tr>\n",
" <td>40</td>\n",
" <td>0.9124368</td>\n",
" <td>0.08554972</td>\n",
" <td>0.0020134845</td>\n",
" </tr>\n",
" <tr>\n",
" <td>43</td>\n",
" <td>0.91849124</td>\n",
" <td>0.079369105</td>\n",
" <td>0.0021397525</td>\n",
" </tr>\n",
" <tr>\n",
" <td>50</td>\n",
" <td>0.909191</td>\n",
" <td>0.08853077</td>\n",
" <td>0.002278217</td>\n",
" </tr>\n",
" <tr>\n",
" <td>52</td>\n",
" <td>0.087838314</td>\n",
" <td>0.5821711</td>\n",
" <td>0.3299906</td>\n",
" </tr>\n",
" <tr>\n",
" <td>54</td>\n",
" <td>0.040643755</td>\n",
" <td>0.41653973</td>\n",
" <td>0.5428166</td>\n",
" </tr>\n",
" <tr>\n",
" <td>55</td>\n",
" <td>0.028924335</td>\n",
" <td>0.42645925</td>\n",
" <td>0.54461634</td>\n",
" </tr>\n",
" <tr>\n",
" <td>59</td>\n",
" <td>0.043529026</td>\n",
" <td>0.48816994</td>\n",
" <td>0.468301</td>\n",
" </tr>\n",
" <tr>\n",
" <td>61</td>\n",
" <td>0.06540182</td>\n",
" <td>0.44180837</td>\n",
" <td>0.4927898</td>\n",
" </tr>\n",
" <tr>\n",
" <td>76</td>\n",
" <td>0.059951168</td>\n",
" <td>0.5297594</td>\n",
" <td>0.41028935</td>\n",
" </tr>\n",
" <tr>\n",
" <td>81</td>\n",
" <td>0.0791236</td>\n",
" <td>0.49948806</td>\n",
" <td>0.42138833</td>\n",
" </tr>\n",
" <tr>\n",
" <td>83</td>\n",
" <td>0.103119485</td>\n",
" <td>0.54959977</td>\n",
" <td>0.34728083</td>\n",
" </tr>\n",
" <tr>\n",
" <td>86</td>\n",
" <td>0.15161447</td>\n",
" <td>0.6227044</td>\n",
" <td>0.22568108</td>\n",
" </tr>\n",
" <tr>\n",
" <td>88</td>\n",
" <td>0.013850493</td>\n",
" <td>0.3046302</td>\n",
" <td>0.6815193</td>\n",
" </tr>\n",
" <tr>\n",
" <td>92</td>\n",
" <td>0.070333414</td>\n",
" <td>0.545334</td>\n",
" <td>0.3843325</td>\n",
" </tr>\n",
" <tr>\n",
" <td>93</td>\n",
" <td>0.07561784</td>\n",
" <td>0.5140931</td>\n",
" <td>0.41028905</td>\n",
" </tr>\n",
" <tr>\n",
" <td>95</td>\n",
" <td>0.08128024</td>\n",
" <td>0.52868783</td>\n",
" <td>0.39003193</td>\n",
" </tr>\n",
" <tr>\n",
" <td>100</td>\n",
" <td>0.10329097</td>\n",
" <td>0.5575698</td>\n",
" <td>0.33913925</td>\n",
" </tr>\n",
" <tr>\n",
" <td>104</td>\n",
" <td>0.010344159</td>\n",
" <td>0.31838065</td>\n",
" <td>0.6712752</td>\n",
" </tr>\n",
" <tr>\n",
" <td>107</td>\n",
" <td>0.039944757</td>\n",
" <td>0.4255802</td>\n",
" <td>0.5344751</td>\n",
" </tr>\n",
" <tr>\n",
" <td>111</td>\n",
" <td>0.026599577</td>\n",
" <td>0.44653893</td>\n",
" <td>0.52686155</td>\n",
" </tr>\n",
" <tr>\n",
" <td>117</td>\n",
" <td>0.012989115</td>\n",
" <td>0.35122624</td>\n",
" <td>0.6357847</td>\n",
" </tr>\n",
" <tr>\n",
" <td>134</td>\n",
" <td>0.019927882</td>\n",
" <td>0.38532582</td>\n",
" <td>0.5947463</td>\n",
" </tr>\n",
" <tr>\n",
" <td>140</td>\n",
" <td>0.009378748</td>\n",
" <td>0.31938007</td>\n",
" <td>0.6712412</td>\n",
" </tr>\n",
" <tr>\n",
" <td>143</td>\n",
" <td>0.013671607</td>\n",
" <td>0.3261078</td>\n",
" <td>0.66022056</td>\n",
" </tr>\n",
" <tr>\n",
" <td>150</td>\n",
" <td>0.031985275</td>\n",
" <td>0.45162654</td>\n",
" <td>0.51638824</td>\n",
" </tr>\n",
"</table>"
],
"text/plain": [
"[(4, 0.89618546, 0.10063652, 0.0031779788),\n",
" (17, 0.9432447, 0.055964436, 0.00079082645),\n",
" (24, 0.87476385, 0.121528275, 0.0037078795),\n",
" (30, 0.8998875, 0.09730224, 0.0028102635),\n",
" (39, 0.89937997, 0.09733549, 0.003284483),\n",
" (40, 0.9124368, 0.08554972, 0.0020134845),\n",
" (43, 0.91849124, 0.079369105, 0.0021397525),\n",
" (50, 0.909191, 0.08853077, 0.002278217),\n",
" (52, 0.087838314, 0.5821711, 0.3299906),\n",
" (54, 0.040643755, 0.41653973, 0.5428166),\n",
" (55, 0.028924335, 0.42645925, 0.54461634),\n",
" (59, 0.043529026, 0.48816994, 0.468301),\n",
" (61, 0.06540182, 0.44180837, 0.4927898),\n",
" (76, 0.059951168, 0.5297594, 0.41028935),\n",
" (81, 0.0791236, 0.49948806, 0.42138833),\n",
" (83, 0.103119485, 0.54959977, 0.34728083),\n",
" (86, 0.15161447, 0.6227044, 0.22568108),\n",
" (88, 0.013850493, 0.3046302, 0.6815193),\n",
" (92, 0.070333414, 0.545334, 0.3843325),\n",
" (93, 0.07561784, 0.5140931, 0.41028905),\n",
" (95, 0.08128024, 0.52868783, 0.39003193),\n",
" (100, 0.10329097, 0.5575698, 0.33913925),\n",
" (104, 0.010344159, 0.31838065, 0.6712752),\n",
" (107, 0.039944757, 0.4255802, 0.5344751),\n",
" (111, 0.026599577, 0.44653893, 0.52686155),\n",
" (117, 0.012989115, 0.35122624, 0.6357847),\n",
" (134, 0.019927882, 0.38532582, 0.5947463),\n",
" (140, 0.009378748, 0.31938007, 0.6712412),\n",
" (143, 0.013671607, 0.3261078, 0.66022056),\n",
" (150, 0.031985275, 0.45162654, 0.51638824)]"
]
},
"execution_count": 21,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"%%sql\n",
"DROP TABLE IF EXISTS iris_predict;\n",
"\n",
"SELECT madlib.madlib_keras_predict('iris_model', -- model\n",
" 'iris_test', -- test_table\n",
" 'id', -- id column\n",
" 'attributes', -- independent var\n",
" 'iris_predict', -- output table\n",
" 'prob' -- response type\n",
" );\n",
"\n",
"SELECT * FROM iris_predict ORDER BY id;"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"<a id=\"warm_start\"></a>\n",
"# 3. Warm start\n",
"Next, use the warm_start parameter to continue learning, using the coefficients from the run above. Note that we don't drop the model table or model summary table:"
]
},
{
"cell_type": "code",
"execution_count": 22,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"1 rows affected.\n"
]
},
{
"data": {
"text/html": [
"<table>\n",
" <tr>\n",
" <th>madlib_keras_fit</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",
"SELECT madlib.madlib_keras_fit('iris_train_packed', -- source table\n",
" 'iris_model', -- model output table\n",
" 'model_arch_library', -- model arch table\n",
" 1, -- model arch id\n",
" $$ loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'] $$, -- compile_params\n",
" $$ batch_size=5, epochs=3 $$, -- fit_params\n",
" 5, -- num_iterations\n",
" 0, -- GPUs per host\n",
" 'iris_test_packed', -- validation dataset\n",
" 1, -- metrics compute frequency\n",
" TRUE, -- warm start\n",
" 'Sophie L.', -- name \n",
" 'Simple MLP for iris dataset' -- description\n",
" );"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"In the summary table note that the loss and accuracy values pick up from where the previous run left off:"
]
},
{
"cell_type": "code",
"execution_count": 23,
"metadata": {
"scrolled": true
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"1 rows affected.\n"
]
},
{
"data": {
"text/html": [
"<table>\n",
" <tr>\n",
" <th>source_table</th>\n",
" <th>model</th>\n",
" <th>dependent_varname</th>\n",
" <th>independent_varname</th>\n",
" <th>model_arch_table</th>\n",
" <th>model_arch_id</th>\n",
" <th>compile_params</th>\n",
" <th>fit_params</th>\n",
" <th>num_iterations</th>\n",
" <th>validation_table</th>\n",
" <th>metrics_compute_frequency</th>\n",
" <th>name</th>\n",
" <th>description</th>\n",
" <th>model_type</th>\n",
" <th>model_size</th>\n",
" <th>start_training_time</th>\n",
" <th>end_training_time</th>\n",
" <th>metrics_elapsed_time</th>\n",
" <th>madlib_version</th>\n",
" <th>num_classes</th>\n",
" <th>class_values</th>\n",
" <th>dependent_vartype</th>\n",
" <th>normalizing_const</th>\n",
" <th>metrics_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>iris_train_packed</td>\n",
" <td>iris_model</td>\n",
" <td>class_text</td>\n",
" <td>attributes</td>\n",
" <td>model_arch_library</td>\n",
" <td>1</td>\n",
" <td> loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'] </td>\n",
" <td> batch_size=5, epochs=3 </td>\n",
" <td>5</td>\n",
" <td>iris_test_packed</td>\n",
" <td>1</td>\n",
" <td>Sophie L.</td>\n",
" <td>Simple MLP for iris dataset</td>\n",
" <td>madlib_keras</td>\n",
" <td>0.7900390625</td>\n",
" <td>2019-07-03 10:01:52.495132</td>\n",
" <td>2019-07-03 10:01:56.620862</td>\n",
" <td>[0.777317047119141, 1.62117600440979, 2.46934199333191, 3.33750104904175, 4.12567687034607]</td>\n",
" <td>1.16</td>\n",
" <td>3</td>\n",
" <td>[u'Iris-setosa', u'Iris-versicolor', u'Iris-virginica']</td>\n",
" <td>character varying</td>\n",
" <td>1.0</td>\n",
" <td>[u'accuracy']</td>\n",
" <td>0.941666662693</td>\n",
" <td>0.256453901529</td>\n",
" <td>[0.941666662693024, 0.941666662693024, 0.941666662693024, 0.941666662693024, 0.941666662693024]</td>\n",
" <td>[0.341408282518387, 0.313415616750717, 0.293370455503464, 0.273623049259186, 0.256453901529312]</td>\n",
" <td>0.899999976158</td>\n",
" <td>0.36899459362</td>\n",
" <td>[0.833333313465118, 0.866666674613953, 0.899999976158142, 0.899999976158142, 0.899999976158142]</td>\n",
" <td>[0.468038767576218, 0.429012358188629, 0.406685948371887, 0.386049389839172, 0.3689945936203]</td>\n",
" <td>[1, 2, 3, 4, 5]</td>\n",
" </tr>\n",
"</table>"
],
"text/plain": [
"[(u'iris_train_packed', u'iris_model', u'class_text', u'attributes', u'model_arch_library', 1, u\" loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'] \", u' batch_size=5, epochs=3 ', 5, u'iris_test_packed', 1, u'Sophie L.', u'Simple MLP for iris dataset', u'madlib_keras', 0.7900390625, datetime.datetime(2019, 7, 3, 10, 1, 52, 495132), datetime.datetime(2019, 7, 3, 10, 1, 56, 620862), [0.777317047119141, 1.62117600440979, 2.46934199333191, 3.33750104904175, 4.12567687034607], u'1.16', 3, [u'Iris-setosa', u'Iris-versicolor', u'Iris-virginica'], u'character varying', 1.0, [u'accuracy'], 0.941666662693, 0.256453901529, [0.941666662693024, 0.941666662693024, 0.941666662693024, 0.941666662693024, 0.941666662693024], [0.341408282518387, 0.313415616750717, 0.293370455503464, 0.273623049259186, 0.256453901529312], 0.899999976158, 0.36899459362, [0.833333313465118, 0.866666674613953, 0.899999976158142, 0.899999976158142, 0.899999976158142], [0.468038767576218, 0.429012358188629, 0.406685948371887, 0.386049389839172, 0.3689945936203], [1, 2, 3, 4, 5])]"
]
},
"execution_count": 23,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"%%sql\n",
"SELECT * FROM iris_model_summary;"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"<a id=\"transfer_learn\"></a>\n",
"# Transfer learning\n",
"\n",
"<a id=\"load2\"></a>\n",
"# 1. Define and load model architecture with some layers frozen\n",
"Here we want to start with initial weights from a pre-trained model rather than training from scratch. We also want to use a model architecture with the earlier feature layer(s) frozen to save on training time. The example below is somewhat contrived but gives you the idea of the steps.\n",
"\n",
"First define a model architecture with the 1st hidden layer frozen:"
]
},
{
"cell_type": "code",
"execution_count": 24,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"_________________________________________________________________\n",
"Layer (type) Output Shape Param # \n",
"=================================================================\n",
"dense_4 (Dense) (None, 10) 50 \n",
"_________________________________________________________________\n",
"dense_5 (Dense) (None, 10) 110 \n",
"_________________________________________________________________\n",
"dense_6 (Dense) (None, 3) 33 \n",
"=================================================================\n",
"Total params: 193\n",
"Trainable params: 143\n",
"Non-trainable params: 50\n",
"_________________________________________________________________\n"
]
}
],
"source": [
"model_transfer = Sequential()\n",
"model_transfer.add(Dense(10, activation='relu', input_shape=(4,), trainable=False))\n",
"model_transfer.add(Dense(10, activation='relu'))\n",
"model_transfer.add(Dense(3, activation='softmax'))\n",
" \n",
"model_transfer.summary()"
]
},
{
"cell_type": "code",
"execution_count": 25,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'{\"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\": false, \"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\": \"softmax\", \"trainable\": true, \"kernel_regularizer\": null, \"bias_initializer\": {\"class_name\": \"Zeros\", \"config\": {}}, \"units\": 3, \"use_bias\": true, \"activity_regularizer\": null}}], \"backend\": \"tensorflow\"}'"
]
},
"execution_count": 25,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"model_transfer.to_json()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Load transfer model into model architecture table"
]
},
{
"cell_type": "code",
"execution_count": 26,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"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>A simple model</td>\n",
" <td>__madlib_temp_62550369_1562173248_86696923__</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_2', u'kernel_constraint': None, u'bias_regularizer': None, u'bias_constraint': None, u'dtype': u'float32', u'activation': u'relu', u'trainable': False, 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_3', 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_4', 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>A transfer model</td>\n",
" <td>__madlib_temp_71661491_1562173329_6849629__</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'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'}, None, u'Sophie', u'A simple model', u'__madlib_temp_62550369_1562173248_86696923__'),\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'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'dtype': u'float32', u'activation': u'relu', u'trainable': False, 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_3', 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_4', 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'}, None, u'Maria', u'A transfer model', u'__madlib_temp_71661491_1562173329_6849629__')]"
]
},
"execution_count": 26,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"%%sql\n",
"SELECT madlib.load_keras_model('model_arch_library', -- Output table,\n",
" \n",
"$$\n",
"{\"class_name\": \"Sequential\", \"keras_version\": \"2.1.6\", \"config\": [{\"class_name\": \"Dense\", \"config\": {\"kernel_initializer\": {\"class_name\": \"VarianceScaling\", \"config\": {\"distribution\": \"uniform\", \"scale\": 1.0, \"seed\": null, \"mode\": \"fan_avg\"}}, \"name\": \"dense_2\", \"kernel_constraint\": null, \"bias_regularizer\": null, \"bias_constraint\": null, \"dtype\": \"float32\", \"activation\": \"relu\", \"trainable\": false, \"kernel_regularizer\": null, \"bias_initializer\": {\"class_name\": \"Zeros\", \"config\": {}}, \"units\": 10, \"batch_input_shape\": [null, 4], \"use_bias\": true, \"activity_regularizer\": null}}, {\"class_name\": \"Dense\", \"config\": {\"kernel_initializer\": {\"class_name\": \"VarianceScaling\", \"config\": {\"distribution\": \"uniform\", \"scale\": 1.0, \"seed\": null, \"mode\": \"fan_avg\"}}, \"name\": \"dense_3\", \"kernel_constraint\": null, \"bias_regularizer\": null, \"bias_constraint\": null, \"activation\": \"relu\", \"trainable\": true, \"kernel_regularizer\": null, \"bias_initializer\": {\"class_name\": \"Zeros\", \"config\": {}}, \"units\": 10, \"use_bias\": true, \"activity_regularizer\": null}}, {\"class_name\": \"Dense\", \"config\": {\"kernel_initializer\": {\"class_name\": \"VarianceScaling\", \"config\": {\"distribution\": \"uniform\", \"scale\": 1.0, \"seed\": null, \"mode\": \"fan_avg\"}}, \"name\": \"dense_4\", \"kernel_constraint\": null, \"bias_regularizer\": null, \"bias_constraint\": null, \"activation\": \"softmax\", \"trainable\": true, \"kernel_regularizer\": null, \"bias_initializer\": {\"class_name\": \"Zeros\", \"config\": {}}, \"units\": 3, \"use_bias\": true, \"activity_regularizer\": null}}], \"backend\": \"tensorflow\"}\n",
"$$\n",
"::json, -- JSON blob\n",
" NULL, -- Weights\n",
" 'Maria', -- Name\n",
" 'A transfer model' -- Descr\n",
");\n",
"\n",
"SELECT * FROM model_arch_library;"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"<a id=\"train2\"></a>\n",
"# 2. Train transfer model\n",
"\n",
"Fetch the weights from a previous MADlib run. (Normally these would be downloaded from a source that trained the same model architecture on a related dataset.)"
]
},
{
"cell_type": "code",
"execution_count": 27,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"1 rows affected.\n"
]
},
{
"data": {
"text/plain": [
"[]"
]
},
"execution_count": 27,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"%%sql\n",
"UPDATE model_arch_library SET model_weights = model_data FROM iris_model WHERE model_id = 2;"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Now train the model using the transfer model and the pre-trained weights:"
]
},
{
"cell_type": "code",
"execution_count": 28,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Done.\n",
"1 rows affected.\n"
]
},
{
"data": {
"text/html": [
"<table>\n",
" <tr>\n",
" <th>madlib_keras_fit</th>\n",
" </tr>\n",
" <tr>\n",
" <td></td>\n",
" </tr>\n",
"</table>"
],
"text/plain": [
"[('',)]"
]
},
"execution_count": 28,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"%%sql\n",
"DROP TABLE IF EXISTS iris_model, iris_model_summary;\n",
"\n",
"SELECT madlib.madlib_keras_fit('iris_train_packed', -- source table\n",
" 'iris_model', -- model output table\n",
" 'model_arch_library', -- model arch table\n",
" 2, -- model arch id\n",
" $$ loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'] $$, -- compile_params\n",
" $$ batch_size=5, epochs=3 $$, -- fit_params\n",
" 10 -- num_iterations\n",
" );"
]
},
{
"cell_type": "code",
"execution_count": 29,
"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>model</th>\n",
" <th>dependent_varname</th>\n",
" <th>independent_varname</th>\n",
" <th>model_arch_table</th>\n",
" <th>model_arch_id</th>\n",
" <th>compile_params</th>\n",
" <th>fit_params</th>\n",
" <th>num_iterations</th>\n",
" <th>validation_table</th>\n",
" <th>metrics_compute_frequency</th>\n",
" <th>name</th>\n",
" <th>description</th>\n",
" <th>model_type</th>\n",
" <th>model_size</th>\n",
" <th>start_training_time</th>\n",
" <th>end_training_time</th>\n",
" <th>metrics_elapsed_time</th>\n",
" <th>madlib_version</th>\n",
" <th>num_classes</th>\n",
" <th>class_values</th>\n",
" <th>dependent_vartype</th>\n",
" <th>normalizing_const</th>\n",
" <th>metrics_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>iris_train_packed</td>\n",
" <td>iris_model</td>\n",
" <td>class_text</td>\n",
" <td>attributes</td>\n",
" <td>model_arch_library</td>\n",
" <td>2</td>\n",
" <td> loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'] </td>\n",
" <td> batch_size=5, epochs=3 </td>\n",
" <td>10</td>\n",
" <td>None</td>\n",
" <td>10</td>\n",
" <td>None</td>\n",
" <td>None</td>\n",
" <td>madlib_keras</td>\n",
" <td>0.7900390625</td>\n",
" <td>2019-07-03 10:02:15.366826</td>\n",
" <td>2019-07-03 10:02:20.437775</td>\n",
" <td>[5.07090902328491]</td>\n",
" <td>1.16</td>\n",
" <td>3</td>\n",
" <td>[u'Iris-setosa', u'Iris-versicolor', u'Iris-virginica']</td>\n",
" <td>character varying</td>\n",
" <td>1.0</td>\n",
" <td>[u'accuracy']</td>\n",
" <td>0.933333337307</td>\n",
" <td>0.188783079386</td>\n",
" <td>[0.933333337306976]</td>\n",
" <td>[0.188783079385757]</td>\n",
" <td>None</td>\n",
" <td>None</td>\n",
" <td>None</td>\n",
" <td>None</td>\n",
" <td>[10]</td>\n",
" </tr>\n",
"</table>"
],
"text/plain": [
"[(u'iris_train_packed', u'iris_model', u'class_text', u'attributes', u'model_arch_library', 2, u\" loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'] \", u' batch_size=5, epochs=3 ', 10, None, 10, None, None, u'madlib_keras', 0.7900390625, datetime.datetime(2019, 7, 3, 10, 2, 15, 366826), datetime.datetime(2019, 7, 3, 10, 2, 20, 437775), [5.07090902328491], u'1.16', 3, [u'Iris-setosa', u'Iris-versicolor', u'Iris-virginica'], u'character varying', 1.0, [u'accuracy'], 0.933333337307, 0.188783079386, [0.933333337306976], [0.188783079385757], None, None, None, None, [10])]"
]
},
"execution_count": 29,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"%%sql\n",
"SELECT * FROM iris_model_summary;"
]
}
],
"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": "2.7.10"
}
},
"nbformat": 4,
"nbformat_minor": 1
}