| <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd"> |
| <html xmlns="http://www.w3.org/1999/xhtml"> |
| <head> |
| <meta http-equiv="Content-Type" content="text/xhtml;charset=UTF-8"/> |
| <meta http-equiv="X-UA-Compatible" content="IE=9"/> |
| <meta name="generator" content="Doxygen 1.8.4"/> |
| <title>MADlib: cross_validation.sql_in Source File</title> |
| <link href="tabs.css" rel="stylesheet" type="text/css"/> |
| <script type="text/javascript" src="jquery.js"></script> |
| <script type="text/javascript" src="dynsections.js"></script> |
| <link href="navtree.css" rel="stylesheet" type="text/css"/> |
| <script type="text/javascript" src="resize.js"></script> |
| <script type="text/javascript" src="navtree.js"></script> |
| <script type="text/javascript"> |
| $(document).ready(initResizable); |
| $(window).load(resizeHeight); |
| </script> |
| <link href="search/search.css" rel="stylesheet" type="text/css"/> |
| <script type="text/javascript" src="search/search.js"></script> |
| <script type="text/javascript"> |
| $(document).ready(function() { searchBox.OnSelectItem(0); }); |
| </script> |
| <script type="text/x-mathjax-config"> |
| MathJax.Hub.Config({ |
| extensions: ["tex2jax.js", "TeX/AMSmath.js", "TeX/AMSsymbols.js"], |
| jax: ["input/TeX","output/HTML-CSS"], |
| }); |
| </script><script src="../mathjax/MathJax.js"></script> |
| <link href="doxygen.css" rel="stylesheet" type="text/css" /> |
| </head> |
| <body> |
| <div id="top"><!-- do not remove this div, it is closed by doxygen! --> |
| <div id="titlearea"> |
| <table cellspacing="0" cellpadding="0"> |
| <tbody> |
| <tr style="height: 56px;"> |
| <td style="padding-left: 0.5em;"> |
| <div id="projectname">MADlib |
|  <span id="projectnumber">1.0</span> <span style="font-size:10pt; font-style:italic"><a href="../latest/./cross__validation_8sql__in_source.html"> A newer version is available</a></span> |
| </div> |
| <div id="projectbrief">User Documentation</div> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| </div> |
| <!-- end header part --> |
| <!-- Generated by Doxygen 1.8.4 --> |
| <script type="text/javascript"> |
| var searchBox = new SearchBox("searchBox", "search",false,'Search'); |
| </script> |
| <div id="navrow1" class="tabs"> |
| <ul class="tablist"> |
| <li><a href="index.html"><span>Main Page</span></a></li> |
| <li><a href="modules.html"><span>Modules</span></a></li> |
| <li> |
| <div id="MSearchBox" class="MSearchBoxInactive"> |
| <span class="left"> |
| <img id="MSearchSelect" src="search/mag_sel.png" |
| onmouseover="return searchBox.OnSearchSelectShow()" |
| onmouseout="return searchBox.OnSearchSelectHide()" |
| alt=""/> |
| <input type="text" id="MSearchField" value="Search" accesskey="S" |
| onfocus="searchBox.OnSearchFieldFocus(true)" |
| onblur="searchBox.OnSearchFieldFocus(false)" |
| onkeyup="searchBox.OnSearchFieldChange(event)"/> |
| </span><span class="right"> |
| <a id="MSearchClose" href="javascript:searchBox.CloseResultsWindow()"><img id="MSearchCloseImg" border="0" src="search/close.png" alt=""/></a> |
| </span> |
| </div> |
| </li> |
| </ul> |
| </div> |
| </div><!-- top --> |
| <div id="side-nav" class="ui-resizable side-nav-resizable"> |
| <div id="nav-tree"> |
| <div id="nav-tree-contents"> |
| <div id="nav-sync" class="sync"></div> |
| </div> |
| </div> |
| <div id="splitbar" style="-moz-user-select:none;" |
| class="ui-resizable-handle"> |
| </div> |
| </div> |
| <script type="text/javascript"> |
| $(document).ready(function(){initNavTree('cross__validation_8sql__in_source.html','');}); |
| </script> |
| <div id="doc-content"> |
| <!-- window showing the filter options --> |
| <div id="MSearchSelectWindow" |
| onmouseover="return searchBox.OnSearchSelectShow()" |
| onmouseout="return searchBox.OnSearchSelectHide()" |
| onkeydown="return searchBox.OnSearchSelectKey(event)"> |
| <a class="SelectItem" href="javascript:void(0)" onclick="searchBox.OnSelectItem(0)"><span class="SelectionMark"> </span>All</a><a class="SelectItem" href="javascript:void(0)" onclick="searchBox.OnSelectItem(1)"><span class="SelectionMark"> </span>Files</a><a class="SelectItem" href="javascript:void(0)" onclick="searchBox.OnSelectItem(2)"><span class="SelectionMark"> </span>Functions</a><a class="SelectItem" href="javascript:void(0)" onclick="searchBox.OnSelectItem(3)"><span class="SelectionMark"> </span>Groups</a></div> |
| |
| <!-- iframe showing the search results (closed by default) --> |
| <div id="MSearchResultsWindow"> |
| <iframe src="javascript:void(0)" frameborder="0" |
| name="MSearchResults" id="MSearchResults"> |
| </iframe> |
| </div> |
| |
| <div class="header"> |
| <div class="headertitle"> |
| <div class="title">cross_validation.sql_in</div> </div> |
| </div><!--header--> |
| <div class="contents"> |
| <a href="cross__validation_8sql__in.html">Go to the documentation of this file.</a><div class="fragment"><div class="line"><a name="l00001"></a><span class="lineno"> 1</span> <span class="comment">/* ----------------------------------------------------------------------- */</span><span class="comment">/** </span></div> |
| <div class="line"><a name="l00002"></a><span class="lineno"> 2</span> <span class="comment"> *</span></div> |
| <div class="line"><a name="l00003"></a><span class="lineno"> 3</span> <span class="comment"> * @file cross_validation.sql_in</span></div> |
| <div class="line"><a name="l00004"></a><span class="lineno"> 4</span> <span class="comment"> *</span></div> |
| <div class="line"><a name="l00005"></a><span class="lineno"> 5</span> <span class="comment"> * @brief SQL functions for cross validation</span></div> |
| <div class="line"><a name="l00006"></a><span class="lineno"> 6</span> <span class="comment"> * @date January 2011</span></div> |
| <div class="line"><a name="l00007"></a><span class="lineno"> 7</span> <span class="comment"> *</span></div> |
| <div class="line"><a name="l00008"></a><span class="lineno"> 8</span> <span class="comment"> * @sa For a brief introduction to the usage of cross validation, see the</span></div> |
| <div class="line"><a name="l00009"></a><span class="lineno"> 9</span> <span class="comment"> * module description \ref grp_validation.</span></div> |
| <div class="line"><a name="l00010"></a><span class="lineno"> 10</span> <span class="comment"> *</span></div> |
| <div class="line"><a name="l00011"></a><span class="lineno"> 11</span> <span class="comment"> */</span><span class="comment">/* ----------------------------------------------------------------------- */</span></div> |
| <div class="line"><a name="l00012"></a><span class="lineno"> 12</span> </div> |
| <div class="line"><a name="l00013"></a><span class="lineno"> 13</span> </div> |
| <div class="line"><a name="l00014"></a><span class="lineno"> 14</span> m4_include(`SQLCommon.m4<span class="stringliteral">') --'</span></div> |
| <div class="line"><a name="l00015"></a><span class="lineno"> 15</span> <span class="comment"></span></div> |
| <div class="line"><a name="l00016"></a><span class="lineno"> 16</span> <span class="comment">/**</span></div> |
| <div class="line"><a name="l00017"></a><span class="lineno"> 17</span> <span class="comment">@addtogroup grp_validation</span></div> |
| <div class="line"><a name="l00018"></a><span class="lineno"> 18</span> <span class="comment"></span></div> |
| <div class="line"><a name="l00019"></a><span class="lineno"> 19</span> <span class="comment">@about</span></div> |
| <div class="line"><a name="l00020"></a><span class="lineno"> 20</span> <span class="comment"></span></div> |
| <div class="line"><a name="l00021"></a><span class="lineno"> 21</span> <span class="comment">Cross-validation, sometimes called rotation estimation, is a technique for assessing how the results of a statistical</span></div> |
| <div class="line"><a name="l00022"></a><span class="lineno"> 22</span> <span class="comment">analysis will generalize to an independent data set. It is mainly used in settings where the goal is prediction, and</span></div> |
| <div class="line"><a name="l00023"></a><span class="lineno"> 23</span> <span class="comment">one wants to estimate how accurately a predictive model will perform in practice. One round of cross-validation</span></div> |
| <div class="line"><a name="l00024"></a><span class="lineno"> 24</span> <span class="comment">involves partitioning a sample of data into complementary subsets, performing the analysis on one subset (called</span></div> |
| <div class="line"><a name="l00025"></a><span class="lineno"> 25</span> <span class="comment">the training set), and validating the analysis on the other subset (called the validation set or testing set). To</span></div> |
| <div class="line"><a name="l00026"></a><span class="lineno"> 26</span> <span class="comment">reduce variability, multiple rounds of cross-validation are performed using different partitions, and the validation</span></div> |
| <div class="line"><a name="l00027"></a><span class="lineno"> 27</span> <span class="comment">results are averaged over the rounds.</span></div> |
| <div class="line"><a name="l00028"></a><span class="lineno"> 28</span> <span class="comment"></span></div> |
| <div class="line"><a name="l00029"></a><span class="lineno"> 29</span> <span class="comment">In k-fold cross-validation, the original sample is randomly partitioned into k equal size subsamples. Of the k subsamples,</span></div> |
| <div class="line"><a name="l00030"></a><span class="lineno"> 30</span> <span class="comment">a single subsample is retained as the validation data for testing the model, and the remaining k − 1 subsamples are used</span></div> |
| <div class="line"><a name="l00031"></a><span class="lineno"> 31</span> <span class="comment">as training data. The cross-validation process is then repeated k times (the folds), with each of the k subsamples used</span></div> |
| <div class="line"><a name="l00032"></a><span class="lineno"> 32</span> <span class="comment">exactly once as the validation data. The k results from the folds then can be averaged (or otherwise combined) to produce</span></div> |
| <div class="line"><a name="l00033"></a><span class="lineno"> 33</span> <span class="comment">a single estimation. The advantage of this method over repeated random sub-sampling is that all observations are used for</span></div> |
| <div class="line"><a name="l00034"></a><span class="lineno"> 34</span> <span class="comment">both training and validation, and each observation is used for validation exactly once. 10-fold cross-validation is</span></div> |
| <div class="line"><a name="l00035"></a><span class="lineno"> 35</span> <span class="comment">commonly used, but in general k remains an unfixed parameter. </span></div> |
| <div class="line"><a name="l00036"></a><span class="lineno"> 36</span> <span class="comment"></span></div> |
| <div class="line"><a name="l00037"></a><span class="lineno"> 37</span> <span class="comment">@input</span></div> |
| <div class="line"><a name="l00038"></a><span class="lineno"> 38</span> <span class="comment"></span></div> |
| <div class="line"><a name="l00039"></a><span class="lineno"> 39</span> <span class="comment"><b>The flexible interface.</b></span></div> |
| <div class="line"><a name="l00040"></a><span class="lineno"> 40</span> <span class="comment"></span></div> |
| <div class="line"><a name="l00041"></a><span class="lineno"> 41</span> <span class="comment">The input includes the data set, a training function, a prediction function and an error metric function.</span></div> |
| <div class="line"><a name="l00042"></a><span class="lineno"> 42</span> <span class="comment"></span></div> |
| <div class="line"><a name="l00043"></a><span class="lineno"> 43</span> <span class="comment">The training function takes in a given data set with independent and dependent variables in it and produces</span></div> |
| <div class="line"><a name="l00044"></a><span class="lineno"> 44</span> <span class="comment">a model, which is stored in an output table.</span></div> |
| <div class="line"><a name="l00045"></a><span class="lineno"> 45</span> <span class="comment"></span></div> |
| <div class="line"><a name="l00046"></a><span class="lineno"> 46</span> <span class="comment">The prediction function takes in the model generated by the training function and a different data set with</span></div> |
| <div class="line"><a name="l00047"></a><span class="lineno"> 47</span> <span class="comment">independent variables in it, and it produces a prediction of the dependent variables bease on the model.</span></div> |
| <div class="line"><a name="l00048"></a><span class="lineno"> 48</span> <span class="comment">The prediction is stored in an output table. The prediction function should take a unique ID column name of</span></div> |
| <div class="line"><a name="l00049"></a><span class="lineno"> 49</span> <span class="comment">the data table as one of the inputs, otherwise the prediction result cannot be compared with the validation</span></div> |
| <div class="line"><a name="l00050"></a><span class="lineno"> 50</span> <span class="comment">values.</span></div> |
| <div class="line"><a name="l00051"></a><span class="lineno"> 51</span> <span class="comment"></span></div> |
| <div class="line"><a name="l00052"></a><span class="lineno"> 52</span> <span class="comment">The error metric function takes in the prediction made by the prediction function, and compare with the known</span></div> |
| <div class="line"><a name="l00053"></a><span class="lineno"> 53</span> <span class="comment">values of the dependent variables of the data set that was fed into the prediction function. It computes the</span></div> |
| <div class="line"><a name="l00054"></a><span class="lineno"> 54</span> <span class="comment">error metric defined by the function. The results are stored in a table</span></div> |
| <div class="line"><a name="l00055"></a><span class="lineno"> 55</span> <span class="comment"></span></div> |
| <div class="line"><a name="l00056"></a><span class="lineno"> 56</span> <span class="comment">Other inputs include the output table name, k value for the k-fold cross-validation, and how many folds the user</span></div> |
| <div class="line"><a name="l00057"></a><span class="lineno"> 57</span> <span class="comment">wants to try (for example, the user can choose to run a simple validation instead of a full cross-validation.)</span></div> |
| <div class="line"><a name="l00058"></a><span class="lineno"> 58</span> <span class="comment"></span></div> |
| <div class="line"><a name="l00059"></a><span class="lineno"> 59</span> <span class="comment">@usage</span></div> |
| <div class="line"><a name="l00060"></a><span class="lineno"> 60</span> <span class="comment"></span></div> |
| <div class="line"><a name="l00061"></a><span class="lineno"> 61</span> <span class="comment"><b>The flexible interface.</b></span></div> |
| <div class="line"><a name="l00062"></a><span class="lineno"> 62</span> <span class="comment"></span></div> |
| <div class="line"><a name="l00063"></a><span class="lineno"> 63</span> <span class="comment">In order to choose the optimum value for a parameter of the model, the user needs to provied the training function,</span></div> |
| <div class="line"><a name="l00064"></a><span class="lineno"> 64</span> <span class="comment">prediction function, error metric function, the parameter and its values to be studied and the data set.</span></div> |
| <div class="line"><a name="l00065"></a><span class="lineno"> 65</span> <span class="comment"></span></div> |
| <div class="line"><a name="l00066"></a><span class="lineno"> 66</span> <span class="comment">It would be better if the data set has a unique ID for each row, so that it is easier to cut the data set into the</span></div> |
| <div class="line"><a name="l00067"></a><span class="lineno"> 67</span> <span class="comment">training part and the validation part. The user also needs to inform the cross validation (CV) function about whether this</span></div> |
| <div class="line"><a name="l00068"></a><span class="lineno"> 68</span> <span class="comment">ID value is randomly assigned to each row. If it is not randomly assigned, the CV function will automatically generate</span></div> |
| <div class="line"><a name="l00069"></a><span class="lineno"> 69</span> <span class="comment">a random ID for each row.</span></div> |
| <div class="line"><a name="l00070"></a><span class="lineno"> 70</span> <span class="comment"></span></div> |
| <div class="line"><a name="l00071"></a><span class="lineno"> 71</span> <span class="comment">If the data set has no unique ID for each row, the CV function will copy the data set and create a randomly assigned ID</span></div> |
| <div class="line"><a name="l00072"></a><span class="lineno"> 72</span> <span class="comment">column for the newly created temp table. The new table will be dropped after the computation is finished. To minimize</span></div> |
| <div class="line"><a name="l00073"></a><span class="lineno"> 73</span> <span class="comment">the copying work load, the user needs to provide the data column names (for independent variables and dependent</span></div> |
| <div class="line"><a name="l00074"></a><span class="lineno"> 74</span> <span class="comment">variables) that are going to be used in the calculation, and only these columns will be copied.</span></div> |
| <div class="line"><a name="l00075"></a><span class="lineno"> 75</span> <span class="comment"></span></div> |
| <div class="line"><a name="l00076"></a><span class="lineno"> 76</span> <span class="comment"><pre>SELECT cross_validation_general(</span></div> |
| <div class="line"><a name="l00077"></a><span class="lineno"> 77</span> <span class="comment"> <em>modelling_func</em>, -- Name of function that trains the model</span></div> |
| <div class="line"><a name="l00078"></a><span class="lineno"> 78</span> <span class="comment"> <em>modelling_params</em>, -- Array of parameters for modelling function</span></div> |
| <div class="line"><a name="l00079"></a><span class="lineno"> 79</span> <span class="comment"> <em>modelling_params_type</em>, -- Types of each parameters for modelling function</span></div> |
| <div class="line"><a name="l00080"></a><span class="lineno"> 80</span> <span class="comment"> --</span></div> |
| <div class="line"><a name="l00081"></a><span class="lineno"> 81</span> <span class="comment"> <em>param_explored</em>, -- Name of parameter that will be checked to find the optimum value, the</span></div> |
| <div class="line"><a name="l00082"></a><span class="lineno"> 82</span> <span class="comment"> ---- same name must also appear in the array of modelling_params</span></div> |
| <div class="line"><a name="l00083"></a><span class="lineno"> 83</span> <span class="comment"> <em>explore_values</em>, -- Values of this parameter that will be studied</span></div> |
| <div class="line"><a name="l00084"></a><span class="lineno"> 84</span> <span class="comment"> --</span></div> |
| <div class="line"><a name="l00085"></a><span class="lineno"> 85</span> <span class="comment"> <em>predict_func</em>, -- Name of function for prediction</span></div> |
| <div class="line"><a name="l00086"></a><span class="lineno"> 86</span> <span class="comment"> <em>predict_params</em>, -- Array of parameters for prediction function</span></div> |
| <div class="line"><a name="l00087"></a><span class="lineno"> 87</span> <span class="comment"> <em>predict_params_type</em>, -- Types of each parameters for prediction function</span></div> |
| <div class="line"><a name="l00088"></a><span class="lineno"> 88</span> <span class="comment"> --</span></div> |
| <div class="line"><a name="l00089"></a><span class="lineno"> 89</span> <span class="comment"> <em>metric_func</em>, -- Name of function for measuring errors</span></div> |
| <div class="line"><a name="l00090"></a><span class="lineno"> 90</span> <span class="comment"> <em>metric_params</em>, -- Array of parameters for error metric function</span></div> |
| <div class="line"><a name="l00091"></a><span class="lineno"> 91</span> <span class="comment"> <em>metric_params_type</em>, -- Types of each parameters for metric function</span></div> |
| <div class="line"><a name="l00092"></a><span class="lineno"> 92</span> <span class="comment"> --</span></div> |
| <div class="line"><a name="l00093"></a><span class="lineno"> 93</span> <span class="comment"> <em>data_tbl</em>, -- Data table which will be split into training and validation parts</span></div> |
| <div class="line"><a name="l00094"></a><span class="lineno"> 94</span> <span class="comment"> <em>data_id</em>, -- Name of the unique ID associated with each row. Provide <em>NULL</em></span></div> |
| <div class="line"><a name="l00095"></a><span class="lineno"> 95</span> <span class="comment"> ---- if there is no such column in the data table</span></div> |
| <div class="line"><a name="l00096"></a><span class="lineno"> 96</span> <span class="comment"> <em>id_is_random</em>, -- Whether the provided ID is randomly assigned to each row</span></div> |
| <div class="line"><a name="l00097"></a><span class="lineno"> 97</span> <span class="comment"> --</span></div> |
| <div class="line"><a name="l00098"></a><span class="lineno"> 98</span> <span class="comment"> <em>validation_result</em>, -- Table name to store the output of CV function, see the Output for</span></div> |
| <div class="line"><a name="l00099"></a><span class="lineno"> 99</span> <span class="comment"> ---- format. It will be automatically created by CV function</span></div> |
| <div class="line"><a name="l00100"></a><span class="lineno"> 100</span> <span class="comment"> --</span></div> |
| <div class="line"><a name="l00101"></a><span class="lineno"> 101</span> <span class="comment"> <em>data_cols</em>, -- Names of data columns that are going to be used. It is only useful when</span></div> |
| <div class="line"><a name="l00102"></a><span class="lineno"> 102</span> <span class="comment"> ---- <em>data_id</em> is NULL, otherwise it is ignored.</span></div> |
| <div class="line"><a name="l00103"></a><span class="lineno"> 103</span> <span class="comment"> <em>fold_num</em> -- Value of k. How many folds validation? Each validation uses 1/fold_num</span></div> |
| <div class="line"><a name="l00104"></a><span class="lineno"> 104</span> <span class="comment"> ---- fraction of the data for validation. Deafult value: 10.</span></div> |
| <div class="line"><a name="l00105"></a><span class="lineno"> 105</span> <span class="comment">);</pre></span></div> |
| <div class="line"><a name="l00106"></a><span class="lineno"> 106</span> <span class="comment"></span></div> |
| <div class="line"><a name="l00107"></a><span class="lineno"> 107</span> <span class="comment">Special keywords in parameter arrays of modelling, prediction and metric functions:</span></div> |
| <div class="line"><a name="l00108"></a><span class="lineno"> 108</span> <span class="comment"></span></div> |
| <div class="line"><a name="l00109"></a><span class="lineno"> 109</span> <span class="comment"><em>\%data%</em> : The argument position for training/validation data </span></div> |
| <div class="line"><a name="l00110"></a><span class="lineno"> 110</span> <span class="comment"></span></div> |
| <div class="line"><a name="l00111"></a><span class="lineno"> 111</span> <span class="comment"><em>\%model%</em> : The argument position for the output/input of modelling/prediction function</span></div> |
| <div class="line"><a name="l00112"></a><span class="lineno"> 112</span> <span class="comment"></span></div> |
| <div class="line"><a name="l00113"></a><span class="lineno"> 113</span> <span class="comment"><em>\%id%</em> : The argument position of unique ID column (provided by user or generated by CV function as is mentioned above)</span></div> |
| <div class="line"><a name="l00114"></a><span class="lineno"> 114</span> <span class="comment"></span></div> |
| <div class="line"><a name="l00115"></a><span class="lineno"> 115</span> <span class="comment"><em>\%prediction%</em> : The argument position for the output/input of prediction/metric function</span></div> |
| <div class="line"><a name="l00116"></a><span class="lineno"> 116</span> <span class="comment"></span></div> |
| <div class="line"><a name="l00117"></a><span class="lineno"> 117</span> <span class="comment"><em>\%error%</em> : The argument position for the output of metric function</span></div> |
| <div class="line"><a name="l00118"></a><span class="lineno"> 118</span> <span class="comment"></span></div> |
| <div class="line"><a name="l00119"></a><span class="lineno"> 119</span> <span class="comment"><b>Note</b>: If the parameter <em>explore_values</em> is NULL or has zero length, then the cross validation function will only run a data folding.</span></div> |
| <div class="line"><a name="l00120"></a><span class="lineno"> 120</span> <span class="comment"></span></div> |
| <div class="line"><a name="l00121"></a><span class="lineno"> 121</span> <span class="comment">Output:</span></div> |
| <div class="line"><a name="l00122"></a><span class="lineno"> 122</span> <span class="comment"><pre> param_explored | average error | standard deviation of error</span></div> |
| <div class="line"><a name="l00123"></a><span class="lineno"> 123</span> <span class="comment">-------------------------|------------------|--------------------------------</span></div> |
| <div class="line"><a name="l00124"></a><span class="lineno"> 124</span> <span class="comment"> .......</span></div> |
| <div class="line"><a name="l00125"></a><span class="lineno"> 125</span> <span class="comment"></pre></span></div> |
| <div class="line"><a name="l00126"></a><span class="lineno"> 126</span> <span class="comment"></span></div> |
| <div class="line"><a name="l00127"></a><span class="lineno"> 127</span> <span class="comment"><b>Note:</b></span></div> |
| <div class="line"><a name="l00128"></a><span class="lineno"> 128</span> <span class="comment"></span></div> |
| <div class="line"><a name="l00129"></a><span class="lineno"> 129</span> <span class="comment"><em>max_locks_per_transaction</em>, which usually has the default value of 64, limits the number of tables that can be</span></div> |
| <div class="line"><a name="l00130"></a><span class="lineno"> 130</span> <span class="comment">dropped inside a single transaction (the CV function). Thus the number of different values of <em>param_explored</em></span></div> |
| <div class="line"><a name="l00131"></a><span class="lineno"> 131</span> <span class="comment">(or the length of array <em>explored_values</em>) cannot be too large. For 10-fold cross validation, the limit of</span></div> |
| <div class="line"><a name="l00132"></a><span class="lineno"> 132</span> <span class="comment">length(<em>explored_values</em>) is around 40. If this number is too large, the use might see "out of shared memory"</span></div> |
| <div class="line"><a name="l00133"></a><span class="lineno"> 133</span> <span class="comment">error because <em>max_locks_per_transaction</em> is used up.</span></div> |
| <div class="line"><a name="l00134"></a><span class="lineno"> 134</span> <span class="comment"></span></div> |
| <div class="line"><a name="l00135"></a><span class="lineno"> 135</span> <span class="comment">One way to overcome this limitation is to run CV function multiple times, and each run covers a different region of</span></div> |
| <div class="line"><a name="l00136"></a><span class="lineno"> 136</span> <span class="comment">values of the parameter.</span></div> |
| <div class="line"><a name="l00137"></a><span class="lineno"> 137</span> <span class="comment"></span></div> |
| <div class="line"><a name="l00138"></a><span class="lineno"> 138</span> <span class="comment">In the future, MADlib will implement cross-validation functions for each individual applicable module, where we can optimize the calculation to avoid table droppings and this max_locks_per_transaction limitation. However, such cross-validation functions need to know the implementation details of the modules to do the optimization and thus cannot be as flexible as the cross-validation function provided here.</span></div> |
| <div class="line"><a name="l00139"></a><span class="lineno"> 139</span> <span class="comment"></span></div> |
| <div class="line"><a name="l00140"></a><span class="lineno"> 140</span> <span class="comment">The cross-validation function provided here is very flexible, and can actually work with any algorithms that the user want to cross-validate including the algorithms written by the user. The price for this flexiblity is that the algorithms' details cannot be utilized to optimize the calculation and thus <em>max_locks_per_transaction</em> limitation cannot be avoided.</span></div> |
| <div class="line"><a name="l00141"></a><span class="lineno"> 141</span> <span class="comment"></span></div> |
| <div class="line"><a name="l00142"></a><span class="lineno"> 142</span> <span class="comment">@examp</span></div> |
| <div class="line"><a name="l00143"></a><span class="lineno"> 143</span> <span class="comment"></span></div> |
| <div class="line"><a name="l00144"></a><span class="lineno"> 144</span> <span class="comment">Cross validation is used on elastic net regression to find the best value of the regularization parameter.</span></div> |
| <div class="line"><a name="l00145"></a><span class="lineno"> 145</span> <span class="comment"></span></div> |
| <div class="line"><a name="l00146"></a><span class="lineno"> 146</span> <span class="comment">(1) Populate the table 'cvtest' with 101 dimensional independent variable 'val', and dependent</span></div> |
| <div class="line"><a name="l00147"></a><span class="lineno"> 147</span> <span class="comment">variable 'dep'.</span></div> |
| <div class="line"><a name="l00148"></a><span class="lineno"> 148</span> <span class="comment"></span></div> |
| <div class="line"><a name="l00149"></a><span class="lineno"> 149</span> <span class="comment">(2) Run the general CV function</span></div> |
| <div class="line"><a name="l00150"></a><span class="lineno"> 150</span> <span class="comment"><pre></span></div> |
| <div class="line"><a name="l00151"></a><span class="lineno"> 151</span> <span class="comment">select madlib.cross_validation_general (</span></div> |
| <div class="line"><a name="l00152"></a><span class="lineno"> 152</span> <span class="comment"> 'madlib.elastic_net_train',</span></div> |
| <div class="line"><a name="l00153"></a><span class="lineno"> 153</span> <span class="comment"> '{\%data%, \%model%, dep, val, gaussian, 1, lambda, True, Null, fista, "{eta = 2, max_stepsize = 2, use_active_set = t}", Null, 2000, 1e-6}'::varchar[],</span></div> |
| <div class="line"><a name="l00154"></a><span class="lineno"> 154</span> <span class="comment"> '{varchar, varchar, varchar, varchar, varchar, double precision, double precision, boolean, varchar, varchar, varchar[], varchar, integer, double precision}'::varchar[],</span></div> |
| <div class="line"><a name="l00155"></a><span class="lineno"> 155</span> <span class="comment"> --</span></div> |
| <div class="line"><a name="l00156"></a><span class="lineno"> 156</span> <span class="comment"> 'lambda',</span></div> |
| <div class="line"><a name="l00157"></a><span class="lineno"> 157</span> <span class="comment"> '{0.02, 0.04, 0.06, 0.08, 0.10, 0.12, 0.14, 0.16, 0.18, 0.20, 0.22, 0.24, 0.26, 0.28, 0.30, 0.32, 0.34, 0.36}'::varchar[],</span></div> |
| <div class="line"><a name="l00158"></a><span class="lineno"> 158</span> <span class="comment"> --</span></div> |
| <div class="line"><a name="l00159"></a><span class="lineno"> 159</span> <span class="comment"> 'madlib.elastic_net_predict',</span></div> |
| <div class="line"><a name="l00160"></a><span class="lineno"> 160</span> <span class="comment"> '{\%model%, \%data%, \%id%, \%prediction%}'::varchar[],</span></div> |
| <div class="line"><a name="l00161"></a><span class="lineno"> 161</span> <span class="comment"> '{text, text, text, text}'::varchar[],</span></div> |
| <div class="line"><a name="l00162"></a><span class="lineno"> 162</span> <span class="comment"> --</span></div> |
| <div class="line"><a name="l00163"></a><span class="lineno"> 163</span> <span class="comment"> 'madlib.mse_error', </span></div> |
| <div class="line"><a name="l00164"></a><span class="lineno"> 164</span> <span class="comment"> '{\%prediction%, \%data%, \%id%, dep, \%error%}'::varchar[],</span></div> |
| <div class="line"><a name="l00165"></a><span class="lineno"> 165</span> <span class="comment"> '{varchar, varchar, varchar, varchar, varchar}'::varchar[],</span></div> |
| <div class="line"><a name="l00166"></a><span class="lineno"> 166</span> <span class="comment"> --</span></div> |
| <div class="line"><a name="l00167"></a><span class="lineno"> 167</span> <span class="comment"> 'cvtest',</span></div> |
| <div class="line"><a name="l00168"></a><span class="lineno"> 168</span> <span class="comment"> NULL::varchar,</span></div> |
| <div class="line"><a name="l00169"></a><span class="lineno"> 169</span> <span class="comment"> False,</span></div> |
| <div class="line"><a name="l00170"></a><span class="lineno"> 170</span> <span class="comment"> --</span></div> |
| <div class="line"><a name="l00171"></a><span class="lineno"> 171</span> <span class="comment"> 'valid_rst_tbl',</span></div> |
| <div class="line"><a name="l00172"></a><span class="lineno"> 172</span> <span class="comment"> '{val, dep}'::varchar[],</span></div> |
| <div class="line"><a name="l00173"></a><span class="lineno"> 173</span> <span class="comment"> 10</span></div> |
| <div class="line"><a name="l00174"></a><span class="lineno"> 174</span> <span class="comment">);</span></div> |
| <div class="line"><a name="l00175"></a><span class="lineno"> 175</span> <span class="comment"></span></div> |
| <div class="line"><a name="l00176"></a><span class="lineno"> 176</span> <span class="comment"></pre></span></div> |
| <div class="line"><a name="l00177"></a><span class="lineno"> 177</span> <span class="comment"></span></div> |
| <div class="line"><a name="l00178"></a><span class="lineno"> 178</span> <span class="comment">@sa File cross_validation.sql_in documenting the SQL functions.</span></div> |
| <div class="line"><a name="l00179"></a><span class="lineno"> 179</span> <span class="comment"></span></div> |
| <div class="line"><a name="l00180"></a><span class="lineno"> 180</span> <span class="comment">*/</span></div> |
| <div class="line"><a name="l00181"></a><span class="lineno"> 181</span> </div> |
| <div class="line"><a name="l00182"></a><span class="lineno"> 182</span> ------------------------------------------------------------------------</div> |
| <div class="line"><a name="l00183"></a><span class="lineno"> 183</span> <span class="comment">/*</span></div> |
| <div class="line"><a name="l00184"></a><span class="lineno"> 184</span> <span class="comment"> * @brief Perform cross validation for modules that conforms with a fixed SQL API</span></div> |
| <div class="line"><a name="l00185"></a><span class="lineno"> 185</span> <span class="comment"> * Note: There is a lock number limitation of this function. It is flexible to use, so that the user can</span></div> |
| <div class="line"><a name="l00186"></a><span class="lineno"> 186</span> <span class="comment"> * try CV method on their own functions. On the other hand, cross_validation function does not have the</span></div> |
| <div class="line"><a name="l00187"></a><span class="lineno"> 187</span> <span class="comment"> * lock number limitation.</span></div> |
| <div class="line"><a name="l00188"></a><span class="lineno"> 188</span> <span class="comment"> *</span></div> |
| <div class="line"><a name="l00189"></a><span class="lineno"> 189</span> <span class="comment"> * @param modelling_func Name of function that trains the model</span></div> |
| <div class="line"><a name="l00190"></a><span class="lineno"> 190</span> <span class="comment"> * @param modelling_params Array of parameters for modelling function</span></div> |
| <div class="line"><a name="l00191"></a><span class="lineno"> 191</span> <span class="comment"> * @param modelling_params_type Types of each parameters for modelling function</span></div> |
| <div class="line"><a name="l00192"></a><span class="lineno"> 192</span> <span class="comment"> * @param param_explored Name of parameter that will be checked to find the optimum value, the same name must also appear in the array of modelling_params</span></div> |
| <div class="line"><a name="l00193"></a><span class="lineno"> 193</span> <span class="comment"> * @param explore_values Values of this parameter that will be studied</span></div> |
| <div class="line"><a name="l00194"></a><span class="lineno"> 194</span> <span class="comment"> * @param predict_func Name of function for prediction</span></div> |
| <div class="line"><a name="l00195"></a><span class="lineno"> 195</span> <span class="comment"> * @param predict_params Array of parameters for prediction function</span></div> |
| <div class="line"><a name="l00196"></a><span class="lineno"> 196</span> <span class="comment"> * @param predict_params_type Types of each parameters for prediction function</span></div> |
| <div class="line"><a name="l00197"></a><span class="lineno"> 197</span> <span class="comment"> * @param metric_func Name of function for measuring errors</span></div> |
| <div class="line"><a name="l00198"></a><span class="lineno"> 198</span> <span class="comment"> * @param metric_params Array of parameters for error metric function</span></div> |
| <div class="line"><a name="l00199"></a><span class="lineno"> 199</span> <span class="comment"> * @param metric_params_type Types of each parameters for metric function</span></div> |
| <div class="line"><a name="l00200"></a><span class="lineno"> 200</span> <span class="comment"> * @param data_tbl Data table which will be split into training and validation parts</span></div> |
| <div class="line"><a name="l00201"></a><span class="lineno"> 201</span> <span class="comment"> * @param data_id Name of the unique ID associated with each row. Provide <em>NULL</em> if there is no such column in the data table</span></div> |
| <div class="line"><a name="l00202"></a><span class="lineno"> 202</span> <span class="comment"> * @param id_is_random Whether the provided ID is randomly assigned to each row</span></div> |
| <div class="line"><a name="l00203"></a><span class="lineno"> 203</span> <span class="comment"> * @param validation_result Table name to store the output of CV function, see the Output for format. It will be automatically created by CV function</span></div> |
| <div class="line"><a name="l00204"></a><span class="lineno"> 204</span> <span class="comment"> * @param fold_num Value of k. How many folds validation? Each validation uses 1/fold_num fraction of the data for validation. Deafult value: 10.</span></div> |
| <div class="line"><a name="l00205"></a><span class="lineno"> 205</span> <span class="comment"> * @param data_cols Names of data columns that are going to be used. It is only useful when <em>data_id</em> is NULL, otherwise it is ignored.</span></div> |
| <div class="line"><a name="l00206"></a><span class="lineno"> 206</span> <span class="comment"> */</span></div> |
| <div class="line"><a name="l00207"></a><span class="lineno"> 207</span> CREATE OR REPLACE FUNCTION MADLIB_SCHEMA.cross_validation_general(</div> |
| <div class="line"><a name="l00208"></a><span class="lineno"> 208</span>  modelling_func VARCHAR, -- <span class="keyword">function</span> <span class="keywordflow">for</span> setting up the model</div> |
| <div class="line"><a name="l00209"></a><span class="lineno"> 209</span>  modelling_params VARCHAR[], -- parameters <span class="keywordflow">for</span> modelling</div> |
| <div class="line"><a name="l00210"></a><span class="lineno"> 210</span>  modelling_params_type VARCHAR[], -- parameter types <span class="keywordflow">for</span> modelling</div> |
| <div class="line"><a name="l00211"></a><span class="lineno"> 211</span>  --</div> |
| <div class="line"><a name="l00212"></a><span class="lineno"> 212</span>  param_explored VARCHAR, -- which parameter will be studied <span class="keyword">using</span> validation</div> |
| <div class="line"><a name="l00213"></a><span class="lineno"> 213</span>  explore_values VARCHAR[], -- values that will be explored <span class="keywordflow">for</span> <span class="keyword">this</span> parameter</div> |
| <div class="line"><a name="l00214"></a><span class="lineno"> 214</span>  --</div> |
| <div class="line"><a name="l00215"></a><span class="lineno"> 215</span>  predict_func VARCHAR, -- <span class="keyword">function</span> <span class="keywordflow">for</span> predicting <span class="keyword">using</span> the model</div> |
| <div class="line"><a name="l00216"></a><span class="lineno"> 216</span>  predict_params VARCHAR[], -- parameters <span class="keywordflow">for</span> prediction</div> |
| <div class="line"><a name="l00217"></a><span class="lineno"> 217</span>  predict_params_type VARCHAR[], -- parameter types <span class="keywordflow">for</span> prediction</div> |
| <div class="line"><a name="l00218"></a><span class="lineno"> 218</span>  --</div> |
| <div class="line"><a name="l00219"></a><span class="lineno"> 219</span>  metric_func VARCHAR, -- <span class="keyword">function</span> that computes the error metric</div> |
| <div class="line"><a name="l00220"></a><span class="lineno"> 220</span>  metric_params VARCHAR[], -- parameters <span class="keywordflow">for</span> metric </div> |
| <div class="line"><a name="l00221"></a><span class="lineno"> 221</span>  metric_params_type VARCHAR[], -- parameter types <span class="keywordflow">for</span> metric</div> |
| <div class="line"><a name="l00222"></a><span class="lineno"> 222</span>  --</div> |
| <div class="line"><a name="l00223"></a><span class="lineno"> 223</span>  data_tbl VARCHAR, -- table containing the data, which will be split into training and validation parts</div> |
| <div class="line"><a name="l00224"></a><span class="lineno"> 224</span>  data_id VARCHAR, -- user provide a unique ID <span class="keywordflow">for each</span> row</div> |
| <div class="line"><a name="l00225"></a><span class="lineno"> 225</span>  id_is_random BOOLEAN, -- the ID provided by user is random</div> |
| <div class="line"><a name="l00226"></a><span class="lineno"> 226</span>  --</div> |
| <div class="line"><a name="l00227"></a><span class="lineno"> 227</span>  validation_result VARCHAR, -- store the result: param values, error, +/-</div> |
| <div class="line"><a name="l00228"></a><span class="lineno"> 228</span>  --</div> |
| <div class="line"><a name="l00229"></a><span class="lineno"> 229</span>  data_cols VARCHAR[], -- names of data columns that are going to be used</div> |
| <div class="line"><a name="l00230"></a><span class="lineno"> 230</span>  fold_num INTEGER -- how many fold validation, <span class="keywordflow">default</span>: 10</div> |
| <div class="line"><a name="l00231"></a><span class="lineno"> 231</span> ) RETURNS VOID AS $$</div> |
| <div class="line"><a name="l00232"></a><span class="lineno"> 232</span> PythonFunction(validation, cross_validation, cross_validation_general)</div> |
| <div class="line"><a name="l00233"></a><span class="lineno"> 233</span> $$ LANGUAGE plpythonu;</div> |
| <div class="line"><a name="l00234"></a><span class="lineno"> 234</span> </div> |
| <div class="line"><a name="l00235"></a><span class="lineno"> 235</span> ------------------------------------------------------------------------</div> |
| <div class="line"><a name="l00236"></a><span class="lineno"> 236</span> </div> |
| <div class="line"><a name="l00237"></a><span class="lineno"> 237</span> CREATE OR REPLACE FUNCTION MADLIB_SCHEMA.cross_validation_general(</div> |
| <div class="line"><a name="l00238"></a><span class="lineno"> 238</span>  modelling_func VARCHAR, -- <span class="keyword">function</span> <span class="keywordflow">for</span> setting up the model</div> |
| <div class="line"><a name="l00239"></a><span class="lineno"> 239</span>  modelling_params VARCHAR[], -- parameters <span class="keywordflow">for</span> modelling</div> |
| <div class="line"><a name="l00240"></a><span class="lineno"> 240</span>  modelling_params_type VARCHAR[], -- parameter types <span class="keywordflow">for</span> modelling</div> |
| <div class="line"><a name="l00241"></a><span class="lineno"> 241</span>  --</div> |
| <div class="line"><a name="l00242"></a><span class="lineno"> 242</span>  param_explored VARCHAR, -- which parameter will be studied <span class="keyword">using</span> validation</div> |
| <div class="line"><a name="l00243"></a><span class="lineno"> 243</span>  explore_values VARCHAR[], -- values that will be explored <span class="keywordflow">for</span> <span class="keyword">this</span> parameter</div> |
| <div class="line"><a name="l00244"></a><span class="lineno"> 244</span>  --</div> |
| <div class="line"><a name="l00245"></a><span class="lineno"> 245</span>  predict_func VARCHAR, -- <span class="keyword">function</span> <span class="keywordflow">for</span> predicting <span class="keyword">using</span> the model</div> |
| <div class="line"><a name="l00246"></a><span class="lineno"> 246</span>  predict_params VARCHAR[], -- parameters <span class="keywordflow">for</span> prediction</div> |
| <div class="line"><a name="l00247"></a><span class="lineno"> 247</span>  predict_params_type VARCHAR[], -- parameter types <span class="keywordflow">for</span> prediction</div> |
| <div class="line"><a name="l00248"></a><span class="lineno"> 248</span>  --</div> |
| <div class="line"><a name="l00249"></a><span class="lineno"> 249</span>  metric_func VARCHAR, -- <span class="keyword">function</span> that computes the error metric</div> |
| <div class="line"><a name="l00250"></a><span class="lineno"> 250</span>  metric_params VARCHAR[], -- parameters <span class="keywordflow">for</span> prediction </div> |
| <div class="line"><a name="l00251"></a><span class="lineno"> 251</span>  metric_params_type VARCHAR[], -- parameter types <span class="keywordflow">for</span> prediction</div> |
| <div class="line"><a name="l00252"></a><span class="lineno"> 252</span>  --</div> |
| <div class="line"><a name="l00253"></a><span class="lineno"> 253</span>  data_tbl VARCHAR, -- table containing the data, which will be split into training and validation parts</div> |
| <div class="line"><a name="l00254"></a><span class="lineno"> 254</span>  data_id VARCHAR, -- user provide a unique ID <span class="keywordflow">for each</span> row</div> |
| <div class="line"><a name="l00255"></a><span class="lineno"> 255</span>  id_is_random BOOLEAN, -- the ID provided by user is random</div> |
| <div class="line"><a name="l00256"></a><span class="lineno"> 256</span>  --</div> |
| <div class="line"><a name="l00257"></a><span class="lineno"> 257</span>  validation_result VARCHAR, -- store the result: param values, error, +/-</div> |
| <div class="line"><a name="l00258"></a><span class="lineno"> 258</span>  --</div> |
| <div class="line"><a name="l00259"></a><span class="lineno"> 259</span>  data_cols VARCHAR[] -- names of data columns that are going to be used </div> |
| <div class="line"><a name="l00260"></a><span class="lineno"> 260</span> ) RETURNS VOID AS $$</div> |
| <div class="line"><a name="l00261"></a><span class="lineno"> 261</span> BEGIN</div> |
| <div class="line"><a name="l00262"></a><span class="lineno"> 262</span>  PERFORM MADLIB_SCHEMA.cross_validation_general($1,$2,$3,$4,$5,$6,$7,$8,$9,$10,$11,$12,$13,$14,$15,$16,10);</div> |
| <div class="line"><a name="l00263"></a><span class="lineno"> 263</span> END;</div> |
| <div class="line"><a name="l00264"></a><span class="lineno"> 264</span> $$ LANGUAGE plpgsql VOLATILE;</div> |
| <div class="line"><a name="l00265"></a><span class="lineno"> 265</span> </div> |
| <div class="line"><a name="l00266"></a><span class="lineno"> 266</span> ------------------------------------------------------------------------</div> |
| <div class="line"><a name="l00267"></a><span class="lineno"> 267</span> ------------------------------------------------------------------------</div> |
| <div class="line"><a name="l00268"></a><span class="lineno"> 268</span> ------------------------------------------------------------------------</div> |
| <div class="line"><a name="l00269"></a><span class="lineno"> 269</span> <span class="comment"></span></div> |
| <div class="line"><a name="l00270"></a><span class="lineno"> 270</span> <span class="comment">/**</span></div> |
| <div class="line"><a name="l00271"></a><span class="lineno"> 271</span> <span class="comment"> * @brief Simple interface of cross-validation, which has no limitation on lock number</span></div> |
| <div class="line"><a name="l00272"></a><span class="lineno"> 272</span> <span class="comment"> *</span></div> |
| <div class="line"><a name="l00273"></a><span class="lineno"> 273</span> <span class="comment"> * @param module_name Module to be cross validated</span></div> |
| <div class="line"><a name="l00274"></a><span class="lineno"> 274</span> <span class="comment"> * @param func_args Arguments of modelling function of the module, including the table name of data</span></div> |
| <div class="line"><a name="l00275"></a><span class="lineno"> 275</span> <span class="comment"> * @param param_to_try The name of the paramter that CV runs through</span></div> |
| <div class="line"><a name="l00276"></a><span class="lineno"> 276</span> <span class="comment"> * @param param_values The values of the parameter that CV will try</span></div> |
| <div class="line"><a name="l00277"></a><span class="lineno"> 277</span> <span class="comment"> * @param data_id Name of the unique ID associated with each row. Provide <em>NULL</em> if there is no such column in the data table</span></div> |
| <div class="line"><a name="l00278"></a><span class="lineno"> 278</span> <span class="comment"> * @param id_is_random Whether the provided ID is randomly assigned to each row</span></div> |
| <div class="line"><a name="l00279"></a><span class="lineno"> 279</span> <span class="comment"> * @param validation_result Table name to store the output of CV function, see the Output for format. It will be automatically created by CV function</span></div> |
| <div class="line"><a name="l00280"></a><span class="lineno"> 280</span> <span class="comment"> * @param fold_num How many fold cross-validation</span></div> |
| <div class="line"><a name="l00281"></a><span class="lineno"> 281</span> <span class="comment"> */</span></div> |
| <div class="line"><a name="l00282"></a><span class="lineno"> 282</span> <span class="comment">/*</span></div> |
| <div class="line"><a name="l00283"></a><span class="lineno"> 283</span> <span class="comment">CREATE OR REPLACE FUNCTION MADLIB_SCHEMA.cross_validation(</span></div> |
| <div class="line"><a name="l00284"></a><span class="lineno"> 284</span> <span class="comment"> module_name VARCHAR, -- module to be cross validated</span></div> |
| <div class="line"><a name="l00285"></a><span class="lineno"> 285</span> <span class="comment"> func_args VARCHAR[],</span></div> |
| <div class="line"><a name="l00286"></a><span class="lineno"> 286</span> <span class="comment"> param_to_try VARCHAR,</span></div> |
| <div class="line"><a name="l00287"></a><span class="lineno"> 287</span> <span class="comment"> param_values DOUBLE PRECISION[],</span></div> |
| <div class="line"><a name="l00288"></a><span class="lineno"> 288</span> <span class="comment"> data_id VARCHAR,</span></div> |
| <div class="line"><a name="l00289"></a><span class="lineno"> 289</span> <span class="comment"> id_is_random BOOLEAN,</span></div> |
| <div class="line"><a name="l00290"></a><span class="lineno"> 290</span> <span class="comment"> validation_result VARCHAR,</span></div> |
| <div class="line"><a name="l00291"></a><span class="lineno"> 291</span> <span class="comment"> fold_num INTEGER</span></div> |
| <div class="line"><a name="l00292"></a><span class="lineno"> 292</span> <span class="comment">) RETURNS VOID AS $$</span></div> |
| <div class="line"><a name="l00293"></a><span class="lineno"> 293</span> <span class="comment">PythonFunction(validation, cross_validation, cross_validation)</span></div> |
| <div class="line"><a name="l00294"></a><span class="lineno"> 294</span> <span class="comment">$$ LANGUAGE plpythonu;</span></div> |
| <div class="line"><a name="l00295"></a><span class="lineno"> 295</span> <span class="comment">*/</span></div> |
| <div class="line"><a name="l00296"></a><span class="lineno"> 296</span> -- ------------------------------------------------------------------------</div> |
| <div class="line"><a name="l00297"></a><span class="lineno"> 297</span> <span class="comment">/*</span></div> |
| <div class="line"><a name="l00298"></a><span class="lineno"> 298</span> <span class="comment">CREATE OR REPLACE FUNCTION MADLIB_SCHEMA.cross_validation(</span></div> |
| <div class="line"><a name="l00299"></a><span class="lineno"> 299</span> <span class="comment"> module_name VARCHAR,</span></div> |
| <div class="line"><a name="l00300"></a><span class="lineno"> 300</span> <span class="comment"> func_args VARCHAR[],</span></div> |
| <div class="line"><a name="l00301"></a><span class="lineno"> 301</span> <span class="comment"> param_to_try VARCHAR,</span></div> |
| <div class="line"><a name="l00302"></a><span class="lineno"> 302</span> <span class="comment"> param_values DOUBLE PRECISION[],</span></div> |
| <div class="line"><a name="l00303"></a><span class="lineno"> 303</span> <span class="comment"> data_id VARCHAR,</span></div> |
| <div class="line"><a name="l00304"></a><span class="lineno"> 304</span> <span class="comment"> id_is_random BOOLEAN,</span></div> |
| <div class="line"><a name="l00305"></a><span class="lineno"> 305</span> <span class="comment"> validation_result VARCHAR</span></div> |
| <div class="line"><a name="l00306"></a><span class="lineno"> 306</span> <span class="comment">) RETURNS VOID AS $$</span></div> |
| <div class="line"><a name="l00307"></a><span class="lineno"> 307</span> <span class="comment">BEGIN</span></div> |
| <div class="line"><a name="l00308"></a><span class="lineno"> 308</span> <span class="comment"> PERFORM MADLIB_SCHEMA.cross_validation($1, $2, $3, $4, $5, $6, $7, 10);</span></div> |
| <div class="line"><a name="l00309"></a><span class="lineno"> 309</span> <span class="comment">END;</span></div> |
| <div class="line"><a name="l00310"></a><span class="lineno"> 310</span> <span class="comment">$$ LANGUAGE plpgsql VOLATILE;</span></div> |
| <div class="line"><a name="l00311"></a><span class="lineno"> 311</span> <span class="comment">*/</span></div> |
| <div class="line"><a name="l00312"></a><span class="lineno"> 312</span> -- ------------------------------------------------------------------------</div> |
| <div class="line"><a name="l00313"></a><span class="lineno"> 313</span> <span class="comment"></span></div> |
| <div class="line"><a name="l00314"></a><span class="lineno"> 314</span> <span class="comment">/**</span></div> |
| <div class="line"><a name="l00315"></a><span class="lineno"> 315</span> <span class="comment"> * @brief Print the help message for a given module's cross-validation.</span></div> |
| <div class="line"><a name="l00316"></a><span class="lineno"> 316</span> <span class="comment"> */</span></div> |
| <div class="line"><a name="l00317"></a><span class="lineno"> 317</span> <span class="comment">/*</span></div> |
| <div class="line"><a name="l00318"></a><span class="lineno"> 318</span> <span class="comment">CREATE OR REPLACE FUNCTION MADLIB_SCHEMA.cross_validation(module_name VARCHAR)</span></div> |
| <div class="line"><a name="l00319"></a><span class="lineno"> 319</span> <span class="comment">RETURNS VARCHAR AS $$</span></div> |
| <div class="line"><a name="l00320"></a><span class="lineno"> 320</span> <span class="comment">PythonFunction(validation, cross_validation, cross_validation_help)</span></div> |
| <div class="line"><a name="l00321"></a><span class="lineno"> 321</span> <span class="comment">$$ LANGUAGE plpythonu;</span></div> |
| <div class="line"><a name="l00322"></a><span class="lineno"> 322</span> <span class="comment">*/</span></div> |
| <div class="line"><a name="l00323"></a><span class="lineno"> 323</span> -- ------------------------------------------------------------------------</div> |
| <div class="line"><a name="l00324"></a><span class="lineno"> 324</span> <span class="comment"></span></div> |
| <div class="line"><a name="l00325"></a><span class="lineno"> 325</span> <span class="comment">/**</span></div> |
| <div class="line"><a name="l00326"></a><span class="lineno"> 326</span> <span class="comment"> * @brief Print the supported module names for cross_validation</span></div> |
| <div class="line"><a name="l00327"></a><span class="lineno"> 327</span> <span class="comment"> */</span></div> |
| <div class="line"><a name="l00328"></a><span class="lineno"> 328</span>  <span class="comment">/*</span></div> |
| <div class="line"><a name="l00329"></a><span class="lineno"> 329</span> <span class="comment">CREATE OR REPLACE FUNCTION MADLIB_SCHEMA.cross_validation()</span></div> |
| <div class="line"><a name="l00330"></a><span class="lineno"> 330</span> <span class="comment">RETURNS VARCHAR AS $$</span></div> |
| <div class="line"><a name="l00331"></a><span class="lineno"> 331</span> <span class="comment">DECLARE</span></div> |
| <div class="line"><a name="l00332"></a><span class="lineno"> 332</span> <span class="comment"> msg VARCHAR;</span></div> |
| <div class="line"><a name="l00333"></a><span class="lineno"> 333</span> <span class="comment">BEGIN</span></div> |
| <div class="line"><a name="l00334"></a><span class="lineno"> 334</span> <span class="comment"> msg := 'cross_validation function now supports Ridge linear regression';</span></div> |
| <div class="line"><a name="l00335"></a><span class="lineno"> 335</span> <span class="comment"> return msg;</span></div> |
| <div class="line"><a name="l00336"></a><span class="lineno"> 336</span> <span class="comment">END;</span></div> |
| <div class="line"><a name="l00337"></a><span class="lineno"> 337</span> <span class="comment">$$ LANGUAGE plpgsql STRICT;</span></div> |
| <div class="line"><a name="l00338"></a><span class="lineno"> 338</span> <span class="comment">*/</span></div> |
| <div class="line"><a name="l00339"></a><span class="lineno"> 339</span> ------------------------------------------------------------------------</div> |
| <div class="line"><a name="l00340"></a><span class="lineno"> 340</span> <span class="comment"></span></div> |
| <div class="line"><a name="l00341"></a><span class="lineno"> 341</span> <span class="comment">/**</span></div> |
| <div class="line"><a name="l00342"></a><span class="lineno"> 342</span> <span class="comment"> * @brief A wrapper for linear regression</span></div> |
| <div class="line"><a name="l00343"></a><span class="lineno"> 343</span> <span class="comment"> */</span></div> |
| <div class="line"><a name="l00344"></a><span class="lineno"> 344</span> CREATE OR REPLACE FUNCTION MADLIB_SCHEMA.cv_linregr_train(</div> |
| <div class="line"><a name="l00345"></a><span class="lineno"> 345</span>  tbl_source VARCHAR,</div> |
| <div class="line"><a name="l00346"></a><span class="lineno"> 346</span>  col_ind_var VARCHAR,</div> |
| <div class="line"><a name="l00347"></a><span class="lineno"> 347</span>  col_dep_var VARCHAR,</div> |
| <div class="line"><a name="l00348"></a><span class="lineno"> 348</span>  tbl_result VARCHAR</div> |
| <div class="line"><a name="l00349"></a><span class="lineno"> 349</span> ) RETURNS VOID AS $$</div> |
| <div class="line"><a name="l00350"></a><span class="lineno"> 350</span> PythonFunction(validation, cross_validation, <a class="code" href="cross__validation_8sql__in.html#aa151eb3fa9acc7f4cc33236e22ad4362" title="Simple interface of cross-validation, which has no limitation on lock number. ">cv_linregr_train</a>)</div> |
| <div class="line"><a name="l00351"></a><span class="lineno"> 351</span> $$ LANGUAGE plpythonu;</div> |
| <div class="line"><a name="l00352"></a><span class="lineno"> 352</span> </div> |
| <div class="line"><a name="l00353"></a><span class="lineno"> 353</span> CREATE OR REPLACE FUNCTION MADLIB_SCHEMA.linregr_predict(</div> |
| <div class="line"><a name="l00354"></a><span class="lineno"> 354</span>  coef DOUBLE PRECISION[],</div> |
| <div class="line"><a name="l00355"></a><span class="lineno"> 355</span>  col_ind DOUBLE PRECISION[]</div> |
| <div class="line"><a name="l00356"></a><span class="lineno"> 356</span> ) RETURNS DOUBLE PRECISION AS $$</div> |
| <div class="line"><a name="l00357"></a><span class="lineno"> 357</span> PythonFunction(validation, cross_validation, linregr_predict)</div> |
| <div class="line"><a name="l00358"></a><span class="lineno"> 358</span> $$ LANGUAGE plpythonu;</div> |
| <div class="line"><a name="l00359"></a><span class="lineno"> 359</span> <span class="comment"></span></div> |
| <div class="line"><a name="l00360"></a><span class="lineno"> 360</span> <span class="comment">/**</span></div> |
| <div class="line"><a name="l00361"></a><span class="lineno"> 361</span> <span class="comment"> * @brief A wrapper for linear regression prediction</span></div> |
| <div class="line"><a name="l00362"></a><span class="lineno"> 362</span> <span class="comment"> */</span></div> |
| <div class="line"><a name="l00363"></a><span class="lineno"> 363</span> CREATE OR REPLACE FUNCTION MADLIB_SCHEMA.cv_linregr_predict(</div> |
| <div class="line"><a name="l00364"></a><span class="lineno"> 364</span>  tbl_model VARCHAR,</div> |
| <div class="line"><a name="l00365"></a><span class="lineno"> 365</span>  tbl_newdata VARCHAR,</div> |
| <div class="line"><a name="l00366"></a><span class="lineno"><a class="code" href="cross__validation_8sql__in.html#aa151eb3fa9acc7f4cc33236e22ad4362"> 366</a></span>  col_ind_var VARCHAR,</div> |
| <div class="line"><a name="l00367"></a><span class="lineno"> 367</span>  col_id VARCHAR, -- ID column</div> |
| <div class="line"><a name="l00368"></a><span class="lineno"> 368</span>  tbl_predict VARCHAR</div> |
| <div class="line"><a name="l00369"></a><span class="lineno"> 369</span> ) RETURNS VOID AS $$</div> |
| <div class="line"><a name="l00370"></a><span class="lineno"> 370</span> PythonFunction(validation, cross_validation, <a class="code" href="cross__validation_8sql__in.html#aa572f1f57c0dd106b30948928161d8cc" title="A wrapper for linear regression prediction. ">cv_linregr_predict</a>)</div> |
| <div class="line"><a name="l00371"></a><span class="lineno"> 371</span> $$ LANGUAGE plpythonu;</div> |
| <div class="line"><a name="l00372"></a><span class="lineno"> 372</span> </div> |
| <div class="line"><a name="l00373"></a><span class="lineno"> 373</span> -- compare the prediction and actual values</div> |
| <div class="line"><a name="l00374"></a><span class="lineno"> 374</span> CREATE OR REPLACE FUNCTION MADLIB_SCHEMA.mse_error(</div> |
| <div class="line"><a name="l00375"></a><span class="lineno"> 375</span>  tbl_prediction VARCHAR, -- predicted values</div> |
| <div class="line"><a name="l00376"></a><span class="lineno"> 376</span>  tbl_actual VARCHAR,</div> |
| <div class="line"><a name="l00377"></a><span class="lineno"> 377</span>  id_actual VARCHAR,</div> |
| <div class="line"><a name="l00378"></a><span class="lineno"> 378</span>  values_actual VARCHAR,</div> |
| <div class="line"><a name="l00379"></a><span class="lineno"> 379</span>  tbl_error VARCHAR</div> |
| <div class="line"><a name="l00380"></a><span class="lineno"> 380</span> ) RETURNS VOID AS $$</div> |
| <div class="line"><a name="l00381"></a><span class="lineno"> 381</span> DECLARE</div> |
| <div class="line"><a name="l00382"></a><span class="lineno"> 382</span>  error DOUBLE PRECISION;</div> |
| <div class="line"><a name="l00383"></a><span class="lineno"> 383</span>  old_messages VARCHAR; </div> |
| <div class="line"><a name="l00384"></a><span class="lineno"> 384</span> BEGIN</div> |
| <div class="line"><a name="l00385"></a><span class="lineno"><a class="code" href="cross__validation_8sql__in.html#aa572f1f57c0dd106b30948928161d8cc"> 385</a></span>  old_messages := (SELECT setting FROM pg_settings WHERE name = <span class="stringliteral">'client_min_messages'</span>);</div> |
| <div class="line"><a name="l00386"></a><span class="lineno"> 386</span>  EXECUTE <span class="stringliteral">'SET client_min_messages TO warning'</span>;</div> |
| <div class="line"><a name="l00387"></a><span class="lineno"> 387</span> </div> |
| <div class="line"><a name="l00388"></a><span class="lineno"> 388</span>  EXECUTE <span class="stringliteral">'</span></div> |
| <div class="line"><a name="l00389"></a><span class="lineno"> 389</span> <span class="stringliteral"> CREATE TABLE '</span>|| tbl_error ||<span class="stringliteral">' AS</span></div> |
| <div class="line"><a name="l00390"></a><span class="lineno"> 390</span> <span class="stringliteral"> SELECT</span></div> |
| <div class="line"><a name="l00391"></a><span class="lineno"> 391</span> <span class="stringliteral"> avg(('</span>|| tbl_prediction ||<span class="stringliteral">'.prediction - '</span>|| tbl_actual ||<span class="charliteral">'.'</span>|| values_actual ||<span class="stringliteral">')^2) as mean_squared_error</span></div> |
| <div class="line"><a name="l00392"></a><span class="lineno"> 392</span> <span class="stringliteral"> FROM</span></div> |
| <div class="line"><a name="l00393"></a><span class="lineno"> 393</span> <span class="stringliteral"> '</span>|| tbl_prediction ||<span class="stringliteral">',</span></div> |
| <div class="line"><a name="l00394"></a><span class="lineno"> 394</span> <span class="stringliteral"> '</span>|| tbl_actual ||<span class="stringliteral">'</span></div> |
| <div class="line"><a name="l00395"></a><span class="lineno"> 395</span> <span class="stringliteral"> WHERE</span></div> |
| <div class="line"><a name="l00396"></a><span class="lineno"> 396</span> <span class="stringliteral"> '</span>|| tbl_prediction ||<span class="stringliteral">'.id = '</span>|| tbl_actual ||<span class="charliteral">'.'</span>|| id_actual;</div> |
| <div class="line"><a name="l00397"></a><span class="lineno"> 397</span> </div> |
| <div class="line"><a name="l00398"></a><span class="lineno"> 398</span>  EXECUTE <span class="stringliteral">'SET client_min_messages TO '</span> || old_messages;</div> |
| <div class="line"><a name="l00399"></a><span class="lineno"> 399</span> END;</div> |
| <div class="line"><a name="l00400"></a><span class="lineno"> 400</span> $$ LANGUAGE plpgsql VOLATILE;</div> |
| <div class="line"><a name="l00401"></a><span class="lineno"> 401</span> </div> |
| <div class="line"><a name="l00402"></a><span class="lineno"> 402</span> ------------------------------------------------------------------------</div> |
| <div class="line"><a name="l00403"></a><span class="lineno"> 403</span> <span class="comment"></span></div> |
| <div class="line"><a name="l00404"></a><span class="lineno"> 404</span> <span class="comment">/**</span></div> |
| <div class="line"><a name="l00405"></a><span class="lineno"> 405</span> <span class="comment"> * @brief A prediction function for logistic regression</span></div> |
| <div class="line"><a name="l00406"></a><span class="lineno"> 406</span> <span class="comment"> *</span></div> |
| <div class="line"><a name="l00407"></a><span class="lineno"> 407</span> <span class="comment"> * @param coef Coefficients. Note: MADlib logregr_train function does not produce a seperate intercept term</span></div> |
| <div class="line"><a name="l00408"></a><span class="lineno"> 408</span> <span class="comment"> * as elastic_net_train function.</span></div> |
| <div class="line"><a name="l00409"></a><span class="lineno"> 409</span> <span class="comment"> * @param col_ind Independent variable, which must be an array</span></div> |
| <div class="line"><a name="l00410"></a><span class="lineno"> 410</span> <span class="comment"> *</span></div> |
| <div class="line"><a name="l00411"></a><span class="lineno"> 411</span> <span class="comment"> */</span></div> |
| <div class="line"><a name="l00412"></a><span class="lineno"> 412</span> CREATE OR REPLACE FUNCTION MADLIB_SCHEMA.logregr_predict(</div> |
| <div class="line"><a name="l00413"></a><span class="lineno"> 413</span>  coef DOUBLE PRECISION[],</div> |
| <div class="line"><a name="l00414"></a><span class="lineno"> 414</span>  col_ind DOUBLE PRECISION[]</div> |
| <div class="line"><a name="l00415"></a><span class="lineno"> 415</span> ) RETURNS BOOLEAN AS $$</div> |
| <div class="line"><a name="l00416"></a><span class="lineno"> 416</span> PythonFunction(validation, cross_validation, <a class="code" href="cross__validation_8sql__in.html#a66b3cb92a758ed6ea3b8da7c6dfa516c" title="A prediction function for logistic regression. ">logregr_predict</a>)</div> |
| <div class="line"><a name="l00417"></a><span class="lineno"> 417</span> $$ LANGUAGE plpythonu;</div> |
| <div class="line"><a name="l00418"></a><span class="lineno"> 418</span> <span class="comment"></span></div> |
| <div class="line"><a name="l00419"></a><span class="lineno"> 419</span> <span class="comment">/**</span></div> |
| <div class="line"><a name="l00420"></a><span class="lineno"> 420</span> <span class="comment"> * @brief A prediction function for logistic regression</span></div> |
| <div class="line"><a name="l00421"></a><span class="lineno"> 421</span> <span class="comment"> * The result is stored in the table of tbl_predict</span></div> |
| <div class="line"><a name="l00422"></a><span class="lineno"> 422</span> <span class="comment"> *</span></div> |
| <div class="line"><a name="l00423"></a><span class="lineno"> 423</span> <span class="comment"> * This function can be used together with cross-validation</span></div> |
| <div class="line"><a name="l00424"></a><span class="lineno"> 424</span> <span class="comment"> */</span></div> |
| <div class="line"><a name="l00425"></a><span class="lineno"> 425</span> CREATE OR REPLACE FUNCTION MADLIB_SCHEMA.cv_logregr_predict(</div> |
| <div class="line"><a name="l00426"></a><span class="lineno"> 426</span>  tbl_model VARCHAR,</div> |
| <div class="line"><a name="l00427"></a><span class="lineno"> 427</span>  tbl_newdata VARCHAR,</div> |
| <div class="line"><a name="l00428"></a><span class="lineno"> 428</span>  col_ind_var VARCHAR,</div> |
| <div class="line"><a name="l00429"></a><span class="lineno"> 429</span>  col_id VARCHAR,</div> |
| <div class="line"><a name="l00430"></a><span class="lineno"> 430</span>  tbl_predict VARCHAR</div> |
| <div class="line"><a name="l00431"></a><span class="lineno"> 431</span> ) RETURNS VOID AS $$</div> |
| <div class="line"><a name="l00432"></a><span class="lineno"> 432</span> PythonFunction(validation, cross_validation, <a class="code" href="cross__validation_8sql__in.html#ac7dbc115f0c4624ccbf62b2d5494388d" title="A prediction function for logistic regression The result is stored in the table of tbl_predict...">cv_logregr_predict</a>)</div> |
| <div class="line"><a name="l00433"></a><span class="lineno"> 433</span> $$ LANGUAGE plpythonu;</div> |
| <div class="line"><a name="l00434"></a><span class="lineno"><a class="code" href="cross__validation_8sql__in.html#a66b3cb92a758ed6ea3b8da7c6dfa516c"> 434</a></span> <span class="comment"></span></div> |
| <div class="line"><a name="l00435"></a><span class="lineno"> 435</span> <span class="comment">/**</span></div> |
| <div class="line"><a name="l00436"></a><span class="lineno"> 436</span> <span class="comment"> * @brief Metric function for logistic regression</span></div> |
| <div class="line"><a name="l00437"></a><span class="lineno"> 437</span> <span class="comment"> *</span></div> |
| <div class="line"><a name="l00438"></a><span class="lineno"> 438</span> <span class="comment"> * @param coef Logistic fitting coefficients. Note: MADlib logregr_train function does not produce a seperate intercept term</span></div> |
| <div class="line"><a name="l00439"></a><span class="lineno"> 439</span> <span class="comment"> * as elastic_net_train function.</span></div> |
| <div class="line"><a name="l00440"></a><span class="lineno"> 440</span> <span class="comment"> * @param col_ind Independent variable, an array</span></div> |
| <div class="line"><a name="l00441"></a><span class="lineno"> 441</span> <span class="comment"> * @param col_dep Dependent variable</span></div> |
| <div class="line"><a name="l00442"></a><span class="lineno"> 442</span> <span class="comment"> *</span></div> |
| <div class="line"><a name="l00443"></a><span class="lineno"> 443</span> <span class="comment"> * returns 1 if the prediction is the same as col_dep, otherwise 0</span></div> |
| <div class="line"><a name="l00444"></a><span class="lineno"> 444</span> <span class="comment"> */</span></div> |
| <div class="line"><a name="l00445"></a><span class="lineno"> 445</span> CREATE OR REPLACE FUNCTION MADLIB_SCHEMA.logregr_accuracy(</div> |
| <div class="line"><a name="l00446"></a><span class="lineno"> 446</span>  coef DOUBLE PRECISION[],</div> |
| <div class="line"><a name="l00447"></a><span class="lineno"><a class="code" href="cross__validation_8sql__in.html#ac7dbc115f0c4624ccbf62b2d5494388d"> 447</a></span>  col_ind DOUBLE PRECISION[],</div> |
| <div class="line"><a name="l00448"></a><span class="lineno"> 448</span>  col_dep BOOLEAN</div> |
| <div class="line"><a name="l00449"></a><span class="lineno"> 449</span> ) RETURNS INTEGER AS $$</div> |
| <div class="line"><a name="l00450"></a><span class="lineno"> 450</span> PythonFunction(validation, cross_validation, <a class="code" href="cross__validation_8sql__in.html#a2d1571ffa794176a5dfed9d35e70fed7" title="Metric function for logistic regression. ">logregr_accuracy</a>)</div> |
| <div class="line"><a name="l00451"></a><span class="lineno"> 451</span> $$ LANGUAGE plpythonu;</div> |
| <div class="line"><a name="l00452"></a><span class="lineno"> 452</span> <span class="comment"></span></div> |
| <div class="line"><a name="l00453"></a><span class="lineno"> 453</span> <span class="comment">/**</span></div> |
| <div class="line"><a name="l00454"></a><span class="lineno"> 454</span> <span class="comment"> * @brief Metric function for logistic regression</span></div> |
| <div class="line"><a name="l00455"></a><span class="lineno"> 455</span> <span class="comment"> *</span></div> |
| <div class="line"><a name="l00456"></a><span class="lineno"> 456</span> <span class="comment"> * It computes the percentage of correct predictions.</span></div> |
| <div class="line"><a name="l00457"></a><span class="lineno"> 457</span> <span class="comment"> * The result is stored in the table of tbl_accuracy</span></div> |
| <div class="line"><a name="l00458"></a><span class="lineno"> 458</span> <span class="comment"> */</span></div> |
| <div class="line"><a name="l00459"></a><span class="lineno"> 459</span> CREATE OR REPLACE FUNCTION MADLIB_SCHEMA.cv_logregr_accuracy(</div> |
| <div class="line"><a name="l00460"></a><span class="lineno"> 460</span>  tbl_predict VARCHAR,</div> |
| <div class="line"><a name="l00461"></a><span class="lineno"> 461</span>  tbl_source VARCHAR,</div> |
| <div class="line"><a name="l00462"></a><span class="lineno"> 462</span>  col_id VARCHAR,</div> |
| <div class="line"><a name="l00463"></a><span class="lineno"> 463</span>  col_dep_var VARCHAR,</div> |
| <div class="line"><a name="l00464"></a><span class="lineno"> 464</span>  tbl_accuracy VARCHAR</div> |
| <div class="line"><a name="l00465"></a><span class="lineno"> 465</span> ) RETURNS VOID AS $$</div> |
| <div class="line"><a name="l00466"></a><span class="lineno"> 466</span> PythonFunction(validation, cross_validation, <a class="code" href="cross__validation_8sql__in.html#ac1b5c57473ff672af45191c8d53f46ed" title="Metric function for logistic regression. ">cv_logregr_accuracy</a>)</div> |
| <div class="line"><a name="l00467"></a><span class="lineno"><a class="code" href="cross__validation_8sql__in.html#a2d1571ffa794176a5dfed9d35e70fed7"> 467</a></span> $$ LANGUAGE plpythonu;</div> |
| </div><!-- fragment --></div><!-- contents --> |
| </div><!-- doc-content --> |
| <!-- start footer part --> |
| <div id="nav-path" class="navpath"><!-- id is needed for treeview function! --> |
| <ul> |
| <li class="navelem"><a class="el" href="dir_68267d1309a1af8e8297ef4c3efbcdba.html">src</a></li><li class="navelem"><a class="el" href="dir_efbcf68973d247bbf15f9eecae7f24e3.html">ports</a></li><li class="navelem"><a class="el" href="dir_a4a48839224ef8488facbffa8a397967.html">postgres</a></li><li class="navelem"><a class="el" href="dir_dc596537ad427a4d866006d1a3e1fe29.html">modules</a></li><li class="navelem"><a class="el" href="dir_9f5e6edf0db58b0627c46b41dbbbb27f.html">validation</a></li><li class="navelem"><a class="el" href="cross__validation_8sql__in.html">cross_validation.sql_in</a></li> |
| <li class="footer">Generated on Tue Sep 10 2013 15:48:04 for MADlib by |
| <a href="http://www.doxygen.org/index.html"> |
| <img class="footer" src="doxygen.png" alt="doxygen"/></a> 1.8.4 </li> |
| </ul> |
| </div> |
| </body> |
| </html> |
