| Previous changeset 7:57a7471292df (2018-07-10) Next changeset 9:c6b3efcba7bd (2018-08-04) |
|
Commit message:
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/sklearn commit f54ff2ba2f8e7542d68966ce5a6b17d7f624ac48 |
|
modified:
main_macros.xml model_validation.xml |
|
removed:
test-data/mv_result07.tabular |
| b |
| diff -r 57a7471292df -r fd7a054ffdbd main_macros.xml --- a/main_macros.xml Tue Jul 10 03:13:16 2018 -0400 +++ b/main_macros.xml Fri Jul 13 03:56:45 2018 -0400 |
| [ |
| b'@@ -35,7 +35,8 @@\n if not options[\'threshold\'] or options[\'threshold\'] == \'None\':\n options[\'threshold\'] = None\n if \'extra_estimator\' in inputs and inputs[\'extra_estimator\'][\'has_estimator\'] == \'no_load\':\n- fitted_estimator = pickle.load(open("inputs[\'extra_estimator\'][\'fitted_estimator\']", \'r\'))\n+ with open("inputs[\'extra_estimator\'][\'fitted_estimator\']", \'rb\') as model_handler:\n+ fitted_estimator = pickle.load(model_handler)\n new_selector = selector(fitted_estimator, prefit=True, **options)\n else:\n estimator=inputs["estimator"]\n@@ -83,7 +84,7 @@\n parse_dates=True\n )\n else:\n- X = mmread(open(file1, \'r\'))\n+ X = mmread(file1)\n \n header = \'infer\' if params["selected_tasks"]["selected_algorithms"]["input_options"]["header2"] else None\n column_option = params["selected_tasks"]["selected_algorithms"]["input_options"]["column_selector_options_2"]["selected_column_selector_option2"]\n@@ -432,19 +433,6 @@\n \n \n <!--Data interface-->\n- <xml name="tabular_input">\n- <param name="infile" type="data" format="tabular" label="Data file with numeric values"/>\n- <param name="start_column" type="data_column" data_ref="infile" optional="True" label="Select a subset of data. Start column:" />\n- <param name="end_column" type="data_column" data_ref="infile" optional="True" label="End column:" />\n- </xml>\n-\n- <xml name="sample_cols" token_label1="File containing true class labels:" token_label2="File containing predicted class labels:" token_multiple1="False" token_multiple2="False" token_format1="tabular" token_format2="tabular" token_help1="" token_help2="">\n- <param name="infile1" type="data" format="@FORMAT1@" label="@LABEL1@" help="@HELP1@"/>\n- <param name="col1" multiple="@MULTIPLE1@" type="data_column" data_ref="infile1" label="Select target column(s):"/>\n- <param name="infile2" type="data" format="@FORMAT2@" label="@LABEL2@" help="@HELP2@"/>\n- <param name="col2" multiple="@MULTIPLE2@" type="data_column" data_ref="infile2" label="Select target column(s):"/>\n- <yield/>\n- </xml>\n \n <xml name="samples_tabular" token_multiple1="false" token_multiple2="false">\n <param name="infile1" type="data" format="tabular" label="Training samples dataset:"/>\n@@ -472,13 +460,13 @@\n <param name="@COL_NAME@" multiple="@MULTIPLE@" type="data_column" data_ref="@INFILE@" label="Select target column(s):"/>\n </when>\n <when value="by_header_name">\n- <param name="@COL_NAME@" type="text" value="" label="Type header name(s):" help="String seperate by colon. For example: target1,target2"/>\n+ <param name="@COL_NAME@" type="text" value="" label="Type header name(s):" help="Comma-separated string. For example: target1,target2"/>\n </when>\n <when value="all_but_by_index_number">\n <param name="@COL_NAME@" multiple="@MULTIPLE@" type="data_column" data_ref="@INFILE@" label="Select target column(s):"/>\n </when>\n <when value="all_but_by_header_name">\n- <param name="@COL_NAME@" type="text" value="" label="Type header name(s):" help="String seperate by colon. For example: target1,target2"/>\n+ <param name="@COL_NAME@" type="text" value="" label="Type header name(s):" help="Comma-separated string. For example: target1,target2"/>\n </when>\n <when value="all_columns">\n </when>\n@@ -553,11 +541,6 @@\n </conditional>\n </xml>\n \n- <xml name="multitype_input" token_format="tabular" token_help="All datasets with tabular format are supporetd.">\n- <param name="infile_transform" type="data" format="@FORMAT@" label="Select a dataset to transform:" help="@HELP@"/>\n- </xml>\n-\n-\n <!--Advanced options-->\n <xml name="nn_advanced_options">\n <section name="options" title="Advanced Options" expanded="False">\n@@ -822,9 +805,17 @@\n </param>\n </xml>\n \n+ <xml name="sparse_preprocessors_ext">\n+ <expand macro="sparse_preprocessors">\n+ <option value="KernelCenterer">Kernel Centerer (Centers a kernel '..b' Options" expanded="False">\n+ <!--feature_range-->\n+ <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true"\n+ label="Use a copy of data for precomputing normalization" help=" "/>\n+ </section>\n+ </when>\n+ <when value="PolynomialFeatures">\n+ <section name="options" title="Advanced Options" expanded="False">\n+ <param argument="degree" type="integer" optional="true" value="2" label="The degree of the polynomial features " help=""/>\n+ <param argument="interaction_only" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="false" label="Produce interaction features only" help="(Features that are products of at most degree distinct input features) "/>\n+ <param argument="include_bias" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true" label="Include a bias column" help="Feature in which all polynomial powers are zero "/>\n+ </section>\n+ </when>\n+ <when value="RobustScaler">\n+ <section name="options" title="Advanced Options" expanded="False">\n+ <!--=True, =True, copy=True-->\n+ <param argument="with_centering" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true"\n+ label="Center the data before scaling" help=" "/>\n+ <param argument="with_scaling" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true"\n+ label="Scale the data to interquartile range" help=" "/>\n+ <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true"\n+ label="Use a copy of data for inplace scaling" help=" "/>\n+ </section>\n+ </when>\n+ </expand>\n+ </xml>\n+\n <xml name="estimator_input_no_fit">\n <expand macro="feature_selection_estimator" />\n <conditional name="extra_estimator">\n@@ -892,6 +914,7 @@\n <expand macro="feature_selection_estimator_choices" />\n </conditional>\n </xml>\n+\n <xml name="feature_selection_all">\n <conditional name="feature_selection_algorithms">\n <param name="selected_algorithm" type="select" label="Select a feature selection algorithm">\n@@ -1014,6 +1037,7 @@\n </when-->\n </conditional>\n </xml>\n+\n <xml name="feature_selection_score_function">\n <param argument="score_func" type="select" label="Select a score function">\n <option value="chi2">chi2 - Compute chi-squared stats between each non-negative feature and class</option>\n@@ -1023,6 +1047,7 @@\n <option value="mutual_info_regression">mutual_info_regression - Estimate mutual information for a continuous target variable</option>\n </param>\n </xml>\n+\n <xml name="feature_selection_estimator">\n <param argument="estimator" type="select" label="Select an estimator" help="The base estimator from which the transformer is built.">\n <option value="svm.SVR(kernel="linear")">svm.SVR(kernel="linear")</option>\n@@ -1032,6 +1057,7 @@\n <option value="ensemble.RandomForestRegressor(n_estimators = 1000, random_state = 42)">ensemble.RandomForestRegressor(n_estimators = 1000, random_state = 42)</option>\n </param>\n </xml>\n+\n <xml name="feature_selection_extra_estimator"> \n <param name="has_estimator" type="select" label="Does your estimator on the list above?">\n <option value="yes">Yes, my estimator is on the list</option>\n@@ -1039,6 +1065,7 @@\n <yield/>\n </param>\n </xml>\n+\n <xml name="feature_selection_estimator_choices">\n <when value="yes">\n </when>\n@@ -1047,6 +1074,7 @@\n </when>\n <yield/>\n </xml>\n+\n <xml name="feature_selection_methods">\n <conditional name="select_methods">\n <param name="selected_method" type="select" label="Select an operation">\n' |
| b |
| diff -r 57a7471292df -r fd7a054ffdbd model_validation.xml --- a/model_validation.xml Tue Jul 10 03:13:16 2018 -0400 +++ b/model_validation.xml Fri Jul 13 03:56:45 2018 -0400 |
| [ |
| @@ -22,7 +22,7 @@ import pickle import numpy as np import sklearn.model_selection -from sklearn import svm, linear_model, ensemble +from sklearn import svm, linear_model, ensemble, preprocessing from sklearn.pipeline import Pipeline @COLUMNS_FUNCTION@ @@ -30,7 +30,8 @@ @FEATURE_SELECTOR_FUNCTION@ input_json_path = sys.argv[1] -params = json.load(open(input_json_path, "r")) +with open(input_json_path, "r") as param_handler: + params = json.load(param_handler) input_type = params["input_options"]["selected_input"] if input_type=="tabular": @@ -49,7 +50,7 @@ parse_dates=True ) else: - X = mmread(open("$input_options.infile1", 'r')) + X = mmread("$input_options.infile1") header = 'infer' if params["input_options"]["header2"] else None column_option = params["input_options"]["column_selector_options_2"]["selected_column_selector_option2"] @@ -75,10 +76,17 @@ pipeline_steps = [] +## Set up pre_processor and add to pipeline steps. +if params['pre_processing']['do_pre_processing'] == 'Yes': + preprocessor = params["pre_processing"]["pre_processors"]["selected_pre_processor"] + pre_processor_options = params["pre_processing"]["pre_processors"]["options"] + my_class = getattr(preprocessing, preprocessor) + pipeline_steps.append( ('pre_processor', my_class(**pre_processor_options)) ) + ## Set up feature selector and add to pipeline steps. if params['feature_selection']['do_feature_selection'] == 'Yes': feature_selector = feature_selector(params['feature_selection']['feature_selection_algorithms']) - pipeline_steps.append( ('feature_selector', feature_selector)) + pipeline_steps.append( ('feature_selector', feature_selector) ) ## Set up estimator and add to pipeline. estimator=params["model_validation_functions"]["estimator"] @@ -138,6 +146,19 @@ </configfile> </configfiles> <inputs> + <conditional name="pre_processing"> + <param name="do_pre_processing" type="select" label="Do pre_processing?"> + <option value="No" selected="true"/> + <option value="Yes"/> + </param> + <when value="No"/> + <when value="Yes"> + <conditional name="pre_processors"> + <expand macro="sparse_preprocessors_ext" /> + <expand macro="sparse_preprocessor_options_ext" /> + </conditional> + </when> + </conditional> <conditional name="feature_selection"> <param name="do_feature_selection" type="select" label="Do feature selection?"> <option value="No" selected="true"/> @@ -352,7 +373,54 @@ <param name="infile2" value="regression_y.tabular" ftype="tabular"/> <param name="header2" value="true" /> <param name="selected_column_selector_option2" value="all_columns"/> - <output name="outfile" file="mv_result07.tabular"/> + <output name="outfile" > + <assert_contents> + <has_line line="0.7824428015300172" /> + </assert_contents> + </output> + </test> + <test> + <param name="do_pre_processing" value="Yes"/> + <param name="selected_pre_processor" value="RobustScaler"/> + <param name="do_feature_selection" value="Yes"/> + <param name="selected_algorithm" value="SelectKBest"/> + <param name="score_func" value="f_classif"/> + <param name="selected_function" value="GridSearchCV"/> + <param name="estimator" value="svm.SVR(kernel="linear")"/> + <param name="has_estimator" value="yes"/> + <param name="param_grid" value="[{'feature_selector__k': [3, 5, 7, 9], 'estimator__C': [1, 10, 100, 1000]}]"/> + <param name="return_type" value="best_score_"/> + <param name="infile1" value="regression_X.tabular" ftype="tabular"/> + <param name="header1" value="true" /> + <param name="selected_column_selector_option" value="all_columns"/> + <param name="infile2" value="regression_y.tabular" ftype="tabular"/> + <param name="header2" value="true" /> + <param name="selected_column_selector_option2" value="all_columns"/> + <output name="outfile" > + <assert_contents> + <has_line line="0.7938837807353147" /> + </assert_contents> + </output> + </test> + <test> + <param name="do_pre_processing" value="Yes"/> + <param name="selected_pre_processor" value="RobustScaler"/> + <param name="selected_function" value="GridSearchCV"/> + <param name="estimator" value="svm.SVR(kernel="linear")"/> + <param name="has_estimator" value="yes"/> + <param name="param_grid" value="[{'estimator__C': [1, 10, 100, 1000]}]"/> + <param name="return_type" value="best_score_"/> + <param name="infile1" value="regression_X.tabular" ftype="tabular"/> + <param name="header1" value="true" /> + <param name="selected_column_selector_option" value="all_columns"/> + <param name="infile2" value="regression_y.tabular" ftype="tabular"/> + <param name="header2" value="true" /> + <param name="selected_column_selector_option2" value="all_columns"/> + <output name="outfile" > + <assert_contents> + <has_line line="0.7904476204861263" /> + </assert_contents> + </output> </test> </tests> <help> |
| b |
| diff -r 57a7471292df -r fd7a054ffdbd test-data/mv_result07.tabular --- a/test-data/mv_result07.tabular Tue Jul 10 03:13:16 2018 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 |
| b |
| @@ -1,1 +0,0 @@ -0.7824428015300172 |