Mercurial > repos > bgruening > sklearn_searchcv
diff search_model_validation.xml @ 8:51cabe6d4ca6 draft
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/sklearn commit c0a3a186966888e5787335a7628bf0a4382637e7
| author | bgruening |
|---|---|
| date | Tue, 14 May 2019 17:37:36 -0400 |
| parents | bd2ef98a56be |
| children | 422f6e8a492d |
line wrap: on
line diff
--- a/search_model_validation.xml Sun Dec 30 01:34:55 2018 -0500 +++ b/search_model_validation.xml Tue May 14 17:37:36 2019 -0400 @@ -3,23 +3,24 @@ <macros> <import>main_macros.xml</import> </macros> - <expand macro="python_requirements"> - <requirement type="package" version="0.6">skrebate</requirement> - <requirement type="package" version="0.4.2">imbalanced-learn</requirement> - </expand> + <expand macro="python_requirements"/> <expand macro="macro_stdio"/> <version_command>echo "@VERSION@"</version_command> <command> <![CDATA[ python '$__tool_directory__/search_model_validation.py' - '$inputs' - '$search_schemes.infile_pipeline' - '$input_options.infile1' - '$input_options.infile2' - '$outfile_result' - #if $save: - '$outfile_estimator' + --inputs '$inputs' + --estimator '$search_schemes.infile_estimator' + --infile1 '$input_options.infile1' + --infile2 '$input_options.infile2' + --outfile_result '$outfile_result' + #if $save + --outfile_object '$outfile_object' #end if + #if $search_schemes.options.cv_selector.selected_cv in ['GroupKFold', 'GroupShuffleSplit', 'LeaveOneGroupOut', 'LeavePGroupsOut'] + --groups '$inputs,$search_schemes.options.cv_selector.groups_selector.infile_g' + #end if + ]]> </command> <configfiles> @@ -27,7 +28,7 @@ </configfiles> <inputs> <conditional name="search_schemes"> - <param name="selected_search_scheme" type="select" label="Select a model selection search scheme:"> + <param name="selected_search_scheme" type="select" label="Select a model selection search scheme"> <option value="GridSearchCV" selected="true">GridSearchCV - Exhaustive search over specified parameter values for an estimator </option> <option value="RandomizedSearchCV">RandomizedSearchCV - Randomized search on hyper parameters for an estimator</option> </param> @@ -46,27 +47,46 @@ </section> </when> </conditional> - <param name="save" type="boolean" truevalue="booltrue" falsevalue="boolfalse" checked="true" label="Save the best estimator/pipeline?"/> + <param name="save" type="boolean" truevalue="booltrue" falsevalue="boolfalse" checked="true" label="Save the searchCV object"/> <expand macro="sl_mixed_input"/> + <conditional name="train_test_split"> + <param name="do_split" type="select" label="Whether to hold a portion of samples for test exclusively?" help="train_test_split"> + <option value="no">Nope</option> + <option value="yes">Yes - I do</option> + </param> + <when value='no'/> + <when value='yes'> + <param argument="test_size" type="float" optional="True" value="0.25" label="Test size:"/> + <param argument="train_size" type="float" optional="True" value="" label="Train size:"/> + <param argument="random_state" type="integer" optional="True" value="" label="Random seed number:"/> + <param argument="shuffle" type="select"> + <option value="None">None - No shuffle</option> + <option value="simple">Shuffle -- for regression problems</option> + <option value="stratified">StratifiedShuffle -- will use the target values as class labels</option> + <option value="group">GroupShuffle -- make sure group CV option is choosen</option> + </param> + </when> + </conditional> </inputs> <outputs> <data format="tabular" name="outfile_result"/> - <data format="zip" name="outfile_estimator" label="${tool.name}: best estimator on ${on_string}"> + <data format="zip" name="outfile_object" label="${search_schemes.selected_search_scheme} on ${on_string}"> <filter>save</filter> </data> </outputs> <tests> <test> <param name="selected_search_scheme" value="GridSearchCV"/> - <param name="infile_pipeline" value="pipeline01" ftype="zip"/> - <conditional name="search_param_selector"> - <param name="search_p" value="C: [1, 10, 100, 1000]"/> - <param name="selected_param_type" value="final_estimator_p"/> - </conditional> - <conditional name="search_param_selector"> - <param name="search_p" value="k: [-1, 3, 5, 7, 9]"/> - <param name="selected_param_type" value="prep_2_p"/> - </conditional> + <param name="infile_estimator" value="pipeline01" ftype="zip"/> + <param name="infile_params" value="get_params01.tabular" ftype="tabular"/> + <repeat name="param_set"> + <param name="sp_list" value="[1, 10, 100, 1000]"/> + <param name="sp_name" value="svr__C"/> + </repeat> + <repeat name="param_set"> + <param name="sp_list" value="[-1, 3, 5, 7, 9]"/> + <param name="sp_name" value="selectkbest__k"/> + </repeat> <param name="error_score" value="false"/> <param name="infile1" value="regression_X.tabular" ftype="tabular"/> <param name="header1" value="true" /> @@ -78,21 +98,22 @@ <assert_contents> <has_n_columns n="13"/> <has_text text="0.7938837807353147"/> - <has_text text="{'estimator__C': 1, 'preprocessing_2__k': 9}"/> + <has_text text="{'selectkbest__k': 9, 'svr__C': 1}"/> </assert_contents> </output> </test> <test expect_failure="true"> <param name="selected_search_scheme" value="GridSearchCV"/> - <param name="infile_pipeline" value="pipeline01" ftype="zip"/> - <conditional name="search_param_selector"> - <param name="search_p" value="C: [1, 10, 100, 1000]"/> - <param name="selected_param_type" value="final_estimator_p"/> - </conditional> - <conditional name="search_param_selector"> - <param name="search_p" value="k: [-1, 3, 5, 7, 9]"/> - <param name="selected_param_type" value="prep_2_p"/> - </conditional> + <param name="infile_estimator" value="pipeline01" ftype="zip"/> + <param name="infile_params" value="get_params01.tabular" ftype="tabular"/> + <repeat name="param_set"> + <param name="sp_list" value="[1, 10, 100, 1000]"/> + <param name="sp_name" value="svr__C"/> + </repeat> + <repeat name="param_set"> + <param name="sp_list" value="[-1, 3, 5, 7, 9]"/> + <param name="sp_name" value="selectkbest__k"/> + </repeat> <param name="error_score" value="true"/> <param name="infile1" value="regression_X.tabular" ftype="tabular"/> <param name="header1" value="true" /> @@ -103,23 +124,24 @@ </test> <test> <param name="selected_search_scheme" value="RandomizedSearchCV"/> - <param name="infile_pipeline" value="pipeline01" ftype="zip"/> - <conditional name="search_param_selector"> - <param name="search_p" value="C: [1, 10, 100, 1000]"/> - <param name="selected_param_type" value="final_estimator_p"/> - </conditional> - <conditional name="search_param_selector"> - <param name="search_p" value="kernel: ['linear', 'poly', 'rbf', 'sigmoid']"/> - <param name="selected_param_type" value="final_estimator_p"/> - </conditional> - <conditional name="search_param_selector"> - <param name="search_p" value="k: [3, 5, 7, 9]"/> - <param name="selected_param_type" value="prep_2_p"/> - </conditional> - <conditional name="search_param_selector"> - <param name="search_p" value="with_centering: [True, False]"/> - <param name="selected_param_type" value="prep_1_p"/> - </conditional> + <param name="infile_estimator" value="pipeline01" ftype="zip"/> + <param name="infile_params" value="get_params01.tabular" ftype="tabular"/> + <repeat name="param_set"> + <param name="sp_list" value="[1, 10, 100, 1000]"/> + <param name="sp_name" value="svr__C"/> + </repeat> + <repeat name="param_set"> + <param name="sp_list" value="['linear', 'poly', 'rbf', 'sigmoid']"/> + <param name="sp_name" value="svr__kernel"/> + </repeat> + <repeat name="param_set"> + <param name="sp_list" value="[3, 5, 7, 9]"/> + <param name="sp_name" value="selectkbest__k"/> + </repeat> + <repeat name="param_set"> + <param name="sp_list" value="[True, False]"/> + <param name="sp_name" value="robustscaler__with_centering"/> + </repeat> <param name="infile1" value="regression_X.tabular" ftype="tabular"/> <param name="header1" value="true" /> <param name="selected_column_selector_option" value="all_columns"/> @@ -129,29 +151,30 @@ <output name="outfile_result" > <assert_contents> <has_n_columns n="15" /> - <has_text text="param_preprocessing_1__with_centering"/> + <has_text text="param_robustscaler__with_centering"/> </assert_contents> </output> </test> <test> <param name="selected_search_scheme" value="RandomizedSearchCV"/> - <param name="infile_pipeline" value="pipeline03" ftype="zip"/> - <conditional name="search_param_selector"> - <param name="search_p" value="n_estimators: np_arange(50, 1001, 50)"/> - <param name="selected_param_type" value="final_estimator_p"/> - </conditional> - <conditional name="search_param_selector"> - <param name="search_p" value="max_depth: scipy_stats_randint(1, 51)"/> - <param name="selected_param_type" value="final_estimator_p"/> - </conditional> - <conditional name="search_param_selector"> - <param name="search_p" value="gamma: scipy_stats_uniform(0., 1.)"/> - <param name="selected_param_type" value="final_estimator_p"/> - </conditional> - <conditional name="search_param_selector"> - <param name="search_p" value="random_state: [324089]"/> - <param name="selected_param_type" value="final_estimator_p"/> - </conditional> + <param name="infile_estimator" value="pipeline03" ftype="zip"/> + <param name="infile_params" value="get_params03.tabular" ftype="tabular"/> + <repeat name="param_set"> + <param name="sp_list" value="np_arange(50, 1001, 50)"/> + <param name="sp_name" value="xgbclassifier__n_estimators"/> + </repeat> + <repeat name="param_set"> + <param name="sp_list" value="scipy_stats_randint(1, 51)"/> + <param name="sp_name" value="xgbclassifier__max_depth"/> + </repeat> + <repeat name="param_set"> + <param name="sp_list" value="scipy_stats_uniform(0., 1.)"/> + <param name="sp_name" value="xgbclassifier__gamma"/> + </repeat> + <repeat name="param_set"> + <param name="sp_list" value="[324089]"/> + <param name="sp_name" value="xgbclassifier__random_state"/> + </repeat> <param name="infile1" value="regression_X.tabular" ftype="tabular"/> <param name="header1" value="true" /> <param name="selected_column_selector_option" value="all_columns"/> @@ -161,21 +184,22 @@ <output name="outfile_result" > <assert_contents> <has_n_columns n="15" /> - <has_text text="param_estimator__max_depth"/> + <has_text text="param_xgbclassifier__max_depth"/> </assert_contents> </output> </test> <test> <param name="selected_search_scheme" value="GridSearchCV"/> - <param name="infile_pipeline" value="pipeline04" ftype="zip"/> - <conditional name="search_param_selector"> - <param name="search_p" value="random_state: list(range(100, 1001, 100))"/> - <param name="selected_param_type" value="final_estimator_p"/> - </conditional> - <conditional name="search_param_selector"> - <param name="search_p" value="estimator-: [sklearn_ensemble.ExtraTreesClassifier(n_estimators=100, random_state=324089)]"/> - <param name="selected_param_type" value="prep_1_p"/> - </conditional> + <param name="infile_estimator" value="pipeline04" ftype="zip"/> + <param name="infile_params" value="get_params04.tabular" ftype="tabular"/> + <repeat name="param_set"> + <param name="sp_list" value="list(range(100, 1001, 100))"/> + <param name="sp_name" value="linearsvc__random_state"/> + </repeat> + <repeat name="param_set"> + <param name="sp_list" value=": [sklearn_ensemble.ExtraTreesClassifier(n_estimators=100, random_state=324089)]"/> + <param name="sp_name" value="selectfrommodel__estimator"/> + </repeat> <param name="infile1" value="regression_X.tabular" ftype="tabular"/> <param name="header1" value="true" /> <param name="selected_column_selector_option" value="all_columns"/> @@ -191,30 +215,32 @@ </test> <test> <param name="selected_search_scheme" value="GridSearchCV"/> - <param name="infile_pipeline" value="pipeline01" ftype="zip"/> - <conditional name="search_param_selector"> - <param name="search_p" value="C: [1, 10, 100, 1000]"/> - <param name="selected_param_type" value="final_estimator_p"/> - </conditional> + <param name="infile_estimator" value="pipeline01" ftype="zip"/> + <param name="infile_params" value="get_params01.tabular" ftype="tabular"/> + <repeat name="param_set"> + <param name="sp_list" value="[1, 10, 100, 1000]"/> + <param name="sp_name" value="svr__C"/> + </repeat> <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_estimator" file="searchCV01" compare="sim_size" delta="1"/> + <output name="outfile_object" file="searchCV01" compare="sim_size" delta="10"/> </test> <test> <param name="selected_search_scheme" value="GridSearchCV"/> - <param name="infile_pipeline" value="pipeline06" ftype="zip"/> - <conditional name="search_param_selector"> - <param name="search_p" value="n_estimators: [10, 50, 200, 1000]"/> - <param name="selected_param_type" value="final_estimator_p"/> - </conditional> - <conditional name="search_param_selector"> - <param name="search_p" value="random_state: [324089]"/> - <param name="selected_param_type" value="final_estimator_p"/> - </conditional> + <param name="infile_estimator" value="pipeline06" ftype="zip"/> + <param name="infile_params" value="get_params06.tabular" ftype="tabular"/> + <repeat name="param_set"> + <param name="sp_list" value="[10, 50, 200, 1000]"/> + <param name="sp_name" value="adaboostregressor__n_estimators"/> + </repeat> + <repeat name="param_set"> + <param name="sp_list" value="[324089]"/> + <param name="sp_name" value="adaboostregressor__random_state"/> + </repeat> <param name="infile1" value="regression_X.tabular" ftype="tabular"/> <param name="header1" value="true" /> <param name="selected_column_selector_option" value="all_columns"/> @@ -230,19 +256,20 @@ </test> <test> <param name="selected_search_scheme" value="GridSearchCV"/> - <param name="infile_pipeline" value="pipeline07" ftype="zip"/> - <conditional name="search_param_selector"> - <param name="search_p" value="n_estimators: [10, 50, 100, 200]"/> - <param name="selected_param_type" value="final_estimator_p"/> - </conditional> - <conditional name="search_param_selector"> - <param name="search_p" value="random_state: [324089]"/> - <param name="selected_param_type" value="final_estimator_p"/> - </conditional> - <conditional name="search_param_selector"> - <param name="search_p" value="gamma: [1.0, 2.0]"/> - <param name="selected_param_type" value="prep_1_p"/> - </conditional> + <param name="infile_estimator" value="pipeline07" ftype="zip"/> + <param name="infile_params" value="get_params07.tabular" ftype="tabular"/> + <repeat name="param_set"> + <param name="sp_list" value="[10, 50, 100, 200]"/> + <param name="sp_name" value="adaboostclassifier__n_estimators"/> + </repeat> + <repeat name="param_set"> + <param name="sp_list" value="[324089]"/> + <param name="sp_name" value="adaboostclassifier__random_state"/> + </repeat> + <repeat name="param_set"> + <param name="sp_list" value="[1.0, 2.0]"/> + <param name="sp_name" value="rbfsampler__gamma"/> + </repeat> <param name='selected_cv' value="default"/> <param name="n_splits" value="3"/> <param name="infile1" value="regression_X.tabular" ftype="tabular"/> @@ -260,19 +287,20 @@ </test> <test> <param name="selected_search_scheme" value="GridSearchCV"/> - <param name="infile_pipeline" value="pipeline08" ftype="zip"/> - <conditional name="search_param_selector"> - <param name="search_p" value="n_estimators: [10, 50, 100, 200]"/> - <param name="selected_param_type" value="final_estimator_p"/> - </conditional> - <conditional name="search_param_selector"> - <param name="search_p" value="random_state: [324089]"/> - <param name="selected_param_type" value="final_estimator_p"/> - </conditional> - <conditional name="search_param_selector"> - <param name="search_p" value="linkage: ['ward', 'complete', 'average']"/> - <param name="selected_param_type" value="prep_1_p"/> - </conditional> + <param name="infile_estimator" value="pipeline08" ftype="zip"/> + <param name="infile_params" value="get_params08.tabular" ftype="tabular"/> + <repeat name="param_set"> + <param name="sp_list" value="[10, 50, 100, 200]"/> + <param name="sp_name" value="adaboostclassifier__n_estimators"/> + </repeat> + <repeat name="param_set"> + <param name="sp_list" value="[324089]"/> + <param name="sp_name" value="adaboostclassifier__random_state"/> + </repeat> + <repeat name="param_set"> + <param name="sp_list" value="['ward', 'complete', 'average']"/> + <param name="sp_name" value="featureagglomeration__linkage"/> + </repeat> <param name="infile1" value="regression_X.tabular" ftype="tabular"/> <param name="header1" value="true" /> <param name="selected_column_selector_option" value="all_columns"/> @@ -287,11 +315,12 @@ </test> <test> <param name="selected_search_scheme" value="GridSearchCV"/> - <param name="infile_pipeline" value="pipeline01" ftype="zip"/> - <conditional name="search_param_selector"> - <param name="search_p" value="C: [1, 10, 100, 1000]"/> - <param name="selected_param_type" value="final_estimator_p"/> - </conditional> + <param name="infile_estimator" value="pipeline01" ftype="zip"/> + <param name="infile_params" value="get_params01.tabular" ftype="tabular"/> + <repeat name="param_set"> + <param name="sp_list" value="[1, 10, 100, 1000]"/> + <param name="sp_name" value="svr__C"/> + </repeat> <param name='selected_cv' value="StratifiedKFold"/> <param name="n_splits" value="3"/> <param name="shuffle" value="true" /> @@ -302,19 +331,20 @@ <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_estimator" file="searchCV02" compare="sim_size" delta="1"/> + <output name="outfile_object" file="searchCV02" compare="sim_size" delta="10"/> </test> <test> <param name="selected_search_scheme" value="GridSearchCV"/> - <param name="infile_pipeline" value="pipeline03" ftype="zip"/> - <conditional name="search_param_selector"> - <param name="search_p" value="n_estimators: [10, 50, 200, 1000]"/> - <param name="selected_param_type" value="final_estimator_p"/> - </conditional> - <conditional name="search_param_selector"> - <param name="search_p" value="random_state: [324089]"/> - <param name="selected_param_type" value="final_estimator_p"/> - </conditional> + <param name="infile_estimator" value="pipeline03" ftype="zip"/> + <param name="infile_params" value="get_params03.tabular" ftype="tabular"/> + <repeat name="param_set"> + <param name="sp_list" value="[10, 50, 200, 1000]"/> + <param name="sp_name" value="xgbclassifier__n_estimators"/> + </repeat> + <repeat name="param_set"> + <param name="sp_list" value="[324089]"/> + <param name="sp_name" value="xgbclassifier__random_state"/> + </repeat> <param name="primary_scoring" value="balanced_accuracy"/> <param name='selected_cv' value="StratifiedKFold"/> <param name="n_splits" value="3"/> @@ -335,15 +365,16 @@ </test> <test> <param name="selected_search_scheme" value="GridSearchCV"/> - <param name="infile_pipeline" value="pipeline09" ftype="zip"/> - <conditional name="search_param_selector"> - <param name="search_p" value="n_neighbors: [50, 100, 150, 200]"/> - <param name="selected_param_type" value="prep_1_p"/> - </conditional> - <conditional name="search_param_selector"> - <param name="search_p" value="random_state: [324089]"/> - <param name="selected_param_type" value="final_estimator_p"/> - </conditional> + <param name="infile_estimator" value="pipeline09" ftype="zip"/> + <param name="infile_params" value="get_params09.tabular" ftype="tabular"/> + <repeat name="param_set"> + <param name="sp_list" value="[50, 100, 150, 200]"/> + <param name="sp_name" value="relieff__n_neighbors"/> + </repeat> + <repeat name="param_set"> + <param name="sp_list" value="[324089]"/> + <param name="sp_name" value="randomforestregressor__random_state"/> + </repeat> <param name="primary_scoring" value="explained_variance"/> <param name="secondary_scoring" value="neg_mean_squared_error,r2"/> <param name='selected_cv' value="StratifiedKFold"/> @@ -367,11 +398,12 @@ </test> <test> <param name="selected_search_scheme" value="GridSearchCV"/> - <param name="infile_pipeline" value="pipeline02" ftype="zip"/> - <conditional name="search_param_selector"> - <param name="search_p" value="eps: [0.01, 0.001]"/> - <param name="selected_param_type" value="final_estimator_p"/> - </conditional> + <param name="infile_estimator" value="pipeline02" ftype="zip"/> + <param name="infile_params" value="get_params02.tabular" ftype="tabular"/> + <repeat name="param_set"> + <param name="sp_list" value="[0.01, 0.001]"/> + <param name="sp_name" value="lassocv__eps"/> + </repeat> <param name="infile1" value="regression_X.tabular" ftype="tabular"/> <param name="header1" value="true" /> <param name="selected_column_selector_option" value="all_columns"/> @@ -381,17 +413,18 @@ <output name="outfile_result"> <assert_contents> <has_n_columns n="12"/> - <has_text text="0.7762968161366681" /> + <has_text text="0.776296816136668" /> </assert_contents> </output> </test> <test> <param name="selected_search_scheme" value="GridSearchCV"/> - <param name="infile_pipeline" value="pipeline05" ftype="zip"/> - <conditional name="search_param_selector"> - <param name="search_p" value="n_estimators: [10, 50, 100, 300]"/> - <param name="selected_param_type" value="final_estimator_p"/> - </conditional> + <param name="infile_estimator" value="pipeline05" ftype="zip"/> + <param name="infile_params" value="get_params05.tabular" ftype="tabular"/> + <repeat name="param_set"> + <param name="sp_list" value="[10, 50, 100, 300]"/> + <param name="sp_name" value="randomforestregressor__n_estimators"/> + </repeat> <param name="infile1" value="regression_X.tabular" ftype="tabular"/> <param name="header1" value="true" /> <param name="selected_column_selector_option" value="all_columns"/> @@ -407,11 +440,12 @@ </test> <test expect_failure="true"> <param name="selected_search_scheme" value="GridSearchCV"/> - <param name="infile_pipeline" value="pipeline01" ftype="zip"/> - <conditional name="search_param_selector"> - <param name="search_p" value="C: open('~/.ssh/authorized_keys', 'r').read()"/> - <param name="selected_param_type" value="final_estimator_p"/> - </conditional> + <param name="infile_estimator" value="pipeline01" ftype="zip"/> + <param name="infile_params" value="get_params01.tabular" ftype="tabular"/> + <repeat name="param_set"> + <param name="sp_list" value="open('~/.ssh/authorized_keys', 'r').read()"/> + <param name="sp_name" value="svr__C"/> + </repeat> <param name="infile1" value="regression_X.tabular" ftype="tabular"/> <param name="header1" value="true" /> <param name="selected_column_selector_option" value="all_columns"/> @@ -421,15 +455,16 @@ </test> <test> <param name="selected_search_scheme" value="GridSearchCV"/> - <param name="infile_pipeline" value="pipeline10" ftype="zip"/> - <conditional name="search_param_selector"> - <param name="search_p" value="base_estimator-: [sklearn_tree.DecisionTreeRegressor(random_state=0), sklearn_tree.ExtraTreeRegressor(random_state=0)]"/> - <param name="selected_param_type" value="final_estimator_p"/> - </conditional> - <conditional name="search_param_selector"> - <param name="search_p" value="random_state: [10]"/> - <param name="selected_param_type" value="final_estimator_p"/> - </conditional> + <param name="infile_estimator" value="pipeline10" ftype="zip"/> + <param name="infile_params" value="get_params10.tabular" ftype="tabular"/> + <repeat name="param_set"> + <param name="sp_list" value=": [sklearn_tree.DecisionTreeRegressor(random_state=0), sklearn_tree.ExtraTreeRegressor(random_state=0)]"/> + <param name="sp_name" value="adaboostregressor__base_estimator"/> + </repeat> + <repeat name="param_set"> + <param name="sp_list" value="[10]"/> + <param name="sp_name" value="adaboostregressor__random_state"/> + </repeat> <param name="infile1" value="regression_X.tabular" ftype="tabular"/> <param name="header1" value="true" /> <param name="selected_column_selector_option" value="all_columns"/> @@ -445,16 +480,17 @@ </test> <test> <param name="selected_search_scheme" value="GridSearchCV"/> - <param name="infile_pipeline" value="pipeline09" ftype="zip"/> - <conditional name="search_param_selector"> - <param name="search_p" value=": [sklearn_feature_selection.SelectKBest(), + <param name="infile_estimator" value="pipeline09" ftype="zip"/> + <param name="infile_params" value="get_params09.tabular" ftype="tabular"/> + <repeat name="param_set"> + <param name="sp_list" value=": [sklearn_feature_selection.SelectKBest(), sklearn_feature_selection.VarianceThreshold(), skrebate_ReliefF(), sklearn_preprocessing.RobustScaler()]"/> - <param name="selected_param_type" value="prep_1_p"/> - </conditional> - <conditional name="search_param_selector"> - <param name="search_p" value="random_state: [10]"/> - <param name="selected_param_type" value="final_estimator_p"/> - </conditional> + <param name="sp_name" value="relieff"/> + </repeat> + <repeat name="param_set"> + <param name="sp_list" value="[10]"/> + <param name="sp_name" value="randomforestregressor__random_state"/> + </repeat> <param name="infile1" value="regression_X.tabular" ftype="tabular"/> <param name="header1" value="true" /> <param name="selected_column_selector_option" value="all_columns"/> @@ -470,15 +506,16 @@ </test> <test> <param name="selected_search_scheme" value="GridSearchCV"/> - <param name="infile_pipeline" value="pipeline09" ftype="zip"/> - <conditional name="search_param_selector"> - <param name="search_p" value=": [None,'sk_prep_all', 8, 14, skrebate_ReliefF(n_features_to_select=12)]"/> - <param name="selected_param_type" value="prep_1_p"/> - </conditional> - <conditional name="search_param_selector"> - <param name="search_p" value="random_state: [10]"/> - <param name="selected_param_type" value="final_estimator_p"/> - </conditional> + <param name="infile_estimator" value="pipeline09" ftype="zip"/> + <param name="infile_params" value="get_params09.tabular" ftype="tabular"/> + <repeat name="param_set"> + <param name="sp_list" value=": [None,'sk_prep_all', 8, 14, skrebate_ReliefF(n_features_to_select=12)]"/> + <param name="sp_name" value="relieff"/> + </repeat> + <repeat name="param_set"> + <param name="sp_list" value="[10]"/> + <param name="sp_name" value="randomforestregressor__random_state"/> + </repeat> <param name="infile1" value="regression_X.tabular" ftype="tabular"/> <param name="header1" value="true" /> <param name="selected_column_selector_option" value="all_columns"/> @@ -494,23 +531,24 @@ </test> <test> <param name="selected_search_scheme" value="GridSearchCV"/> - <param name="infile_pipeline" value="pipeline11" ftype="zip"/> - <conditional name="search_param_selector"> - <param name="search_p" value="n_neighbors: [3,4,5]"/> - <param name="selected_param_type" value="prep_1_p"/> - </conditional> - <conditional name="search_param_selector"> - <param name="search_p" value="random_state: [10]"/> - <param name="selected_param_type" value="prep_1_p"/> - </conditional> - <conditional name="search_param_selector"> - <param name="search_p" value="n_estimators:[10, 50, 100, 500]"/> - <param name="selected_param_type" value="final_estimator_p"/> - </conditional> - <conditional name="search_param_selector"> - <param name="search_p" value="random_state: [10]"/> - <param name="selected_param_type" value="final_estimator_p"/> - </conditional> + <param name="infile_estimator" value="pipeline11" ftype="zip"/> + <param name="infile_params" value="get_params11.tabular" ftype="tabular"/> + <repeat name="param_set"> + <param name="sp_list" value="[3,4,5]"/> + <param name="sp_name" value="editednearestneighbours__n_neighbors"/> + </repeat> + <repeat name="param_set"> + <param name="sp_list" value="[10]"/> + <param name="sp_name" value="editednearestneighbours__random_state"/> + </repeat> + <repeat name="param_set"> + <param name="sp_list" value="[10, 50, 100, 500]"/> + <param name="sp_name" value="randomforestclassifier__n_estimators"/> + </repeat> + <repeat name="param_set"> + <param name="sp_list" value="[10]"/> + <param name="sp_name" value="randomforestclassifier__random_state"/> + </repeat> <param name="primary_scoring" value="f1_macro"/> <param name="secondary_scoring" value="balanced_accuracy,accuracy"/> <param name="n_splits" value="5"/> @@ -531,15 +569,16 @@ </test> <test> <param name="selected_search_scheme" value="GridSearchCV"/> - <param name="infile_pipeline" value="pipeline12" ftype="zip"/> - <conditional name="search_param_selector"> - <param name="search_p" value="estimator__n_estimators: [10, 100, 200]"/> - <param name="selected_param_type" value="final_estimator_p"/> - </conditional> - <conditional name="search_param_selector"> - <param name="search_p" value="n_features_to_select: [10, None]"/> - <param name="selected_param_type" value="final_estimator_p"/> - </conditional> + <param name="infile_estimator" value="pipeline12" ftype="zip"/> + <param name="infile_params" value="get_params12.tabular" ftype="tabular"/> + <repeat name="param_set"> + <param name="sp_list" value="[10, 100, 200]"/> + <param name="sp_name" value="rfe__estimator__n_estimators"/> + </repeat> + <repeat name="param_set"> + <param name="sp_list" value="[10, None]"/> + <param name="sp_name" value="rfe__n_features_to_select"/> + </repeat> <param name="primary_scoring" value="r2"/> <param name="infile1" value="regression_X.tabular" ftype="tabular"/> <param name="header1" value="true" /> @@ -554,38 +593,66 @@ </assert_contents> </output> </test> + <!--test> + <conditional name="search_schemes"> + <param name="selected_search_scheme" value="GridSearchCV"/> + <param name="infile_estimator" value="pipeline05" ftype="zip"/> + <section name="search_params_builder"> + <param name="infile_params" value="get_params05.tabular" ftype="tabular"/> + <repeat name="param_set"> + <param name="sp_list" value="[10, 50, 100, 300]"/> + <param name="sp_name" value="randomforestregressor__n_estimators"/> + </repeat> + </section> + </conditional> + <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_result"> + <assert_contents> + <has_n_columns n="1"/> + <has_text text="0.7986842219788204" /> + </assert_contents> + </output> + </test--> </tests> <help> <![CDATA[ **What it does** -Searches optimized parameter values for an estimator or pipeline through either exhaustive grid cross validation search or Randomized cross validation search. +Searches optimized parameter settings for an estimator or pipeline through either exhaustive grid cross validation search or Randomized cross validation search. please refer to `Scikit-learn model_selection GridSearchCV`_, `Scikit-learn model_selection RandomizedSearchCV`_ and `Tuning hyper-parameters`_. -**How to choose search patameters?** +**Return** + +Outputs `cv_results_` from SearchCV in a tabular dataset if no train_test_split, otherwise the test score(s). Besides, Output of the SearchCV object is optional. + +**How to choose search patameters grid?** Please refer to `svm`_, `linear_model`_, `ensemble`_, `naive_bayes`_, `tree`_, `neighbors`_ and `xgboost`_ for estimator parameters. -Refer to `sklearn.preprocessing`_, `feature_selection`_, `decomposition`_, `kernel_approximation`_, `cluster.FeatureAgglomeration`_ and `skrebate`_ for parameter in the pre-processing steps. - -**Search parameter input** accepts parameter and setting in key:value pair. One pair per input box. Setting can be list, numpy array, or distribution. -The evaluation of settings supports operations in Math, list comprehension, numpy.arange(np_arange), most numpy.random(e.g., np_random_uniform) and some scipy.stats(e.g., scipy_stats_zipf) classes or functions, and others. +Refer to `sklearn.preprocessing`_, `feature_selection`_, `decomposition`_, `kernel_approximation`_, `cluster.FeatureAgglomeration`_ +and `skrebate`_ for parameter in the pre-processing steps. -**Examples:** +**Search parameter list** can be list, numpy array, or distribution. The evaluation of settings supports operations in Math, +list comprehension, numpy.arange(np_arange), most numpy.random(e.g., np_random_uniform) and some scipy.stats(e.g., scipy_stats_zipf) classes or functions, and others. -- K: [3, 5, 7, 9] +Examples: -- n_estimators: list(range(50, 1001, 50)) +- [3, 5, 7, 9] -- gamma: np_arange(0.01, 1, 0.1) +- list(range(50, 1001, 50)) -- alpha: np_random_choice(list(range(1, 51)) + [None], size=20) +- np_arange(0.01, 1, 0.1) -- max_depth: scipy_stats_randin(1, 11) +- np_random_choice(list(range(1, 51)) + [None], size=20) -**Estimator search/eval (additional '-')**:: +- scipy_stats_randin(1, 11) - base_estimator-: [sklearn_tree.DecisionTreeRegressor(), sklearn_tree.ExtraTreeRegressor()] +**Estimator / Preprocessor search (additional `:` in the front)**:: -**Preprocessors search/swap**:: + : [sklearn_tree.DecisionTreeRegressor(), sklearn_tree.ExtraTreeRegressor()] : [sklearn_feature_selection.SelectKBest(), sklearn_feature_selection.VarianceThreshold(), skrebate_ReliefF(), sklearn_preprocessing.RobustScaler()] @@ -656,6 +723,17 @@ : [None, 'sk_prep_all', 22, 'k_appr_all', sklearn_feature_selection.SelectKBest(k=50)] + +**Whether to do train_test_split?** + +Please refer to `https://scikit-learn.org/stable/modules/cross_validation.html#cross-validation`_ + + +.. image:: https://scikit-learn.org/stable/_images/grid_search_cross_validation.png + :height: 300 + :width: 400 + + .. _`Scikit-learn model_selection GridSearchCV`: http://scikit-learn.org/stable/modules/generated/sklearn.model_selection.GridSearchCV.html .. _`Scikit-learn model_selection RandomizedSearchCV`: http://scikit-learn.org/stable/modules/generated/sklearn.model_selection.RandomizedSearchCV.html .. _`Tuning hyper-parameters`: http://scikit-learn.org/stable/modules/grid_search.html @@ -674,6 +752,7 @@ .. _`kernel_approximation`: http://scikit-learn.org/stable/modules/classes.html#module-sklearn.kernel_approximation .. _`cluster.FeatureAgglomeration`: http://scikit-learn.org/stable/modules/generated/sklearn.cluster.FeatureAgglomeration.html .. _`skrebate`: https://epistasislab.github.io/scikit-rebate/using/ +.. _`https://scikit-learn.org/stable/modules/cross_validation.html#cross-validation`: https://scikit-learn.org/stable/modules/cross_validation.html#cross-validation ]]> </help>