Mercurial > repos > bgruening > sklearn_build_pipeline
diff pipeline.xml @ 0:73535ddcfa69 draft
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/sklearn commit 76583c1fcd9d06a4679cc46ffaee44117b9e22cd
| author | bgruening |
|---|---|
| date | Sat, 04 Aug 2018 12:32:40 -0400 |
| parents | |
| children | 0857964e07c2 |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/pipeline.xml Sat Aug 04 12:32:40 2018 -0400 @@ -0,0 +1,281 @@ +<tool id="sklearn_build_pipeline" name="Pipeline Builder" version="@VERSION@"> + <description>constructs a list of transforms and a final estimator</description> + <macros> + <import>main_macros.xml</import> + </macros> + <expand macro="python_requirements"/> + <expand macro="macro_stdio"/> + <version_command>echo "@VERSION@"</version_command> + <command> + <![CDATA[ + python "$sklearn_pipeline_script" '$inputs' + ]]> + </command> + <configfiles> + <inputs name="inputs" /> + <configfile name="sklearn_pipeline_script"> + <![CDATA[ +import sys +import json +import pickle +import pprint +import xgboost +import ast +import sklearn.feature_selection +from sklearn import ( preprocessing, svm, linear_model, ensemble, naive_bayes, + tree, neighbors, decomposition, kernel_approximation, cluster) +from sklearn.pipeline import Pipeline + +@GET_ESTIMATOR_FUNCTION@ +@FEATURE_SELECTOR_FUNCTION@ + +input_json_path = sys.argv[1] +with open(input_json_path, "r") as param_handler: + params = json.load(param_handler) + +pipeline_steps = [] + +def get_component(input_json, check_none=False): + if input_json['component_type'] == 'None': + if not check_none: + return + else: + sys.exit("The pre-processing component type can't be None when the number of components is greater than 1.") + if input_json['component_type'] == 'pre_processor': + preprocessor = input_json["pre_processors"]["selected_pre_processor"] + pre_processor_options = input_json["pre_processors"]["options"] + my_class = getattr(preprocessing, preprocessor) + return my_class(**pre_processor_options) + if input_json['component_type'] == 'feature_selection': + fs_obj = feature_selector(input_json['fs_algorithm_selector']) + return fs_obj + if input_json['component_type'] == 'decomposition': + algorithm = input_json['matrix_decomposition_selector']['select_algorithm'] + obj = getattr(decomposition, algorithm)() + options = input_json['matrix_decomposition_selector']['text_params'].strip() + if options != "": + options = ast.literal_eval('{' + options + '}') + obj.set_params(**options) + return obj + if input_json['component_type'] == 'kernel_approximation': + algorithm = input_json['kernel_approximation_selector']['select_algorithm'] + obj = getattr(kernel_approximation, algorithm)() + options = input_json['kernel_approximation_selector']['text_params'].strip() + if options != "": + options = ast.literal_eval('{' + options + '}') + obj.set_params(**options) + return obj + if input_json['component_type'] == 'FeatureAgglomeration': + algorithm = input_json['FeatureAgglomeration_selector']['select_algorithm'] + obj = getattr(cluster, algorithm)() + options = input_json['FeatureAgglomeration_selector']['text_params'].strip() + if options != "": + options = ast.literal_eval('{' + options + '}') + obj.set_params(**options) + return obj +if len(params['pipeline_component']) == 1: + step_obj = get_component( params['pipeline_component'][0]['component_selector']) + if step_obj: + pipeline_steps.append( ('preprocessing_1', step_obj) ) +else: + for i, c in enumerate(params['pipeline_component']): + step_obj = get_component( c['component_selector'], check_none=True ) + pipeline_steps.append( ('preprocessing_' + str(i+1), step_obj) ) + +# Set up final estimator and add to pipeline. +estimator_json = params["final_estimator"]['estimator_selector'] +estimator = get_estimator(estimator_json) + +pipeline_steps.append( ('estimator', estimator) ) + +pipeline = Pipeline(pipeline_steps) +pprint.pprint(pipeline.named_steps) + +with open("$outfile", 'wb') as out_handler: + pickle.dump(pipeline, out_handler, pickle.HIGHEST_PROTOCOL) + + ]]> + </configfile> + </configfiles> + <inputs> + <repeat name="pipeline_component" min="1" max="5" title="Pre-processing step"> + <conditional name="component_selector"> + <param name="component_type" type="select" label="Choose the type of transformation:"> + <option value="none" selected="true">None</option> + <option value="pre_processor">Sklearn Preprocessor</option> + <option value="feature_selection">Feature Selection</option> + <option value="decomposition">Matrix Decomposition</option> + <option value="kernel_approximation">Kernel Approximation</option> + <option value="FeatureAgglomeration">Agglomerate Features</option> + </param> + <when value="none"/> + <when value="pre_processor"> + <conditional name="pre_processors"> + <expand macro="sparse_preprocessors_ext" /> + <expand macro="sparse_preprocessor_options_ext" /> + </conditional> + </when> + <when value="feature_selection"> + <expand macro="feature_selection_all"> + <expand macro="fs_selectfrommodel_no_prefitted"/> + </expand> + </when> + <when value="decomposition"> + <expand macro="matrix_decomposition_all"/> + </when> + <when value="kernel_approximation"> + <expand macro="kernel_approximation_all"/> + </when> + <when value="FeatureAgglomeration"> + <expand macro="FeatureAgglomeration"/> + </when> + </conditional> + </repeat> + <section name="final_estimator" title="Final Estimator" expanded="true"> + <expand macro="estimator_selector_all" /> + </section> + </inputs> + <outputs> + <data format="zip" name="outfile"/> + </outputs> + <tests> + <test> + <repeat name="pipeline_component"> + <conditional name="component_selector"> + <param name="component_type" value="pre_processor"/> + <conditional name="pre_processors"> + <param name="selected_pre_processor" value="RobustScaler"/> + </conditional> + </conditional> + </repeat> + <repeat name="pipeline_component"> + <conditional name="component_selector"> + <param name="component_type" value="feature_selection"/> + <conditional name="fs_algorithm_selector"> + <param name="selected_algorithm" value="SelectKBest"/> + <param name="score_func" value="f_classif"/> + </conditional> + </conditional> + </repeat> + <param name="selected_module" value="svm"/> + <param name="selected_estimator" value="SVR"/> + <param name="text_params" value="'kernel': 'linear'"/> + <output name="outfile" file="pipeline01" compare="sim_size" delta="1"/> + </test> + <test> + <conditional name="component_selector"> + <param name="component_type" value="pre_processor"/> + <conditional name="pre_processors"> + <param name="selected_pre_processor" value="RobustScaler"/> + </conditional> + </conditional> + <param name="selected_module" value="linear_model"/> + <param name="selected_estimator" value="LassoCV"/> + <output name="outfile" file="pipeline02" compare="sim_size" delta="1"/> + </test> + <test> + <conditional name="component_selector"> + <param name="component_type" value="pre_processor"/> + <conditional name="pre_processors"> + <param name="selected_pre_processor" value="RobustScaler"/> + </conditional> + </conditional> + <param name="selected_module" value="xgboost"/> + <param name="selected_estimator" value="XGBClassifier"/> + <output name="outfile" file="pipeline03" compare="sim_size" delta="1"/> + </test> + <test> + <conditional name="component_selector"> + <param name="component_type" value="feature_selection"/> + <conditional name="fs_algorithm_selector"> + <param name="selected_algorithm" value="SelectFromModel"/> + <conditional name="model_inputter"> + <conditional name="estimator_selector"> + <param name="selected_module" value="ensemble"/> + <param name="selected_estimator" value="AdaBoostClassifier"/> + </conditional> + </conditional> + </conditional> + </conditional> + <section name="final_estimator"> + <param name="selected_module" value="svm"/> + <param name="selected_estimator" value="LinearSVC"/> + </section> + <output name="outfile" file="pipeline04" compare="sim_size" delta="1"/> + </test> + <test> + <conditional name="component_selector"> + <param name="component_type" value="None"/> + </conditional> + <param name="selected_module" value="ensemble"/> + <param name="selected_estimator" value="RandomForestRegressor"/> + <param name="text_params" value="'n_estimators': 100, 'random_state': 42"/> + <output name="outfile" file="pipeline05" compare="sim_size" delta="1"/> + </test> + <test> + <conditional name="component_selector"> + <param name="component_type" value="decomposition"/> + <conditional name="matrix_decomposition_selector"> + <param name="select_algorithm" value="PCA"/> + </conditional> + </conditional> + <param name="selected_module" value="ensemble"/> + <param name="selected_estimator" value="AdaBoostRegressor"/> + <output name="outfile" file="pipeline06" compare="sim_size" delta="1"/> + </test> + <test> + <conditional name="component_selector"> + <param name="component_type" value="kernel_approximation"/> + <conditional name="kernel_approximation_selector"> + <param name="select_algorithm" value="RBFSampler"/> + <param name="text_params" value="'n_components': 10, 'gamma': 2.0"/> + </conditional> + </conditional> + <param name="selected_module" value="ensemble"/> + <param name="selected_estimator" value="AdaBoostClassifier"/> + <output name="outfile" file="pipeline07" compare="sim_size" delta="1"/> + </test> + <test> + <conditional name="component_selector"> + <param name="component_type" value="FeatureAgglomeration"/> + <conditional name="FeatureAgglomeration_selector"> + <param name="select_algorithm" value="FeatureAgglomeration"/> + <param name="text_params" value="'n_clusters': 3, 'affinity': 'euclidean'"/> + </conditional> + </conditional> + <param name="selected_module" value="ensemble"/> + <param name="selected_estimator" value="AdaBoostClassifier"/> + <output name="outfile" file="pipeline08" compare="sim_size" delta="1"/> + </test> + </tests> + <help> + <![CDATA[ +**What it does** +Constructs a pipeline that contains a list of transfroms and a final estimator. Pipeline assembles several steps +that can be cross-validated together while setting different parameters. +please refer to `Scikit-learn pipeline Pipeline`_. + +**Pre-processing components** allow None, one or a combination of up to 5 transformations from `sklearn.preprocessing`_, `feature_selection`_, `decomposition`_, `kernel_approximation`_ and/or `cluster.FeatureAgglomeration`_. + +**Estimator** selector supports estimators from `xgboost`_ and many scikit-learn modules, including `svm`_, `linear_model`_, `ensemble`_, `naive_bayes`_, `tree`_ and `neighbors`_. + + +.. _`Scikit-learn pipeline Pipeline`: http://scikit-learn.org/stable/modules/generated/sklearn.pipeline.Pipeline.html +.. _`svm`: http://scikit-learn.org/stable/modules/classes.html#module-sklearn.svm +.. _`linear_model`: http://scikit-learn.org/stable/modules/classes.html#module-sklearn.linear_model +.. _`ensemble`: http://scikit-learn.org/stable/modules/classes.html#module-sklearn.ensemble +.. _`naive_bayes`: http://scikit-learn.org/stable/modules/classes.html#module-sklearn.naive_bayes +.. _`tree`: http://scikit-learn.org/stable/modules/classes.html#module-sklearn.tree +.. _`neighbors`: http://scikit-learn.org/stable/modules/classes.html#module-sklearn.neighbors +.. _`xgboost`: https://xgboost.readthedocs.io/en/latest/python/python_api.html + +.. _`sklearn.preprocessing`: http://scikit-learn.org/stable/modules/classes.html#module-sklearn.preprocessing +.. _`feature_selection`: http://scikit-learn.org/stable/modules/classes.html#module-sklearn.feature_selection +.. _`decomposition`: http://scikit-learn.org/stable/modules/classes.html#module-sklearn.decomposition +.. _`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 + + ]]> + </help> + <expand macro="sklearn_citation"/> +</tool>