Mercurial > repos > bgruening > sklearn_numeric_clustering
changeset 15:d093a5421bba draft
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/sklearn commit 4ed8c4f6ef9ece81797a398b17a99bbaf49a6978
| author | bgruening |
|---|---|
| date | Wed, 30 May 2018 08:20:52 -0400 |
| parents | 9e4bda259863 |
| children | cd661d6d20c4 |
| files | main_macros.xml test-data/mv_result07.tabular |
| diffstat | 2 files changed, 51 insertions(+), 2 deletions(-) [+] |
line wrap: on
line diff
--- a/main_macros.xml Tue May 22 19:27:07 2018 -0400 +++ b/main_macros.xml Wed May 30 08:20:52 2018 -0400 @@ -16,6 +16,47 @@ return y </token> +## generate an instance for one of sklearn.feature_selection classes +## must call "@COLUMNS_FUNCTION@" + <token name="@FEATURE_SELECTOR_FUNCTION@"> +def feature_selector(inputs): + selector = inputs["selected_algorithm"] + selector = getattr(sklearn.feature_selection, selector) + options = inputs["options"] + + if inputs['selected_algorithm'] == 'SelectFromModel': + if not options['threshold'] or options['threshold'] == 'None': + options['threshold'] = None + if 'extra_estimator' in inputs and inputs['extra_estimator']['has_estimator'] == 'no_load': + fitted_estimator = pickle.load(open("inputs['extra_estimator']['fitted_estimator']", 'r')) + new_selector = selector(fitted_estimator, prefit=True, **options) + else: + estimator=inputs["estimator"] + if inputs["extra_estimator"]["has_estimator"]=='no': + estimator=inputs["extra_estimator"]["new_estimator"] + estimator=eval(estimator.replace('__dq__', '"').replace("__sq__","'")) + new_selector = selector(estimator, **options) + + elif inputs['selected_algorithm'] in ['RFE', 'RFECV']: + if 'scoring' in options and (not options['scoring'] or options['scoring'] == 'None'): + options['scoring'] = None + estimator=inputs["estimator"] + if inputs["extra_estimator"]["has_estimator"]=='no': + estimator=inputs["extra_estimator"]["new_estimator"] + estimator=eval(estimator.replace('__dq__', '"').replace("__sq__","'")) + new_selector = selector(estimator, **options) + + elif inputs['selected_algorithm'] == "VarianceThreshold": + new_selector = selector(**options) + + else: + score_func = inputs["score_func"] + score_func = getattr(sklearn.feature_selection, score_func) + new_selector = selector(score_func, **options) + + return new_selector + </token> + <xml name="python_requirements"> <requirements> <requirement type="package" version="2.7">python</requirement> @@ -794,6 +835,13 @@ </when> <yield/> </xml> + <xml name="estimator_input_no_fit"> + <expand macro="feature_selection_estimator" /> + <conditional name="extra_estimator"> + <expand macro="feature_selection_extra_estimator" /> + <expand macro="feature_selection_estimator_choices" /> + </conditional> + </xml> <xml name="feature_selection_all"> <conditional name="feature_selection_algorithms"> <param name="selected_algorithm" type="select" label="Select a feature selection algorithm"> @@ -975,8 +1023,8 @@ <param argument="scoring" type="text" value="" optional="true" label="scoring" help="A metric used to evaluate the estimator"/> </xml> - <xml name="pre_dispatch"> - <param argument="pre_dispatch" type="text" value="all" optional="true" label="pre_dispatch" help="Number of predispatched jobs for parallel execution"/> + <xml name="pre_dispatch" token_type="text" token_default_value="all" token_help="Number of predispatched jobs for parallel execution"> + <param argument="pre_dispatch" type="@TYPE@" value="@DEFAULT_VALUE@" optional="true" label="pre_dispatch" help="@HELP@"/> </xml> <!-- Outputs -->