Mercurial > repos > bgruening > sklearn_feature_selection

comparison feature_selection.xml @ 3:3a1acc39b39b draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/sklearn commit 4ed8c4f6ef9ece81797a398b17a99bbaf49a6978
author bgruening
date Wed, 30 May 2018 08:25:49 -0400
parents 2eb90e73f0d5
children 44e26f8a82c6
comparison
equal deleted inserted replaced
2:2eb90e73f0d5 3:3a1acc39b39b
23 import sklearn.feature_selection 23 import sklearn.feature_selection
24 from sklearn import svm, linear_model, ensemble 24 from sklearn import svm, linear_model, ensemble
25 25
26 @COLUMNS_FUNCTION@ 26 @COLUMNS_FUNCTION@
27 27
28 @FEATURE_SELECTOR_FUNCTION@
29
28 input_json_path = sys.argv[1] 30 input_json_path = sys.argv[1]
29 params = json.load(open(input_json_path, "r")) 31 params = json.load(open(input_json_path, "r"))
30 32
31 ## Read features 33 ## Read features
32 features_has_header = params["input_options"]["header1"] 34 features_has_header = params["input_options"]["header1"]
55 parse_dates=True 57 parse_dates=True
56 ) 58 )
57 y=y.ravel() 59 y=y.ravel()
58 60
59 ## Create feature selector 61 ## Create feature selector
60 selector = params["feature_selection_algorithms"]["selected_algorithm"] 62 new_selector = feature_selector(params['feature_selection_algorithms'])
61 selector = getattr(sklearn.feature_selection, selector) 63 if params['feature_selection_algorithms']['selected_algorithm'] != 'SelectFromModel' or \
62 options = params["feature_selection_algorithms"]["options"] 64 'extra_estimator' not in params['feature_selection_algorithms'] or \
63 65 params['feature_selection_algorithms']['extra_estimator']['has_estimator'] != 'no_load' :
64 if params['feature_selection_algorithms']['selected_algorithm'] == 'SelectFromModel':
65 if not options['threshold'] or options['threshold'] == 'None':
66 options['threshold'] = None
67 if 'extra_estimator' in params['feature_selection_algorithms'] and params['feature_selection_algorithms']['extra_estimator']['has_estimator'] == 'no_load':
68 fitted_estimator = pickle.load(open("params['feature_selection_algorithms']['extra_estimator']['fitted_estimator']", 'r'))
69 new_selector = selector(fitted_estimator, prefit=True, **options)
70 else:
71 estimator=params["feature_selection_algorithms"]["estimator"]
72 if params["feature_selection_algorithms"]["extra_estimator"]["has_estimator"]=='no':
73 estimator=params["feature_selection_algorithms"]["extra_estimator"]["new_estimator"]
74 estimator=eval(estimator.replace('__dq__', '"').replace("__sq__","'"))
75 new_selector = selector(estimator, **options)
76 new_selector.fit(X, y)
77
78 elif params['feature_selection_algorithms']['selected_algorithm'] in ['RFE', 'RFECV']:
79 if 'scoring' in options and (not options['scoring'] or options['scoring'] == 'None'):
80 options['scoring'] = None
81 estimator=params["feature_selection_algorithms"]["estimator"]
82 if params["feature_selection_algorithms"]["extra_estimator"]["has_estimator"]=='no':
83 estimator=params["feature_selection_algorithms"]["extra_estimator"]["new_estimator"]
84 estimator=eval(estimator.replace('__dq__', '"').replace("__sq__","'"))
85 new_selector = selector(estimator, **options)
86 new_selector.fit(X, y)
87
88 elif params['feature_selection_algorithms']['selected_algorithm'] == "VarianceThreshold":
89 new_selector = selector(**options)
90 new_selector.fit(X, y)
91
92 else:
93 score_func = params["feature_selection_algorithms"]["score_func"]
94 score_func = getattr(sklearn.feature_selection, score_func)
95 new_selector = selector(score_func, **options)
96 new_selector.fit(X, y) 66 new_selector.fit(X, y)
97 67
98 ## Transform to select features 68 ## Transform to select features
99 selected_names = None 69 selected_names = None
100 if "$select_methods.selected_method" == "fit_transform": 70 if "$select_methods.selected_method" == "fit_transform":