Mercurial > repos > bgruening > sklearn_model_validation

comparison search_model_validation.py @ 17:cf9aa11b91c8 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 ab963ec9498bd05d2fb2f24f75adb2fccae7958c
author bgruening
date Wed, 15 May 2019 07:42:07 -0400
parents 86e1e2874460
children efbec977a47d
comparison
equal deleted inserted replaced
16:86e1e2874460 17:cf9aa11b91c8
1 import argparse
2 import collections
1 import imblearn 3 import imblearn
2 import json 4 import json
3 import numpy as np 5 import numpy as np
4 import os
5 import pandas 6 import pandas
6 import pickle 7 import pickle
7 import skrebate 8 import skrebate
8 import sklearn 9 import sklearn
9 import sys 10 import sys
10 import xgboost 11 import xgboost
11 import warnings 12 import warnings
13 import iraps_classifier
14 import model_validations
15 import preprocessors
16 import feature_selectors
12 from imblearn import under_sampling, over_sampling, combine 17 from imblearn import under_sampling, over_sampling, combine
13 from imblearn.pipeline import Pipeline as imbPipeline 18 from scipy.io import mmread
14 from sklearn import (cluster, compose, decomposition, ensemble, feature_extraction, 19 from mlxtend import classifier, regressor
15 feature_selection, gaussian_process, kernel_approximation, metrics, 20 from sklearn import (cluster, compose, decomposition, ensemble,
16 model_selection, naive_bayes, neighbors, pipeline, preprocessing, 21 feature_extraction, feature_selection,
17 svm, linear_model, tree, discriminant_analysis) 22 gaussian_process, kernel_approximation, metrics,
23 model_selection, naive_bayes, neighbors,
24 pipeline, preprocessing, svm, linear_model,
25 tree, discriminant_analysis)
18 from sklearn.exceptions import FitFailedWarning 26 from sklearn.exceptions import FitFailedWarning
19 from sklearn.externals import joblib 27 from sklearn.externals import joblib
20 from utils import get_cv, get_scoring, get_X_y, load_model, read_columns, SafeEval 28 from sklearn.model_selection._validation import _score
21 29
22 30 from utils import (SafeEval, get_cv, get_scoring, get_X_y,
23 N_JOBS = int(os.environ.get('GALAXY_SLOTS', 1)) 31 load_model, read_columns)
24 32 from model_validations import train_test_split
25 33
26 def get_search_params(params_builder): 34
35 N_JOBS = int(__import__('os').environ.get('GALAXY_SLOTS', 1))
36 CACHE_DIR = './cached'
37 NON_SEARCHABLE = ('n_jobs', 'pre_dispatch', 'memory', 'steps',
38 'nthread', 'verbose')
39
40
41 def _eval_search_params(params_builder):
27 search_params = {} 42 search_params = {}
28 safe_eval = SafeEval(load_scipy=True, load_numpy=True)
29 safe_eval_es = SafeEval(load_estimators=True)
30 43
31 for p in params_builder['param_set']: 44 for p in params_builder['param_set']:
32 search_p = p['search_param_selector']['search_p'] 45 search_list = p['sp_list'].strip()
33 if search_p.strip() == '': 46 if search_list == '':
34 continue 47 continue
35 param_type = p['search_param_selector']['selected_param_type'] 48
36 49 param_name = p['sp_name']
37 lst = search_p.split(':') 50 if param_name.lower().endswith(NON_SEARCHABLE):
38 assert (len(lst) == 2), "Error, make sure there is one and only one colon in search parameter input." 51 print("Warning: `%s` is not eligible for search and was "
39 literal = lst[1].strip() 52 "omitted!" % param_name)
40 param_name = lst[0].strip() 53 continue
41 if param_name: 54
42 if param_name.lower() == 'n_jobs': 55 if not search_list.startswith(':'):
43 sys.exit("Parameter `%s` is invalid for search." %param_name) 56 safe_eval = SafeEval(load_scipy=True, load_numpy=True)
44 elif not param_name.endswith('-'): 57 ev = safe_eval(search_list)
45 ev = safe_eval(literal) 58 search_params[param_name] = ev
46 if param_type == 'final_estimator_p': 59 else:
47 search_params['estimator__' + param_name] = ev 60 # Have `:` before search list, asks for estimator evaluatio
48 else: 61 safe_eval_es = SafeEval(load_estimators=True)
49 search_params['preprocessing_' + param_type[5:6] + '__' + param_name] = ev 62 search_list = search_list[1:].strip()
50 else: 63 # TODO maybe add regular express check
51 # only for estimator eval, add `-` to the end of param 64 ev = safe_eval_es(search_list)
52 #TODO maybe add regular express check 65 preprocessors = (
53 ev = safe_eval_es(literal) 66 preprocessing.StandardScaler(), preprocessing.Binarizer(),
54 for obj in ev: 67 preprocessing.Imputer(), preprocessing.MaxAbsScaler(),
55 if 'n_jobs' in obj.get_params(): 68 preprocessing.Normalizer(), preprocessing.MinMaxScaler(),
56 obj.set_params( n_jobs=N_JOBS ) 69 preprocessing.PolynomialFeatures(),
57 if param_type == 'final_estimator_p': 70 preprocessing.RobustScaler(), feature_selection.SelectKBest(),
58 search_params['estimator__' + param_name[:-1]] = ev 71 feature_selection.GenericUnivariateSelect(),
59 else: 72 feature_selection.SelectPercentile(),
60 search_params['preprocessing_' + param_type[5:6] + '__' + param_name[:-1]] = ev 73 feature_selection.SelectFpr(), feature_selection.SelectFdr(),
61 elif param_type != 'final_estimator_p': 74 feature_selection.SelectFwe(),
62 #TODO regular express check ? 75 feature_selection.VarianceThreshold(),
63 ev = safe_eval_es(literal) 76 decomposition.FactorAnalysis(random_state=0),
64 preprocessors = [preprocessing.StandardScaler(), preprocessing.Binarizer(), preprocessing.Imputer(), 77 decomposition.FastICA(random_state=0),
65 preprocessing.MaxAbsScaler(), preprocessing.Normalizer(), preprocessing.MinMaxScaler(), 78 decomposition.IncrementalPCA(),
66 preprocessing.PolynomialFeatures(),preprocessing.RobustScaler(), 79 decomposition.KernelPCA(random_state=0, n_jobs=N_JOBS),
67 feature_selection.SelectKBest(), feature_selection.GenericUnivariateSelect(), 80 decomposition.LatentDirichletAllocation(
68 feature_selection.SelectPercentile(), feature_selection.SelectFpr(), feature_selection.SelectFdr(), 81 random_state=0, n_jobs=N_JOBS),
69 feature_selection.SelectFwe(), feature_selection.VarianceThreshold(), 82 decomposition.MiniBatchDictionaryLearning(
70 decomposition.FactorAnalysis(random_state=0), decomposition.FastICA(random_state=0), decomposition.IncrementalPCA(), 83 random_state=0, n_jobs=N_JOBS),
71 decomposition.KernelPCA(random_state=0, n_jobs=N_JOBS), decomposition.LatentDirichletAllocation(random_state=0, n_jobs=N_JOBS), 84 decomposition.MiniBatchSparsePCA(
72 decomposition.MiniBatchDictionaryLearning(random_state=0, n_jobs=N_JOBS), 85 random_state=0, n_jobs=N_JOBS),
73 decomposition.MiniBatchSparsePCA(random_state=0, n_jobs=N_JOBS), decomposition.NMF(random_state=0), 86 decomposition.NMF(random_state=0),
74 decomposition.PCA(random_state=0), decomposition.SparsePCA(random_state=0, n_jobs=N_JOBS), 87 decomposition.PCA(random_state=0),
75 decomposition.TruncatedSVD(random_state=0), 88 decomposition.SparsePCA(random_state=0, n_jobs=N_JOBS),
76 kernel_approximation.Nystroem(random_state=0), kernel_approximation.RBFSampler(random_state=0), 89 decomposition.TruncatedSVD(random_state=0),
77 kernel_approximation.AdditiveChi2Sampler(), kernel_approximation.SkewedChi2Sampler(random_state=0), 90 kernel_approximation.Nystroem(random_state=0),
78 cluster.FeatureAgglomeration(), 91 kernel_approximation.RBFSampler(random_state=0),
79 skrebate.ReliefF(n_jobs=N_JOBS), skrebate.SURF(n_jobs=N_JOBS), skrebate.SURFstar(n_jobs=N_JOBS), 92 kernel_approximation.AdditiveChi2Sampler(),
80 skrebate.MultiSURF(n_jobs=N_JOBS), skrebate.MultiSURFstar(n_jobs=N_JOBS), 93 kernel_approximation.SkewedChi2Sampler(random_state=0),
81 imblearn.under_sampling.ClusterCentroids(random_state=0, n_jobs=N_JOBS), 94 cluster.FeatureAgglomeration(),
82 imblearn.under_sampling.CondensedNearestNeighbour(random_state=0, n_jobs=N_JOBS), 95 skrebate.ReliefF(n_jobs=N_JOBS),
83 imblearn.under_sampling.EditedNearestNeighbours(random_state=0, n_jobs=N_JOBS), 96 skrebate.SURF(n_jobs=N_JOBS),
84 imblearn.under_sampling.RepeatedEditedNearestNeighbours(random_state=0, n_jobs=N_JOBS), 97 skrebate.SURFstar(n_jobs=N_JOBS),
85 imblearn.under_sampling.AllKNN(random_state=0, n_jobs=N_JOBS), 98 skrebate.MultiSURF(n_jobs=N_JOBS),
86 imblearn.under_sampling.InstanceHardnessThreshold(random_state=0, n_jobs=N_JOBS), 99 skrebate.MultiSURFstar(n_jobs=N_JOBS),
87 imblearn.under_sampling.NearMiss(random_state=0, n_jobs=N_JOBS), 100 imblearn.under_sampling.ClusterCentroids(
88 imblearn.under_sampling.NeighbourhoodCleaningRule(random_state=0, n_jobs=N_JOBS), 101 random_state=0, n_jobs=N_JOBS),
89 imblearn.under_sampling.OneSidedSelection(random_state=0, n_jobs=N_JOBS), 102 imblearn.under_sampling.CondensedNearestNeighbour(
90 imblearn.under_sampling.RandomUnderSampler(random_state=0), 103 random_state=0, n_jobs=N_JOBS),
91 imblearn.under_sampling.TomekLinks(random_state=0, n_jobs=N_JOBS), 104 imblearn.under_sampling.EditedNearestNeighbours(
92 imblearn.over_sampling.ADASYN(random_state=0, n_jobs=N_JOBS), 105 random_state=0, n_jobs=N_JOBS),
93 imblearn.over_sampling.RandomOverSampler(random_state=0), 106 imblearn.under_sampling.RepeatedEditedNearestNeighbours(
94 imblearn.over_sampling.SMOTE(random_state=0, n_jobs=N_JOBS), 107 random_state=0, n_jobs=N_JOBS),
95 imblearn.over_sampling.SVMSMOTE(random_state=0, n_jobs=N_JOBS), 108 imblearn.under_sampling.AllKNN(random_state=0, n_jobs=N_JOBS),
96 imblearn.over_sampling.BorderlineSMOTE(random_state=0, n_jobs=N_JOBS), 109 imblearn.under_sampling.InstanceHardnessThreshold(
97 imblearn.over_sampling.SMOTENC(categorical_features=[], random_state=0, n_jobs=N_JOBS), 110 random_state=0, n_jobs=N_JOBS),
98 imblearn.combine.SMOTEENN(random_state=0), imblearn.combine.SMOTETomek(random_state=0)] 111 imblearn.under_sampling.NearMiss(
112 random_state=0, n_jobs=N_JOBS),
113 imblearn.under_sampling.NeighbourhoodCleaningRule(
114 random_state=0, n_jobs=N_JOBS),
115 imblearn.under_sampling.OneSidedSelection(
116 random_state=0, n_jobs=N_JOBS),
117 imblearn.under_sampling.RandomUnderSampler(
118 random_state=0),
119 imblearn.under_sampling.TomekLinks(
120 random_state=0, n_jobs=N_JOBS),
121 imblearn.over_sampling.ADASYN(random_state=0, n_jobs=N_JOBS),
122 imblearn.over_sampling.RandomOverSampler(random_state=0),
123 imblearn.over_sampling.SMOTE(random_state=0, n_jobs=N_JOBS),
124 imblearn.over_sampling.SVMSMOTE(random_state=0, n_jobs=N_JOBS),
125 imblearn.over_sampling.BorderlineSMOTE(
126 random_state=0, n_jobs=N_JOBS),
127 imblearn.over_sampling.SMOTENC(
128 categorical_features=[], random_state=0, n_jobs=N_JOBS),
129 imblearn.combine.SMOTEENN(random_state=0),
130 imblearn.combine.SMOTETomek(random_state=0))
99 newlist = [] 131 newlist = []
100 for obj in ev: 132 for obj in ev:
101 if obj is None: 133 if obj is None:
102 newlist.append(None) 134 newlist.append(None)
103 elif obj == 'all_0': 135 elif obj == 'all_0':
112 newlist.extend(preprocessors[26:30]) 144 newlist.extend(preprocessors[26:30])
113 elif obj == 'reb_all': 145 elif obj == 'reb_all':
114 newlist.extend(preprocessors[31:36]) 146 newlist.extend(preprocessors[31:36])
115 elif obj == 'imb_all': 147 elif obj == 'imb_all':
116 newlist.extend(preprocessors[36:55]) 148 newlist.extend(preprocessors[36:55])
117 elif type(obj) is int and -1 < obj < len(preprocessors): 149 elif type(obj) is int and -1 < obj < len(preprocessors):
118 newlist.append(preprocessors[obj]) 150 newlist.append(preprocessors[obj])
119 elif hasattr(obj, 'get_params'): # user object 151 elif hasattr(obj, 'get_params'): # user uploaded object
120 if 'n_jobs' in obj.get_params(): 152 if 'n_jobs' in obj.get_params():
121 newlist.append( obj.set_params(n_jobs=N_JOBS) ) 153 newlist.append(obj.set_params(n_jobs=N_JOBS))
122 else: 154 else:
123 newlist.append(obj) 155 newlist.append(obj)
124 else: 156 else:
125 sys.exit("Unsupported preprocessor type: %r" %(obj)) 157 sys.exit("Unsupported estimator type: %r" % (obj))
126 search_params['preprocessing_' + param_type[5:6]] = newlist 158
127 else: 159 search_params[param_name] = newlist
128 sys.exit("Parameter name of the final estimator can't be skipped!")
129 160
130 return search_params 161 return search_params
131 162
132 163
133 if __name__ == '__main__': 164 def main(inputs, infile_estimator, infile1, infile2,
165 outfile_result, outfile_object=None, groups=None):
166 """
167 Parameter
168 ---------
169 inputs : str
170 File path to galaxy tool parameter
171
172 infile_estimator : str
173 File path to estimator
174
175 infile1 : str
176 File path to dataset containing features
177
178 infile2 : str
179 File path to dataset containing target values
180
181 outfile_result : str
182 File path to save the results, either cv_results or test result
183
184 outfile_object : str, optional
185 File path to save searchCV object
186
187 groups : str
188 File path to dataset containing groups labels
189 """
134 190
135 warnings.simplefilter('ignore') 191 warnings.simplefilter('ignore')
136 192
137 input_json_path = sys.argv[1] 193 with open(inputs, 'r') as param_handler:
138 with open(input_json_path, 'r') as param_handler:
139 params = json.load(param_handler) 194 params = json.load(param_handler)
140 195 if groups:
141 infile_pipeline = sys.argv[2] 196 (params['search_schemes']['options']['cv_selector']
142 infile1 = sys.argv[3] 197 ['groups_selector']['infile_g']) = groups
143 infile2 = sys.argv[4]
144 outfile_result = sys.argv[5]
145 if len(sys.argv) > 6:
146 outfile_estimator = sys.argv[6]
147 else:
148 outfile_estimator = None
149 198
150 params_builder = params['search_schemes']['search_params_builder'] 199 params_builder = params['search_schemes']['search_params_builder']
151 200
152 input_type = params['input_options']['selected_input'] 201 input_type = params['input_options']['selected_input']
153 if input_type == 'tabular': 202 if input_type == 'tabular':
154 header = 'infer' if params['input_options']['header1'] else None 203 header = 'infer' if params['input_options']['header1'] else None
155 column_option = params['input_options']['column_selector_options_1']['selected_column_selector_option'] 204 column_option = (params['input_options']['column_selector_options_1']
156 if column_option in ['by_index_number', 'all_but_by_index_number', 'by_header_name', 'all_but_by_header_name']: 205 ['selected_column_selector_option'])
206 if column_option in ['by_index_number', 'all_but_by_index_number',
207 'by_header_name', 'all_but_by_header_name']:
157 c = params['input_options']['column_selector_options_1']['col1'] 208 c = params['input_options']['column_selector_options_1']['col1']
158 else: 209 else:
159 c = None 210 c = None
160 X = read_columns( 211 X = read_columns(
161 infile1, 212 infile1,
162 c = c, 213 c=c,
163 c_option = column_option, 214 c_option=column_option,
164 sep='\t', 215 sep='\t',
165 header=header, 216 header=header,
166 parse_dates=True 217 parse_dates=True).astype(float)
167 )
168 else: 218 else:
169 X = mmread(open(infile1, 'r')) 219 X = mmread(open(infile1, 'r'))
170 220
171 header = 'infer' if params['input_options']['header2'] else None 221 header = 'infer' if params['input_options']['header2'] else None
172 column_option = params['input_options']['column_selector_options_2']['selected_column_selector_option2'] 222 column_option = (params['input_options']['column_selector_options_2']
173 if column_option in ['by_index_number', 'all_but_by_index_number', 'by_header_name', 'all_but_by_header_name']: 223 ['selected_column_selector_option2'])
224 if column_option in ['by_index_number', 'all_but_by_index_number',
225 'by_header_name', 'all_but_by_header_name']:
174 c = params['input_options']['column_selector_options_2']['col2'] 226 c = params['input_options']['column_selector_options_2']['col2']
175 else: 227 else:
176 c = None 228 c = None
177 y = read_columns( 229 y = read_columns(
178 infile2, 230 infile2,
179 c = c, 231 c=c,
180 c_option = column_option, 232 c_option=column_option,
181 sep='\t', 233 sep='\t',
182 header=header, 234 header=header,
183 parse_dates=True 235 parse_dates=True)
184 )
185 y = y.ravel() 236 y = y.ravel()
186 237
187 optimizer = params['search_schemes']['selected_search_scheme'] 238 optimizer = params['search_schemes']['selected_search_scheme']
188 optimizer = getattr(model_selection, optimizer) 239 optimizer = getattr(model_selection, optimizer)
189 240
190 options = params['search_schemes']['options'] 241 options = params['search_schemes']['options']
242
191 splitter, groups = get_cv(options.pop('cv_selector')) 243 splitter, groups = get_cv(options.pop('cv_selector'))
192 if groups is None: 244 options['cv'] = splitter
193 options['cv'] = splitter
194 elif groups == '':
195 options['cv'] = list( splitter.split(X, y, groups=None) )
196 else:
197 options['cv'] = list( splitter.split(X, y, groups=groups) )
198 options['n_jobs'] = N_JOBS 245 options['n_jobs'] = N_JOBS
199 primary_scoring = options['scoring']['primary_scoring'] 246 primary_scoring = options['scoring']['primary_scoring']
200 options['scoring'] = get_scoring(options['scoring']) 247 options['scoring'] = get_scoring(options['scoring'])
201 if options['error_score']: 248 if options['error_score']:
202 options['error_score'] = 'raise' 249 options['error_score'] = 'raise'
203 else: 250 else:
204 options['error_score'] = np.NaN 251 options['error_score'] = np.NaN
205 if options['refit'] and isinstance(options['scoring'], dict): 252 if options['refit'] and isinstance(options['scoring'], dict):
206 options['refit'] = 'primary' 253 options['refit'] = primary_scoring
207 if 'pre_dispatch' in options and options['pre_dispatch'] == '': 254 if 'pre_dispatch' in options and options['pre_dispatch'] == '':
208 options['pre_dispatch'] = None 255 options['pre_dispatch'] = None
209 256
210 with open(infile_pipeline, 'rb') as pipeline_handler: 257 with open(infile_estimator, 'rb') as estimator_handler:
211 pipeline = load_model(pipeline_handler) 258 estimator = load_model(estimator_handler)
212 259
213 search_params = get_search_params(params_builder) 260 memory = joblib.Memory(location=CACHE_DIR, verbose=0)
214 searcher = optimizer(pipeline, search_params, **options) 261 # cache iraps_core fits could increase search speed significantly
262 if estimator.__class__.__name__ == 'IRAPSClassifier':
263 estimator.set_params(memory=memory)
264 else:
265 for p, v in estimator.get_params().items():
266 if p.endswith('memory'):
267 if len(p) > 8 and p[:-8].endswith('irapsclassifier'):
268 # cache iraps_core fits could increase search
269 # speed significantly
270 new_params = {p: memory}
271 estimator.set_params(**new_params)
272 elif v:
273 new_params = {p, None}
274 estimator.set_params(**new_params)
275 elif p.endswith('n_jobs'):
276 new_params = {p: 1}
277 estimator.set_params(**new_params)
278
279 param_grid = _eval_search_params(params_builder)
280 searcher = optimizer(estimator, param_grid, **options)
281
282 # do train_test_split
283 do_train_test_split = params['train_test_split'].pop('do_split')
284 if do_train_test_split == 'yes':
285 # make sure refit is choosen
286 if not options['refit']:
287 raise ValueError("Refit must be `True` for shuffle splitting!")
288 split_options = params['train_test_split']
289
290 # splits
291 if split_options['shuffle'] == 'stratified':
292 split_options['labels'] = y
293 X, X_test, y, y_test = train_test_split(X, y, **split_options)
294 elif split_options['shuffle'] == 'group':
295 if not groups:
296 raise ValueError("No group based CV option was "
297 "choosen for group shuffle!")
298 split_options['labels'] = groups
299 X, X_test, y, y_test, groups, _ =\
300 train_test_split(X, y, **split_options)
301 else:
302 if split_options['shuffle'] == 'None':
303 split_options['shuffle'] = None
304 X, X_test, y, y_test =\
305 train_test_split(X, y, **split_options)
306 # end train_test_split
215 307
216 if options['error_score'] == 'raise': 308 if options['error_score'] == 'raise':
217 searcher.fit(X, y) 309 searcher.fit(X, y, groups=groups)
218 else: 310 else:
219 warnings.simplefilter('always', FitFailedWarning) 311 warnings.simplefilter('always', FitFailedWarning)
220 with warnings.catch_warnings(record=True) as w: 312 with warnings.catch_warnings(record=True) as w:
221 try: 313 try:
222 searcher.fit(X, y) 314 searcher.fit(X, y, groups=groups)
223 except ValueError: 315 except ValueError:
224 pass 316 pass
225 for warning in w: 317 for warning in w:
226 print(repr(warning.message)) 318 print(repr(warning.message))
227 319
228 cv_result = pandas.DataFrame(searcher.cv_results_) 320 if do_train_test_split == 'no':
229 cv_result.rename(inplace=True, columns={'mean_test_primary': 'mean_test_'+primary_scoring, 'rank_test_primary': 'rank_test_'+primary_scoring}) 321 # save results
230 cv_result.to_csv(path_or_buf=outfile_result, sep='\t', header=True, index=False) 322 cv_results = pandas.DataFrame(searcher.cv_results_)
231 323 cv_results = cv_results[sorted(cv_results.columns)]
232 if outfile_estimator: 324 cv_results.to_csv(path_or_buf=outfile_result, sep='\t',
233 with open(outfile_estimator, 'wb') as output_handler: 325 header=True, index=False)
234 pickle.dump(searcher.best_estimator_, output_handler, pickle.HIGHEST_PROTOCOL) 326
327 # output test result using best_estimator_
328 else:
329 best_estimator_ = searcher.best_estimator_
330 if isinstance(options['scoring'], collections.Mapping):
331 is_multimetric = True
332 else:
333 is_multimetric = False
334
335 test_score = _score(best_estimator_, X_test,
336 y_test, options['scoring'],
337 is_multimetric=is_multimetric)
338 if not is_multimetric:
339 test_score = {primary_scoring: test_score}
340 for key, value in test_score.items():
341 test_score[key] = [value]
342 result_df = pandas.DataFrame(test_score)
343 result_df.to_csv(path_or_buf=outfile_result, sep='\t',
344 header=True, index=False)
345
346 memory.clear(warn=False)
347
348 if outfile_object:
349 with open(outfile_object, 'wb') as output_handler:
350 pickle.dump(searcher, output_handler, pickle.HIGHEST_PROTOCOL)
351
352
353 if __name__ == '__main__':
354 aparser = argparse.ArgumentParser()
355 aparser.add_argument("-i", "--inputs", dest="inputs", required=True)
356 aparser.add_argument("-e", "--estimator", dest="infile_estimator")
357 aparser.add_argument("-X", "--infile1", dest="infile1")
358 aparser.add_argument("-y", "--infile2", dest="infile2")
359 aparser.add_argument("-r", "--outfile_result", dest="outfile_result")
360 aparser.add_argument("-o", "--outfile_object", dest="outfile_object")
361 aparser.add_argument("-g", "--groups", dest="groups")
362 args = aparser.parse_args()
363
364 main(args.inputs, args.infile_estimator, args.infile1, args.infile2,
365 args.outfile_result, outfile_object=args.outfile_object,
366 groups=args.groups)