Mercurial > repos > bgruening > sklearn_regression_metrics

comparison keras_deep_learning.py @ 27:95a37d463eac 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 208a8d348e7c7a182cfbe1b6f17868146428a7e2"
author bgruening
date Tue, 13 Apr 2021 20:55:18 +0000
parents fe37e4c07643
children 842d9c59b6b7
comparison
equal deleted inserted replaced
26:fa0e99359ba8 27:95a37d463eac
1 import argparse 1 import argparse
2 import json 2 import json
3 import pickle
4 import warnings
5 from ast import literal_eval
6
3 import keras 7 import keras
4 import pandas as pd 8 import pandas as pd
5 import pickle
6 import six 9 import six
7 import warnings 10 from galaxy_ml.utils import get_search_params, SafeEval, try_get_attr
8 11 from keras.models import Model, Sequential
9 from ast import literal_eval
10 from keras.models import Sequential, Model
11 from galaxy_ml.utils import try_get_attr, get_search_params, SafeEval
12 12
13 13
14 safe_eval = SafeEval() 14 safe_eval = SafeEval()
15 15
16 16
175 options.update(kwargs) 175 options.update(kwargs)
176 176
177 # merge layers 177 # merge layers
178 if 'merging_layers' in options: 178 if 'merging_layers' in options:
179 idxs = literal_eval(options.pop('merging_layers')) 179 idxs = literal_eval(options.pop('merging_layers'))
180 merging_layers = [all_layers[i-1] for i in idxs] 180 merging_layers = [all_layers[i - 1] for i in idxs]
181 new_layer = klass(**options)(merging_layers) 181 new_layer = klass(**options)(merging_layers)
182 # non-input layers 182 # non-input layers
183 elif inbound_nodes is not None: 183 elif inbound_nodes is not None:
184 new_layer = klass(**options)(all_layers[inbound_nodes-1]) 184 new_layer = klass(**options)(all_layers[inbound_nodes - 1])
185 # input layers 185 # input layers
186 else: 186 else:
187 new_layer = klass(**options) 187 new_layer = klass(**options)
188 188
189 all_layers.append(new_layer) 189 all_layers.append(new_layer)
190 190
191 input_indexes = _handle_shape(config['input_layers']) 191 input_indexes = _handle_shape(config['input_layers'])
192 input_layers = [all_layers[i-1] for i in input_indexes] 192 input_layers = [all_layers[i - 1] for i in input_indexes]
193 193
194 output_indexes = _handle_shape(config['output_layers']) 194 output_indexes = _handle_shape(config['output_layers'])
195 output_layers = [all_layers[i-1] for i in output_indexes] 195 output_layers = [all_layers[i - 1] for i in output_indexes]
196 196
197 return Model(inputs=input_layers, outputs=output_layers) 197 return Model(inputs=input_layers, outputs=output_layers)
198 198
199 199
200 def get_batch_generator(config): 200 def get_batch_generator(config):
298 ['optimizer_selection']['optimizer_type']).lower() 298 ['optimizer_selection']['optimizer_type']).lower()
299 299
300 options.update((inputs['mode_selection']['compile_params'] 300 options.update((inputs['mode_selection']['compile_params']
301 ['optimizer_selection']['optimizer_options'])) 301 ['optimizer_selection']['optimizer_options']))
302 302
303 train_metrics = (inputs['mode_selection']['compile_params'] 303 train_metrics = inputs['mode_selection']['compile_params']['metrics']
304 ['metrics']).split(',')
305 if train_metrics[-1] == 'none': 304 if train_metrics[-1] == 'none':
306 train_metrics = train_metrics[:-1] 305 train_metrics = train_metrics[:-1]
307 options['metrics'] = train_metrics 306 options['metrics'] = train_metrics
308 307
309 options.update(inputs['mode_selection']['fit_params']) 308 options.update(inputs['mode_selection']['fit_params'])