forked from BeckResearchLab/USP-inhibition
-
Notifications
You must be signed in to change notification settings - Fork 0
/
models.py
335 lines (285 loc) · 13.2 KB
/
models.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
#!/usr/bin/env python
"""
Construct a neural network model, support vector and decision trees regression models from the data
"""
import pickle
from multiprocessing import Process
import numpy as np
from lasagne import nonlinearities
from lasagne.layers import DenseLayer
from lasagne.layers import InputLayer
from nolearn.lasagne import NeuralNet
import sklearn
__author__ = "Pearl Philip"
__credits__ = "David Beck"
__license__ = "BSD 3-Clause License"
__maintainer__ = "Pearl Philip"
__email__ = "pphilip@uw.edu"
__status__ = "Development"
NODES = 10
NN_PICKLE = 'nn_data.pkl'
SVM_PICKLE = 'svm_data.pkl'
DT_PICKLE = 'dt_data.pkl'
RR_PICKLE = 'rr_data.pkl'
BRR_PICKLE = 'brr_data.pkl'
LASSO_PICKLE = 'lasso_data.pkl'
def run_models(x_train, y_train, x_test, y_test):
"""
Function to drive all models in parallel.
:param x_train: features dataframe for model training
:param y_train: target dataframe for model training
:param x_test: features dataframe for model testing
:param y_test: target dataframe for model testing
:return: None
"""
p1 = Process(target=build_nn, args=(x_train, y_train, x_test, y_test))
p1.start()
p2 = Process(target=build_svm, args=(x_train, y_train, x_test, y_test))
p2.start()
p3 = Process(target=build_tree, args=(x_train, y_train, x_test, y_test))
p3.start()
p4 = Process(target=build_ridge, args=(x_train, y_train, x_test, y_test))
p4.start()
p5 = Process(target=build_bayesian_rr, args=(x_train, y_train, x_test, y_test))
p5.start()
p6 = Process(target=build_lasso, args=(x_train, y_train, x_test, y_test))
p6.start()
p1.join()
p2.join()
p3.join()
p4.join()
p5.join()
p6.join()
return
def build_nn(x_train, y_train, x_test, y_test):
"""
Construct a regression neural network model from input dataframe
:param x_train: features dataframe for model training
:param y_train: target dataframe for model training
:param x_test: features dataframe for model testing
:param y_test: target dataframe for model testing
:return: None
"""
# Create classification model
net = NeuralNet(layers=[('input', InputLayer),
('hidden0', DenseLayer),
('hidden1', DenseLayer),
('output', DenseLayer)],
input_shape=(None, x_train.shape[1]),
hidden0_num_units=NODES,
hidden0_nonlinearity=nonlinearities.softmax,
hidden1_num_units=NODES,
hidden1_nonlinearity=nonlinearities.softmax,
output_num_units=len(np.unique(y_train)),
output_nonlinearity=nonlinearities.softmax,
update_learning_rate=0.1,
verbose=1,
max_epochs=100)
param_grid = {'hidden0_num_units': [1, 4, 17, 25],
'hidden0_nonlinearity':
[nonlinearities.sigmoid, nonlinearities.softmax],
'hidden1_num_units': [1, 4, 17, 25],
'hidden1_nonlinearity':
[nonlinearities.sigmoid, nonlinearities.softmax],
'update_learning_rate': [0.01, 0.1, 0.5]}
grid = sklearn.grid_search.GridSearchCV(net, param_grid, verbose=0,
n_jobs=3, cv=3)
grid.fit(x_train, y_train)
y_pred = grid.predict(x_test)
# Mean absolute error regression loss
mean_abs = sklearn.metrics.mean_absolute_error(y_test, y_pred)
# Mean squared error regression loss
mean_sq = sklearn.metrics.mean_squared_error(y_test, y_pred)
# Median absolute error regression loss
median_abs = sklearn.metrics.median_absolute_error(y_test, y_pred)
# R^2 (coefficient of determination) regression score function
r2 = sklearn.metrics.r2_score(y_test, y_pred)
# Explained variance regression score function
exp_var_score = sklearn.metrics.explained_variance_score(y_test, y_pred)
# Accuracy prediction score
accuracy = sklearn.metrics.accuracy_score(y_test, y_pred)
with open(NN_PICKLE, 'wb') as results:
pickle.dump(grid, results, pickle.HIGHEST_PROTOCOL)
pickle.dump(net, results, pickle.HIGHEST_PROTOCOL)
pickle.dump(mean_abs, results, pickle.HIGHEST_PROTOCOL)
pickle.dump(mean_sq, results, pickle.HIGHEST_PROTOCOL)
pickle.dump(median_abs, results, pickle.HIGHEST_PROTOCOL)
pickle.dump(r2, results, pickle.HIGHEST_PROTOCOL)
pickle.dump(exp_var_score, results, pickle.HIGHEST_PROTOCOL)
pickle.dump(accuracy, results, pickle.HIGHEST_PROTOCOL)
pickle.dump(y_pred, results, pickle.HIGHEST_PROTOCOL)
return
def build_svm(x_train, y_train, x_test, y_test):
"""
Construct a support vector regression model from input dataframe
:param x_train: features dataframe for model training
:param y_train: target dataframe for model training
:param x_test: features dataframe for model testing
:param y_test: target dataframe for model testing
:return: None
"""
clf = sklearn.svm.SVR()
clf.fit(x_train, y_train)
y_pred = clf.predict(x_test)
# Mean absolute error regression loss
mean_abs = sklearn.metrics.mean_absolute_error(y_test, y_pred)
# Mean squared error regression loss
mean_sq = sklearn.metrics.mean_squared_error(y_test, y_pred)
# Median absolute error regression loss
median_abs = sklearn.metrics.median_absolute_error(y_test, y_pred)
# R^2 (coefficient of determination) regression score function
r2 = sklearn.metrics.r2_score(y_test, y_pred)
# Explained variance regression score function
exp_var_score = sklearn.metrics.explained_variance_score(y_test, y_pred)
# Accuracy prediction score
accuracy = sklearn.metrics.accuracy_score(y_test, y_pred)
with open(SVM_PICKLE, 'wb') as results:
pickle.dump(mean_abs, results, pickle.HIGHEST_PROTOCOL)
pickle.dump(mean_sq, results, pickle.HIGHEST_PROTOCOL)
pickle.dump(median_abs, results, pickle.HIGHEST_PROTOCOL)
pickle.dump(r2, results, pickle.HIGHEST_PROTOCOL)
pickle.dump(exp_var_score, results, pickle.HIGHEST_PROTOCOL)
pickle.dump(accuracy, results, pickle.HIGHEST_PROTOCOL)
pickle.dump(y_pred, results, pickle.HIGHEST_PROTOCOL)
return
def build_tree(x_train, y_train, x_test, y_test):
"""
Construct a decision trees regression model from input dataframe
:param x_train: features dataframe for model training
:param y_train: target dataframe for model training
:param x_test: features dataframe for model testing
:param y_test: target dataframe for model testing
:return: None
"""
clf = sklearn.tree.DecisionTreeRegressor()
clf.fit(x_train, y_train)
y_pred = clf.predict(x_test)
# Mean absolute error regression loss
mean_abs = sklearn.metrics.mean_absolute_error(y_test, y_pred)
# Mean squared error regression loss
mean_sq = sklearn.metrics.mean_squared_error(y_test, y_pred)
# Median absolute error regression loss
median_abs = sklearn.metrics.median_absolute_error(y_test, y_pred)
# R^2 (coefficient of determination) regression score function
r2 = sklearn.metrics.r2_score(y_test, y_pred)
# Explained variance regression score function
exp_var_score = sklearn.metrics.explained_variance_score(y_test, y_pred)
# Accuracy prediction score
accuracy = sklearn.metrics.accuracy_score(y_test, y_pred)
with open(DT_PICKLE, 'wb') as results:
pickle.dump(mean_abs, results, pickle.HIGHEST_PROTOCOL)
pickle.dump(mean_sq, results, pickle.HIGHEST_PROTOCOL)
pickle.dump(median_abs, results, pickle.HIGHEST_PROTOCOL)
pickle.dump(r2, results, pickle.HIGHEST_PROTOCOL)
pickle.dump(exp_var_score, results, pickle.HIGHEST_PROTOCOL)
pickle.dump(accuracy, results, pickle.HIGHEST_PROTOCOL)
pickle.dump(y_pred, results, pickle.HIGHEST_PROTOCOL)
return
def build_ridge(x_train, y_train, x_test, y_test):
"""
Construct a ridge regression model from input dataframe
:param x_train: features dataframe for model training
:param y_train: target dataframe for model training
:param x_test: features dataframe for model testing
:param y_test: target dataframe for model testing
:return: None
"""
clf = sklearn.linear_model.RidgeCV(alphas=[0.01, 0.1, 1.0, 10.0])
clf.fit(x_train, y_train)
y_pred = clf.predict(x_test)
# Mean absolute error regression loss
mean_abs = sklearn.metrics.mean_absolute_error(y_test, y_pred)
# Mean squared error regression loss
mean_sq = sklearn.metrics.mean_squared_error(y_test, y_pred)
# Median absolute error regression loss
median_abs = sklearn.metrics.median_absolute_error(y_test, y_pred)
# R^2 (coefficient of determination) regression score function
r2 = sklearn.metrics.r2_score(y_test, y_pred)
# Explained variance regression score function
exp_var_score = sklearn.metrics.explained_variance_score(y_test, y_pred)
# Accuracy prediction score
accuracy = sklearn.metrics.accuracy_score(y_test, y_pred)
# Optimal ridge regression alpha value from CV
ridge_alpha = clf.alpha_
with open(RR_PICKLE, 'wb') as results:
pickle.dump(mean_abs, results, pickle.HIGHEST_PROTOCOL)
pickle.dump(mean_sq, results, pickle.HIGHEST_PROTOCOL)
pickle.dump(median_abs, results, pickle.HIGHEST_PROTOCOL)
pickle.dump(r2, results, pickle.HIGHEST_PROTOCOL)
pickle.dump(exp_var_score, results, pickle.HIGHEST_PROTOCOL)
pickle.dump(accuracy, results, pickle.HIGHEST_PROTOCOL)
pickle.dump(ridge_alpha, results, pickle.HIGHEST_PROTOCOL)
pickle.dump(y_pred, results, pickle.HIGHEST_PROTOCOL)
return
def build_bayesian_rr(x_train, y_train, x_test, y_test):
"""
Construct a Bayesian ridge regression model from input dataframe
:param x_train: features dataframe for model training
:param y_train: target dataframe for model training
:param x_test: features dataframe for model testing
:param y_test: target dataframe for model testing
:return: None
"""
clf = sklearn.linear_model.BayesianRidge()
clf.fit(x_train, y_train)
y_pred = clf.predict(x_test)
# Mean absolute error regression loss
mean_abs = sklearn.metrics.mean_absolute_error(y_test, y_pred)
# Mean squared error regression loss
mean_sq = sklearn.metrics.mean_squared_error(y_test, y_pred)
# Median absolute error regression loss
median_abs = sklearn.metrics.median_absolute_error(y_test, y_pred)
# R^2 (coefficient of determination) regression score function
r2 = sklearn.metrics.r2_score(y_test, y_pred)
# Explained variance regression score function
exp_var_score = sklearn.metrics.explained_variance_score(y_test, y_pred)
# Accuracy prediction score
accuracy = sklearn.metrics.accuracy_score(y_test, y_pred)
# Optimal ridge regression alpha value from CV
ridge_alpha = clf.alpha_
with open(BRR_PICKLE, 'wb') as results:
pickle.dump(mean_abs, results, pickle.HIGHEST_PROTOCOL)
pickle.dump(mean_sq, results, pickle.HIGHEST_PROTOCOL)
pickle.dump(median_abs, results, pickle.HIGHEST_PROTOCOL)
pickle.dump(r2, results, pickle.HIGHEST_PROTOCOL)
pickle.dump(exp_var_score, results, pickle.HIGHEST_PROTOCOL)
pickle.dump(accuracy, results, pickle.HIGHEST_PROTOCOL)
pickle.dump(ridge_alpha, results, pickle.HIGHEST_PROTOCOL)
pickle.dump(y_pred, results, pickle.HIGHEST_PROTOCOL)
return
def build_lasso(x_train, y_train, x_test, y_test):
"""
Construct a Lasso linear model with cross validation from input dataframe
:param x_train: features dataframe for model training
:param y_train: target dataframe for model training
:param x_test: features dataframe for model testing
:param y_test: target dataframe for model testing
:return: None
"""
clf = sklearn.linear_model.LassoCV()
clf.fit(x_train, y_train)
y_pred = clf.predict(x_test)
# Mean absolute error regression loss
mean_abs = sklearn.metrics.mean_absolute_error(y_test, y_pred)
# Mean squared error regression loss
mean_sq = sklearn.metrics.mean_squared_error(y_test, y_pred)
# Median absolute error regression loss
median_abs = sklearn.metrics.median_absolute_error(y_test, y_pred)
# R^2 (coefficient of determination) regression score function
r2 = sklearn.metrics.r2_score(y_test, y_pred)
# Explained variance regression score function
exp_var_score = sklearn.metrics.explained_variance_score(y_test, y_pred)
# Accuracy prediction score
accuracy = sklearn.metrics.accuracy_score(y_test, y_pred)
# Optimal ridge regression alpha value from CV
lasso_alpha = clf.alpha_
with open(LASSO_PICKLE, 'wb') as results:
pickle.dump(mean_abs, results, pickle.HIGHEST_PROTOCOL)
pickle.dump(mean_sq, results, pickle.HIGHEST_PROTOCOL)
pickle.dump(median_abs, results, pickle.HIGHEST_PROTOCOL)
pickle.dump(r2, results, pickle.HIGHEST_PROTOCOL)
pickle.dump(exp_var_score, results, pickle.HIGHEST_PROTOCOL)
pickle.dump(accuracy, results, pickle.HIGHEST_PROTOCOL)
pickle.dump(lasso_alpha, results, pickle.HIGHEST_PROTOCOL)
pickle.dump(y_pred, results, pickle.HIGHEST_PROTOCOL)
return