-
Notifications
You must be signed in to change notification settings - Fork 0
/
ae_both_main.py
247 lines (207 loc) · 9.82 KB
/
ae_both_main.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
import torch
import json
import os
import argparse
import random
import pickle
from collections import defaultdict
import itertools
from data import DataProvider
import train_ae
import fine_tuning_mul
import fine_tuning
from copy import deepcopy
def generate_encoded_features(encoder, dataloader, normalize_flag=False):
"""
:param normalize_flag:
:param encoder:
:param dataloader:
:return:
"""
encoder.eval()
raw_feature_tensor = dataloader.dataset.tensors[0].cpu()
label_tensor = dataloader.dataset.tensors[1].cpu()
encoded_feature_tensor = encoder.cpu()(raw_feature_tensor)
if normalize_flag:
encoded_feature_tensor = torch.nn.functional.normalize(encoded_feature_tensor, p=2, dim=1)
return encoded_feature_tensor, label_tensor
def load_pickle(pickle_file):
data = []
with open(pickle_file, 'rb') as f:
try:
while True:
data.append(pickle.load(f))
except EOFError:
pass
return data
def wrap_training_params(training_params, type='unlabeled'):
aux_dict = {k: v for k, v in training_params.items() if k not in ['unlabeled', 'labeled']}
aux_dict.update(**training_params[type])
return aux_dict
def safe_make_dir(new_folder_name):
if not os.path.exists(new_folder_name):
os.makedirs(new_folder_name)
else:
print(new_folder_name, 'exists!')
def dict_to_str(d):
return "_".join(["_".join([k, str(v)]) for k, v in d.items()])
def main(args, update_params_dict):
train_fn = train_ae.train_ae
device = 'cuda' if torch.cuda.is_available() else 'cpu'
with open(os.path.join('model_save', 'train_params.json'), 'r') as f:
training_params = json.load(f)
training_params['unlabeled'].update(update_params_dict)
param_str = dict_to_str(update_params_dict)
training_params.update(
{
'device': device,
'es_flag': False,
'retrain_flag': args.retrain_flag
})
if args.omics != 'both':
training_params.update(
{
'device': device,
'model_save_folder': os.path.join('model_save', 'ae', args.omics, param_str),
'es_flag': False,
'retrain_flag': args.retrain_flag
})
safe_make_dir(training_params['model_save_folder'])
task_save_folder = os.path.join('model_save', 'ae', args.omics, param_str)
safe_make_dir(task_save_folder)
random.seed(2020)
data_provider = DataProvider(batch_size=training_params['unlabeled']['batch_size'],
target=args.measurement)
# if args.omics == 'both':
# training_params.update(
# {
# 'input_dim': sum([data_provider.shape_dict[k] for k in data_provider.shape_dict if k != 'target']),
# 'output_dim': data_provider.shape_dict['target']
# }
# )
# else:
training_params.update(
{
'output_dim': data_provider.shape_dict['target']
}
)
if args.omics != 'both':
training_params.update(
{
'input_dim': data_provider.shape_dict[args.omics],
}
)
# start unlabeled training
if args.omics == 'gex':
encoder, historys = train_fn(dataloader=data_provider.get_unlabeled_gex_dataloader(),
**wrap_training_params(training_params, type='unlabeled'))
with open(os.path.join(training_params['model_save_folder'], f'unlabel_train_history.pickle'),
'wb') as f:
for history in historys:
pickle.dump(dict(history), f)
elif args.omics == 'mut':
encoder, historys = train_fn(dataloader=data_provider.get_unlabeld_mut_dataloader(match=False),
**wrap_training_params(training_params, type='unlabeled'))
with open(os.path.join(training_params['model_save_folder'], f'unlabel_train_history.pickle'),
'wb') as f:
for history in historys:
pickle.dump(dict(history), f)
else:
training_params.update(
{
'model_save_folder': os.path.join('model_save', 'ae', 'gex', param_str),
'input_dim': data_provider.shape_dict['gex'],
})
safe_make_dir(training_params['model_save_folder'])
gex_encoder, gex_historys = train_fn(dataloader=data_provider.get_unlabeled_gex_dataloader(),
**wrap_training_params(training_params, type='unlabeled'))
training_params.update(
{
'model_save_folder': os.path.join('model_save', 'ae', 'mut', param_str),
'input_dim': data_provider.shape_dict['mut'],
})
safe_make_dir(training_params['model_save_folder'])
mut_encoder, mut_historys = train_fn(dataloader=data_provider.get_unlabeld_mut_dataloader(match=False),
**wrap_training_params(training_params, type='unlabeled'))
ft_evaluation_metrics = defaultdict(list)
fold_count = 0
if args.omics == 'gex':
labeled_dataloader_generator = data_provider.get_labeled_data_generator(omics='gex')
for train_labeled_dataloader, val_labeled_dataloader in labeled_dataloader_generator:
ft_encoder = deepcopy(encoder)
target_regressor, ft_historys = fine_tuning.fine_tune_encoder(
encoder=ft_encoder,
train_dataloader=train_labeled_dataloader,
val_dataloader=val_labeled_dataloader,
test_dataloader=val_labeled_dataloader,
seed=fold_count,
metric_name=args.metric,
task_save_folder=task_save_folder,
**wrap_training_params(training_params, type='labeled')
)
for metric in ['dpearsonr', 'dspearmanr','drmse', 'cpearsonr', 'cspearmanr','crmse']:
ft_evaluation_metrics[metric].append(ft_historys[-2][metric][ft_historys[-2]['best_index']])
fold_count += 1
elif args.omics == 'mut':
labeled_dataloader_generator = data_provider.get_labeled_data_generator(omics='mut')
test_ft_evaluation_metrics = defaultdict(list)
for train_labeled_dataloader, val_labeled_dataloader, test_labeled_dataloader in labeled_dataloader_generator:
ft_encoder = deepcopy(encoder)
target_regressor, ft_historys = fine_tuning.fine_tune_encoder(
encoder=ft_encoder,
train_dataloader=train_labeled_dataloader,
val_dataloader=val_labeled_dataloader,
test_dataloader=test_labeled_dataloader,
seed=fold_count,
metric_name=args.metric,
task_save_folder=task_save_folder,
**wrap_training_params(training_params, type='labeled')
)
for metric in ['dpearsonr', 'dspearmanr','drmse', 'cpearsonr', 'cspearmanr','crmse']:
ft_evaluation_metrics[metric].append(ft_historys[-2][metric][ft_historys[-2]['best_index']])
test_ft_evaluation_metrics[metric].append(ft_historys[-1][metric][ft_historys[-2]['best_index']])
fold_count += 1
with open(os.path.join(task_save_folder, f'{param_str}_test_ft_evaluation_results.json'), 'w') as f:
json.dump(test_ft_evaluation_metrics, f)
else:
labeled_dataloader_generator = data_provider.get_labeled_data_generator(omics='both')
for train_labeled_dataloader, val_labeled_dataloader in labeled_dataloader_generator:
ft_gex_encoder = deepcopy(gex_encoder)
ft_mut_encoder = deepcopy(mut_encoder)
target_regressor, ft_historys = fine_tuning_mul.fine_tune_encoder(
encoders=[ft_gex_encoder, ft_mut_encoder],
train_dataloader=train_labeled_dataloader,
val_dataloader=val_labeled_dataloader,
test_dataloader=val_labeled_dataloader,
seed=fold_count,
metric_name=args.metric,
task_save_folder=task_save_folder,
**wrap_training_params(training_params, type='labeled')
)
for metric in ['dpearsonr', 'dspearmanr','drmse', 'cpearsonr', 'cspearmanr','crmse']:
ft_evaluation_metrics[metric].append(ft_historys[-2][metric][ft_historys[-2]['best_index']])
fold_count += 1
with open(os.path.join(task_save_folder, f'{param_str}_ft_evaluation_results.json'), 'w') as f:
json.dump(ft_evaluation_metrics, f)
if __name__ == '__main__':
parser = argparse.ArgumentParser('CLEIT training and evaluation')
parser.add_argument('--omics', dest='omics', nargs='?', default='both',
choices=['gex', 'mut', 'both'])
parser.add_argument('--metric', dest='metric', nargs='?', default='cpearsonr', choices=['cpearsonr', 'dpearsonr'])
parser.add_argument('--measurement', dest='measurement', nargs='?', default='AUC', choices=['AUC', 'LN_IC50'])
parser.add_argument('--n', dest='n', nargs='?', type=int, default=5)
train_group = parser.add_mutually_exclusive_group(required=False)
train_group.add_argument('--train', dest='retrain_flag', action='store_true')
train_group.add_argument('--no-train', dest='retrain_flag', action='store_false')
parser.set_defaults(retrain_flag=False)
args = parser.parse_args()
params_grid = {
#"pretrain_num_epochs": [0, 50, 100, 200, 300],
#"train_num_epochs": [100, 300, 500, 1000, 2000, 3000, 5000],
"train_num_epochs": [100, 300, 500, 1000, 2000, 3000, 5000],
"dop": [0.0, 0.1]
}
keys, values = zip(*params_grid.items())
update_params_dict_list = [dict(zip(keys, v)) for v in itertools.product(*values)]
for param_dict in update_params_dict_list:
main(args=args, update_params_dict=param_dict)