-
Notifications
You must be signed in to change notification settings - Fork 545
/
main.py
executable file
·157 lines (122 loc) · 5.7 KB
/
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
from utils.utils import generate_results_csv
from utils.utils import create_directory
from utils.utils import read_dataset
from utils.utils import transform_mts_to_ucr_format
from utils.utils import visualize_filter
from utils.utils import viz_for_survey_paper
from utils.utils import viz_cam
import os
import numpy as np
import sys
import sklearn
import utils
from utils.constants import CLASSIFIERS
from utils.constants import ARCHIVE_NAMES
from utils.constants import ITERATIONS
from utils.utils import read_all_datasets
def fit_classifier():
x_train = datasets_dict[dataset_name][0]
y_train = datasets_dict[dataset_name][1]
x_test = datasets_dict[dataset_name][2]
y_test = datasets_dict[dataset_name][3]
nb_classes = len(np.unique(np.concatenate((y_train, y_test), axis=0)))
# transform the labels from integers to one hot vectors
enc = sklearn.preprocessing.OneHotEncoder(categories='auto')
enc.fit(np.concatenate((y_train, y_test), axis=0).reshape(-1, 1))
y_train = enc.transform(y_train.reshape(-1, 1)).toarray()
y_test = enc.transform(y_test.reshape(-1, 1)).toarray()
# save orignal y because later we will use binary
y_true = np.argmax(y_test, axis=1)
if len(x_train.shape) == 2: # if univariate
# add a dimension to make it multivariate with one dimension
x_train = x_train.reshape((x_train.shape[0], x_train.shape[1], 1))
x_test = x_test.reshape((x_test.shape[0], x_test.shape[1], 1))
input_shape = x_train.shape[1:]
classifier = create_classifier(classifier_name, input_shape, nb_classes, output_directory)
classifier.fit(x_train, y_train, x_test, y_test, y_true)
def create_classifier(classifier_name, input_shape, nb_classes, output_directory, verbose=True):
if classifier_name == 'fcn':
from classifiers import fcn
return fcn.Classifier_FCN(output_directory, input_shape, nb_classes, verbose)
if classifier_name == 'mlp':
from classifiers import mlp
return mlp.Classifier_MLP(output_directory, input_shape, nb_classes, verbose)
if classifier_name == 'resnet':
from classifiers import resnet
return resnet.Classifier_RESNET(output_directory, input_shape, nb_classes, verbose)
if classifier_name == 'mcnn':
from classifiers import mcnn
return mcnn.Classifier_MCNN(output_directory, verbose)
if classifier_name == 'tlenet':
from classifiers import tlenet
return tlenet.Classifier_TLENET(output_directory, verbose)
if classifier_name == 'twiesn':
from classifiers import twiesn
return twiesn.Classifier_TWIESN(output_directory, verbose)
if classifier_name == 'encoder':
from classifiers import encoder
return encoder.Classifier_ENCODER(output_directory, input_shape, nb_classes, verbose)
if classifier_name == 'mcdcnn':
from classifiers import mcdcnn
return mcdcnn.Classifier_MCDCNN(output_directory, input_shape, nb_classes, verbose)
if classifier_name == 'cnn': # Time-CNN
from classifiers import cnn
return cnn.Classifier_CNN(output_directory, input_shape, nb_classes, verbose)
if classifier_name == 'inception':
from classifiers import inception
return inception.Classifier_INCEPTION(output_directory, input_shape, nb_classes, verbose)
############################################### main
# change this directory for your machine
root_dir = '/dl-4-tsc/'
if sys.argv[1] == 'run_all':
for classifier_name in CLASSIFIERS:
print('classifier_name', classifier_name)
for archive_name in ARCHIVE_NAMES:
print('\tarchive_name', archive_name)
datasets_dict = read_all_datasets(root_dir, archive_name)
for iter in range(ITERATIONS):
print('\t\titer', iter)
trr = ''
if iter != 0:
trr = '_itr_' + str(iter)
tmp_output_directory = root_dir + '/results/' + classifier_name + '/' + archive_name + trr + '/'
for dataset_name in utils.constants.dataset_names_for_archive[archive_name]:
print('\t\t\tdataset_name: ', dataset_name)
output_directory = tmp_output_directory + dataset_name + '/'
create_directory(output_directory)
fit_classifier()
print('\t\t\t\tDONE')
# the creation of this directory means
create_directory(output_directory + '/DONE')
elif sys.argv[1] == 'transform_mts_to_ucr_format':
transform_mts_to_ucr_format()
elif sys.argv[1] == 'visualize_filter':
visualize_filter(root_dir)
elif sys.argv[1] == 'viz_for_survey_paper':
viz_for_survey_paper(root_dir)
elif sys.argv[1] == 'viz_cam':
viz_cam(root_dir)
elif sys.argv[1] == 'generate_results_csv':
res = generate_results_csv('results.csv', root_dir)
print(res.to_string())
else:
# this is the code used to launch an experiment on a dataset
archive_name = sys.argv[1]
dataset_name = sys.argv[2]
classifier_name = sys.argv[3]
itr = sys.argv[4]
if itr == '_itr_0':
itr = ''
output_directory = root_dir + '/results/' + classifier_name + '/' + archive_name + itr + '/' + \
dataset_name + '/'
test_dir_df_metrics = output_directory + 'df_metrics.csv'
print('Method: ', archive_name, dataset_name, classifier_name, itr)
if os.path.exists(test_dir_df_metrics):
print('Already done')
else:
create_directory(output_directory)
datasets_dict = read_dataset(root_dir, archive_name, dataset_name)
fit_classifier()
print('DONE')
# the creation of this directory means
create_directory(output_directory + '/DONE')