Newer
Older
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
import sys
import os
import time
import argparse
import pandas as pd
from data_preprocessing import Preprocessor
from features_extractor import feature_extractor
from ClassPreprocessor import remove_weak_classes, resample_classes, create_dict, split_class
from classifiers import classifiers, grid_params
from sklearn.model_selection import train_test_split
from sklearn import preprocessing
from evaluate_model import evaluate_model
from sklearn.model_selection import GridSearchCV
import configparser
parser = argparse.ArgumentParser()
parser.add_argument("dataPath", help="Path of the dataframe")
parser.add_argument("columnText", help="the column name of the text that should preproceed", default = 'content')
parser.add_argument("columnClass", help="ColumnClass the column name of the classes")
parser.add_argument("minOfInstancePerClass", help="minOfInstancePerClass the minimum of instance required for each class", type=int)
parser.add_argument("maxOfInstancePerClass", help="maxOfInstancePerClass the maximum of instance required resamling classes", type=int)
args = parser.parse_args()
dataPath = args.dataPath
columnText = args.columnText
columnClass = args.columnClass
minOfInstancePerClass = args.minOfInstancePerClass
maxOfInstancePerClass = args.maxOfInstancePerClass
# create directory in the reports directory so save the classification results
dir_name_report = str(minOfInstancePerClass) + '_' + str(maxOfInstancePerClass)
if not os.path.exists(os.path.join('reports', columnClass, dir_name_report)):
os.makedirs(os.path.join('reports', columnClass, dir_name_report))
# Reading data and preprocessings steps
preprocessor = Preprocessor()
df = df_original[[columnClass,columnText]].copy()
preprocessor.remove_null_rows(df, columnText)
preprocessor.remove_null_rows(df, columnClass)
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
df = remove_weak_classes(df, columnClass, minOfInstancePerClass )
df = resample_classes(df, columnClass, maxOfInstancePerClass)
preprocessor.getFirstParagraph(df, columnText, 'paragraphe' ) # select first sentence of each text
#Read configuration file for retreiving parameters of features extractors
config = configparser.ConfigParser()
config.read('settings.conf')
vectorization_max_df = int(config.get('vectorizers','vectorization_max_df')) if config.get('vectorizers','vectorization_max_df').isdigit() else float(config.get('vectorizers','vectorization_max_df'))
vectorization_min_df = int(config.get('vectorizers','vectorization_min_df')) if config.get('vectorizers','vectorization_min_df').isdigit() else float(config.get('vectorizers','vectorization_min_df'))
vectorization_numberOfFeatures = int(config.get('vectorizers','vectorization_numberOfFeatures')) if config.get('vectorizers','vectorization_numberOfFeatures').isdigit() else None
doc2vec_vec_size = int(config.get('vectorizers','doc2vec_vec_size'))
doc2vec_epochs = int(config.get('vectorizers','doc2vec_epochs'))
doc2vec_lr = float(config.get('vectorizers','doc2vec_lr'))
extractor = feature_extractor(df,columnText, columnClass)
extractor_paragraphe = feature_extractor(df,'paragraphe', columnClass)
features_techniques = [
('counter', extractor.count_vect(max_df = vectorization_max_df, min_df = vectorization_min_df, numberOfFeatures = vectorization_numberOfFeatures )),
('tf_idf', extractor.tf_idf(max_df = vectorization_max_df, min_df = vectorization_min_df, numberOfFeatures = vectorization_numberOfFeatures)),
('doc2vec', extractor.doc2vec(doc2vec_epochs, doc2vec_vec_size, doc2vec_lr))]
features_techniques_paragraphe = [
('counter', extractor_paragraphe.count_vect(max_df = vectorization_max_df, min_df = vectorization_min_df, numberOfFeatures = vectorization_numberOfFeatures )),
('tf_idf', extractor_paragraphe.tf_idf(max_df = vectorization_max_df, min_df = vectorization_min_df, numberOfFeatures = vectorization_numberOfFeatures)),
('doc2vec', extractor_paragraphe.doc2vec(doc2vec_epochs, doc2vec_vec_size, doc2vec_lr))]
#prepare data
df = df[df[columnClass] != 'unclassified']
y = df[columnClass]
#case of full text
for feature_technique_name, features in features_techniques:
train_x, test_x, train_y, test_y = train_test_split(features, y, test_size=0.33, random_state=42, stratify = y )
encoder = preprocessing.LabelEncoder()
train_y = encoder.fit_transform(train_y)
valid_y = encoder.fit_transform(test_y)
for tmp_clf, tmp_grid_params in zip(classifiers, grid_params):
clf_name, clf = tmp_clf
grid_param_name, grid_param = tmp_grid_params
print(clf_name, clf, grid_param_name, grid_param)
if clf_name == 'bayes' :
if feature_technique_name == 'doc2vec':
continue
else:
t_begin = time.time()
clf.fit(train_x, train_y)
t_end =time.time()
training_time = t_end - t_begin
y_pred = clf.predict(test_x)
else :
clf = GridSearchCV(clf, grid_param, refit = True, verbose = 3)
t_begin = time.time()
clf.fit(train_x, train_y)
t_end =time.time()
training_time = t_end - t_begin
y_pred = clf.predict(test_x)
#evaluate model
file_name_report = feature_technique_name + '_' + clf_name
report, accuracy, weighted_avg = evaluate_model(clf, test_x, valid_y, y_pred, valid_y, [str(e) for e in encoder.transform(encoder.classes_)], encoder.classes_, os.path.join('reports', columnClass, dir_name_report, file_name_report)+'.pdf')
with open(os.path.join('reports', columnClass, dir_name_report, file_name_report+'.txt'), 'w') as f:
sys.stdout = f # Change the standard output to the file we created.
print(report)
print('accuracy : {}'.format(accuracy))
print('weighted_Precision : {}'.format(weighted_avg['precision']))
print('weighted_Recall : {}'.format(weighted_avg['recall']))
print('weighted_F-score : {}'.format(weighted_avg['f1-score']))
print('weighted_Support : {}'.format(weighted_avg['support']))
print(dict(zip(encoder.classes_, encoder.transform(encoder.classes_))))
print('training time : {}'.format(training_time))
#sys.stdout = sys.stdout # Reset the standard output to its original value
sys.stdout = sys.__stdout__
for feature_technique_name, features in features_techniques_paragraphe:
train_x, test_x, train_y, test_y = train_test_split(features, y, test_size=0.33, random_state=42, stratify = y )
encoder = preprocessing.LabelEncoder()
train_y = encoder.fit_transform(train_y)
valid_y = encoder.fit_transform(test_y)
for tmp_clf, clf_grid_params in zip(classifiers, grid_params):
clf_name, clf = tmp_clf
grid_param_name, grid_param = tmp_grid_params
if clf_name == 'bayes' :
if feature_technique_name == 'doc2vec':
continue
else:
t_begin = time.time()
clf.fit(train_x, train_y)
t_end =time.time()
training_time = t_end - t_begin
y_pred = clf.predict(test_x)
else :
clf = GridSearchCV(clf, grid_param, refit = True, verbose = 3)
t_begin = time.time()
clf.fit(train_x, train_y)
t_end =time.time()
training_time = t_end - t_begin
y_pred = clf.predict(test_x)
#evaluate model
file_name_report_paragraphe = feature_technique_name + '_paragraphe_' + clf_name
report, accuracy, weighted_avg = evaluate_model(clf, test_x, valid_y, y_pred, valid_y, [str(e) for e in encoder.transform(encoder.classes_)], encoder.classes_, os.path.join('reports', columnClass, dir_name_report, file_name_report_paragraphe)+'.pdf')
with open(os.path.join('reports', columnClass, dir_name_report, file_name_report_paragraphe+'.txt'), 'w') as f:
sys.stdout = f # Change the standard output to the file we created.
print(report)
print('accuracy : {}'.format(accuracy))
print('weighted_Precision : {}'.format(weighted_avg['precision']))
print('weighted_Recall : {}'.format(weighted_avg['recall']))
print('weighted_F-score : {}'.format(weighted_avg['f1-score']))
print('weighted_Support : {}'.format(weighted_avg['support']))
print(dict(zip(encoder.classes_, encoder.transform(encoder.classes_))))
print('training time : {}'.format(training_time))
sys.stdout = sys.stdout # Reset the standard output to its original value
sys.stdout = sys.__stdout__