-
Notifications
You must be signed in to change notification settings - Fork 0
/
fitter_vocab.py
133 lines (118 loc) · 4.24 KB
/
fitter_vocab.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
def fitter_age():
from sklearn.feature_extraction.text import CountVectorizer
from transliterate import translit
labels = []
data_dict = {}
data = []
label = []
vectorizer = CountVectorizer()
with open('spisok', 'r') as file:
for line in file:
if len(line) < 3:
continue
line_no_spaces = line.replace(' ', '')
try:
start = int(line_no_spaces[0])
except:
labels.append(line_no_spaces[:-1])
continue
for i in range(len(line)):
if line[i] == ' ':
continue
if line[i] == '.':
line = line[i + 2:]
break
if len(labels) == 2 or len(labels) == 7:
data_dict[translit(u"{}".format(line[:-1]), "ru", reversed=True)] = len(labels)
data.append(translit(u"{}".format(line[:-1]), "ru", reversed=True))
label.append(0)
continue
data_dict[line[:-1]] = len(labels)
data.append(line[:-1])
label.append(0)
with open('modern_tech', 'r') as file:
for line in file:
if len(line) < 3:
continue
line_no_spaces = line.replace(' ', '')
try:
start = int(line_no_spaces[0])
except:
labels.append(line_no_spaces[:-1])
continue
for i in range(len(line)):
if line[i] == ' ':
continue
if line[i] == '.':
line = line[i + 2:]
break
data_dict[translit(u"{}".format(line[:-1]), "ru", reversed=True)] = len(labels)
data.append(translit(u"{}".format(line[:-1]), "ru", reversed=True))
label.append(1)
return data
def fitter_WWII():
from sklearn.feature_extraction.text import CountVectorizer
from transliterate import translit
labels = []
data_dict = {}
data = []
label = []
vectorizer = CountVectorizer()
with open('spisok', 'r') as file:
for line in file:
if len(line) < 3:
continue
line_no_spaces = line.replace(' ', '')
try:
start = int(line_no_spaces[0])
except:
labels.append(line_no_spaces[:-1])
continue
for i in range(len(line)):
if line[i] == ' ':
continue
if line[i] == '.':
line = line[i + 2:]
break
if len(labels) == 2 or len(labels) == 7:
data_dict[translit(u"{}".format(line[:-1]), "ru", reversed=True)] = len(labels)
data.append(translit(u"{}".format(line[:-1]), "ru", reversed=True))
label.append(len(labels))
continue
data_dict[line[:-1]] = len(labels)
data.append(translit(u"{}".format(line[:-1]), "ru", reversed=True))
label.append(len(labels))
return data
def fitter_modern():
from sklearn.feature_extraction.text import CountVectorizer
from transliterate import translit
labels = []
data_dict = {}
datam = []
label = []
vectorizer = CountVectorizer()
with open('modern_tech', 'r') as file:
for line in file:
if len(line) < 3:
continue
line_no_spaces = line.replace(' ', '')
try:
start = int(line_no_spaces[0])
except:
labels.append(line_no_spaces[:-1])
continue
for i in range(len(line)):
if line[i] == ' ':
continue
if line[i] == '.':
line = line[i + 2:]
break
if len(labels) == 2 or len(labels) == 7:
data_dict[translit(u"{}".format(line[:-1]), "ru", reversed=True)] = len(labels)
datam.append(translit(u"{}".format(line[:-1]), "ru", reversed=True))
label.append(0)
continue
data_dict[line[:-1]] = len(labels)
datam.append(line[:-1])
label.append(0)
return datam