質問編集履歴
2
もう一度考えます。
title
CHANGED
|
File without changes
|
body
CHANGED
|
@@ -1,20 +1,6 @@
|
|
|
1
|
-
```python
|
|
2
|
-
import text
|
|
3
|
-
|
|
1
|
+
#!/usr/bin/env python3
|
|
2
|
+
# -*- coding: utf-8 -*-
|
|
4
3
|
|
|
5
|
-
kw_volume=[]
|
|
6
|
-
mid=[]
|
|
7
|
-
for i in range(len(test1)):
|
|
8
|
-
mid=text.count_csv_noun(sentences[i])
|
|
9
|
-
result=[]
|
|
10
|
-
for x in mid:
|
|
11
|
-
if not x[0] in stopwords:
|
|
12
|
-
x[1]=int(x[1])
|
|
13
|
-
x = tuple(x)
|
|
14
|
-
result.append(x)
|
|
15
|
-
kw_volume.append(result)
|
|
16
|
-
```
|
|
17
|
-
```python(test)
|
|
18
4
|
import MeCab as mc
|
|
19
5
|
from collections import Counter
|
|
20
6
|
from argparse import ArgumentParser
|
|
@@ -31,138 +17,4 @@
|
|
|
31
17
|
if args.number_of_words:
|
|
32
18
|
return '{}'.format(count_csv(args.number_of_words))
|
|
33
19
|
if args.word_count:
|
|
34
|
-
return '{}'.format(word_line(args.word_count))
|
|
20
|
+
return '{}'.format(word_line(args.word_count))
|
|
35
|
-
#文字数カウントの関数の追加
|
|
36
|
-
def word_line(input_text):
|
|
37
|
-
with open(input_text) as f:
|
|
38
|
-
lines = f.readlines()
|
|
39
|
-
return len(lines)
|
|
40
|
-
|
|
41
|
-
#allバージョン
|
|
42
|
-
def mecab_analysis_all(text):
|
|
43
|
-
t = mc.Tagger("-Ochasen")
|
|
44
|
-
t.parse('')
|
|
45
|
-
node = t.parseToNode(text)
|
|
46
|
-
output = []
|
|
47
|
-
while node:
|
|
48
|
-
if node.surface != "": # ヘッダとフッタを除外
|
|
49
|
-
word_type = node.feature.split(",")[0]
|
|
50
|
-
if word_type in [ "動詞","名詞","形容詞"]:
|
|
51
|
-
output.append(node.surface)
|
|
52
|
-
node = node.next
|
|
53
|
-
if node is None:
|
|
54
|
-
break
|
|
55
|
-
return output
|
|
56
|
-
|
|
57
|
-
|
|
58
|
-
#名詞バージョン
|
|
59
|
-
def mecab_analysis_noun(text):
|
|
60
|
-
t = mc.Tagger("-Ochasen")
|
|
61
|
-
t.parse('')
|
|
62
|
-
node = t.parseToNode(text)
|
|
63
|
-
output = []
|
|
64
|
-
while node:
|
|
65
|
-
if node.surface != "": # ヘッダとフッタを除外
|
|
66
|
-
word_type = node.feature.split(",")[0]
|
|
67
|
-
if word_type in [ "名詞"]:
|
|
68
|
-
output.append(node.surface)
|
|
69
|
-
node = node.next
|
|
70
|
-
if node is None:
|
|
71
|
-
break
|
|
72
|
-
return output
|
|
73
|
-
|
|
74
|
-
|
|
75
|
-
#動詞バージョン
|
|
76
|
-
def mecab_analysis_verb(text):
|
|
77
|
-
t = mc.Tagger("-Ochasen")
|
|
78
|
-
t.parse('')
|
|
79
|
-
node = t.parseToNode(text)
|
|
80
|
-
output = []
|
|
81
|
-
while node:
|
|
82
|
-
if node.surface != "": # ヘッダとフッタを除外
|
|
83
|
-
word_type = node.feature.split(",")[0]
|
|
84
|
-
if word_type in [ "動詞"]:
|
|
85
|
-
output.append(node.surface)
|
|
86
|
-
node = node.next
|
|
87
|
-
if node is None:
|
|
88
|
-
break
|
|
89
|
-
return output
|
|
90
|
-
|
|
91
|
-
#形容詞バージョン
|
|
92
|
-
def mecab_analysis_adjective(text):
|
|
93
|
-
t = mc.Tagger("-Ochasen")
|
|
94
|
-
t.parse('')
|
|
95
|
-
node = t.parseToNode(text)
|
|
96
|
-
output = []
|
|
97
|
-
while node:
|
|
98
|
-
if node.surface != "": # ヘッダとフッタを除外
|
|
99
|
-
word_type = node.feature.split(",")[0]
|
|
100
|
-
if word_type in [ "形容詞"]:
|
|
101
|
-
output.append(node.surface)
|
|
102
|
-
node = node.next
|
|
103
|
-
if node is None:
|
|
104
|
-
break
|
|
105
|
-
return output
|
|
106
|
-
|
|
107
|
-
|
|
108
|
-
#inputはテキスト
|
|
109
|
-
|
|
110
|
-
#all
|
|
111
|
-
def count_csv_all(text_input):
|
|
112
|
-
text= str(text_input)
|
|
113
|
-
words = mecab_analysis_all(text)
|
|
114
|
-
counter = Counter(words)
|
|
115
|
-
output = []
|
|
116
|
-
for word, count in counter.most_common():
|
|
117
|
-
if len(word) > 0:
|
|
118
|
-
middle = [word,count]
|
|
119
|
-
output.append(middle)
|
|
120
|
-
return output
|
|
121
|
-
|
|
122
|
-
#noun
|
|
123
|
-
def count_csv_noun(text_input):
|
|
124
|
-
text= str(text_input)
|
|
125
|
-
words = mecab_analysis_noun(text)
|
|
126
|
-
counter = Counter(words)
|
|
127
|
-
output = []
|
|
128
|
-
for word, count in counter.most_common():
|
|
129
|
-
if len(word) > 0:
|
|
130
|
-
middle = [word,count]
|
|
131
|
-
output.append(middle)
|
|
132
|
-
return output
|
|
133
|
-
|
|
134
|
-
#verb
|
|
135
|
-
def count_csv_verb(text_input):
|
|
136
|
-
text= str(text_input)
|
|
137
|
-
words = mecab_analysis_verb(text)
|
|
138
|
-
counter = Counter(words)
|
|
139
|
-
output = []
|
|
140
|
-
for word, count in counter.most_common():
|
|
141
|
-
if len(word) > 0:
|
|
142
|
-
middle = [word,count]
|
|
143
|
-
output.append(middle)
|
|
144
|
-
return output
|
|
145
|
-
|
|
146
|
-
#adjective
|
|
147
|
-
def count_csv_adjective(text_input):
|
|
148
|
-
text= str(text_input)
|
|
149
|
-
words = mecab_analysis_verb(text)
|
|
150
|
-
counter = Counter(words)
|
|
151
|
-
output = []
|
|
152
|
-
for word, count in counter.most_common():
|
|
153
|
-
if len(word) > 0:
|
|
154
|
-
middle = [word,count]
|
|
155
|
-
output.append(middle)
|
|
156
|
-
return output
|
|
157
|
-
|
|
158
|
-
def banner():
|
|
159
|
-
print("単語,出現回数")
|
|
160
|
-
|
|
161
|
-
|
|
162
|
-
if __name__ == '__main__':
|
|
163
|
-
#banner()
|
|
164
|
-
result = parser()
|
|
165
|
-
print(result)
|
|
166
|
-
|
|
167
|
-
```
|
|
168
|
-
kw_volumeとmidをprintで出力すると、何もデータが入ってないんですが、それはなぜでしょうか。
|
1
書式の変更
title
CHANGED
|
File without changes
|
body
CHANGED
|
@@ -1,3 +1,4 @@
|
|
|
1
|
+
```python
|
|
1
2
|
import text
|
|
2
3
|
stopwords =["そう",","/"]
|
|
3
4
|
|
|
@@ -12,5 +13,156 @@
|
|
|
12
13
|
x = tuple(x)
|
|
13
14
|
result.append(x)
|
|
14
15
|
kw_volume.append(result)
|
|
16
|
+
```
|
|
17
|
+
```python(test)
|
|
18
|
+
import MeCab as mc
|
|
19
|
+
from collections import Counter
|
|
20
|
+
from argparse import ArgumentParser
|
|
15
21
|
|
|
22
|
+
|
|
23
|
+
def parser():
|
|
24
|
+
usage = 'Usage:python3 count_word.py [-t <FILE.txt>] [--help]'\
|
|
25
|
+
.format(__file__)
|
|
26
|
+
parser = ArgumentParser(usage=usage)
|
|
27
|
+
parser.add_argument('-l','--word_count_line',dest='word_count',help='行数' )
|
|
28
|
+
parser.add_argument('-w','--number_of_words',dest='number_of_words',help='単語数' )
|
|
29
|
+
args = parser.parse_args()
|
|
30
|
+
|
|
31
|
+
if args.number_of_words:
|
|
32
|
+
return '{}'.format(count_csv(args.number_of_words))
|
|
33
|
+
if args.word_count:
|
|
34
|
+
return '{}'.format(word_line(args.word_count))
|
|
35
|
+
#文字数カウントの関数の追加
|
|
36
|
+
def word_line(input_text):
|
|
37
|
+
with open(input_text) as f:
|
|
38
|
+
lines = f.readlines()
|
|
39
|
+
return len(lines)
|
|
40
|
+
|
|
41
|
+
#allバージョン
|
|
42
|
+
def mecab_analysis_all(text):
|
|
43
|
+
t = mc.Tagger("-Ochasen")
|
|
44
|
+
t.parse('')
|
|
45
|
+
node = t.parseToNode(text)
|
|
46
|
+
output = []
|
|
47
|
+
while node:
|
|
48
|
+
if node.surface != "": # ヘッダとフッタを除外
|
|
49
|
+
word_type = node.feature.split(",")[0]
|
|
50
|
+
if word_type in [ "動詞","名詞","形容詞"]:
|
|
51
|
+
output.append(node.surface)
|
|
52
|
+
node = node.next
|
|
53
|
+
if node is None:
|
|
54
|
+
break
|
|
55
|
+
return output
|
|
56
|
+
|
|
57
|
+
|
|
58
|
+
#名詞バージョン
|
|
59
|
+
def mecab_analysis_noun(text):
|
|
60
|
+
t = mc.Tagger("-Ochasen")
|
|
61
|
+
t.parse('')
|
|
62
|
+
node = t.parseToNode(text)
|
|
63
|
+
output = []
|
|
64
|
+
while node:
|
|
65
|
+
if node.surface != "": # ヘッダとフッタを除外
|
|
66
|
+
word_type = node.feature.split(",")[0]
|
|
67
|
+
if word_type in [ "名詞"]:
|
|
68
|
+
output.append(node.surface)
|
|
69
|
+
node = node.next
|
|
70
|
+
if node is None:
|
|
71
|
+
break
|
|
72
|
+
return output
|
|
73
|
+
|
|
74
|
+
|
|
75
|
+
#動詞バージョン
|
|
76
|
+
def mecab_analysis_verb(text):
|
|
77
|
+
t = mc.Tagger("-Ochasen")
|
|
78
|
+
t.parse('')
|
|
79
|
+
node = t.parseToNode(text)
|
|
80
|
+
output = []
|
|
81
|
+
while node:
|
|
82
|
+
if node.surface != "": # ヘッダとフッタを除外
|
|
83
|
+
word_type = node.feature.split(",")[0]
|
|
84
|
+
if word_type in [ "動詞"]:
|
|
85
|
+
output.append(node.surface)
|
|
86
|
+
node = node.next
|
|
87
|
+
if node is None:
|
|
88
|
+
break
|
|
89
|
+
return output
|
|
90
|
+
|
|
91
|
+
#形容詞バージョン
|
|
92
|
+
def mecab_analysis_adjective(text):
|
|
93
|
+
t = mc.Tagger("-Ochasen")
|
|
94
|
+
t.parse('')
|
|
95
|
+
node = t.parseToNode(text)
|
|
96
|
+
output = []
|
|
97
|
+
while node:
|
|
98
|
+
if node.surface != "": # ヘッダとフッタを除外
|
|
99
|
+
word_type = node.feature.split(",")[0]
|
|
100
|
+
if word_type in [ "形容詞"]:
|
|
101
|
+
output.append(node.surface)
|
|
102
|
+
node = node.next
|
|
103
|
+
if node is None:
|
|
104
|
+
break
|
|
105
|
+
return output
|
|
106
|
+
|
|
107
|
+
|
|
108
|
+
#inputはテキスト
|
|
109
|
+
|
|
110
|
+
#all
|
|
111
|
+
def count_csv_all(text_input):
|
|
112
|
+
text= str(text_input)
|
|
113
|
+
words = mecab_analysis_all(text)
|
|
114
|
+
counter = Counter(words)
|
|
115
|
+
output = []
|
|
116
|
+
for word, count in counter.most_common():
|
|
117
|
+
if len(word) > 0:
|
|
118
|
+
middle = [word,count]
|
|
119
|
+
output.append(middle)
|
|
120
|
+
return output
|
|
121
|
+
|
|
122
|
+
#noun
|
|
123
|
+
def count_csv_noun(text_input):
|
|
124
|
+
text= str(text_input)
|
|
125
|
+
words = mecab_analysis_noun(text)
|
|
126
|
+
counter = Counter(words)
|
|
127
|
+
output = []
|
|
128
|
+
for word, count in counter.most_common():
|
|
129
|
+
if len(word) > 0:
|
|
130
|
+
middle = [word,count]
|
|
131
|
+
output.append(middle)
|
|
132
|
+
return output
|
|
133
|
+
|
|
134
|
+
#verb
|
|
135
|
+
def count_csv_verb(text_input):
|
|
136
|
+
text= str(text_input)
|
|
137
|
+
words = mecab_analysis_verb(text)
|
|
138
|
+
counter = Counter(words)
|
|
139
|
+
output = []
|
|
140
|
+
for word, count in counter.most_common():
|
|
141
|
+
if len(word) > 0:
|
|
142
|
+
middle = [word,count]
|
|
143
|
+
output.append(middle)
|
|
144
|
+
return output
|
|
145
|
+
|
|
146
|
+
#adjective
|
|
147
|
+
def count_csv_adjective(text_input):
|
|
148
|
+
text= str(text_input)
|
|
149
|
+
words = mecab_analysis_verb(text)
|
|
150
|
+
counter = Counter(words)
|
|
151
|
+
output = []
|
|
152
|
+
for word, count in counter.most_common():
|
|
153
|
+
if len(word) > 0:
|
|
154
|
+
middle = [word,count]
|
|
155
|
+
output.append(middle)
|
|
156
|
+
return output
|
|
157
|
+
|
|
158
|
+
def banner():
|
|
159
|
+
print("単語,出現回数")
|
|
160
|
+
|
|
161
|
+
|
|
162
|
+
if __name__ == '__main__':
|
|
163
|
+
#banner()
|
|
164
|
+
result = parser()
|
|
165
|
+
print(result)
|
|
166
|
+
|
|
167
|
+
```
|
|
16
168
|
kw_volumeとmidをprintで出力すると、何もデータが入ってないんですが、それはなぜでしょうか。
|