質問編集履歴
1
コードを追記しました。
test
CHANGED
|
File without changes
|
test
CHANGED
|
@@ -24,7 +24,111 @@
|
|
|
24
24
|
|
|
25
25
|
|
|
26
26
|
|
|
27
|
-
コード
|
|
27
|
+
コードになります。
|
|
28
|
+
|
|
29
|
+
|
|
30
|
+
|
|
31
|
+
```
|
|
32
|
+
|
|
33
|
+
from wordcloud import WordCloud
|
|
34
|
+
|
|
35
|
+
import matplotlib.pyplot as plt
|
|
36
|
+
|
|
37
|
+
|
|
38
|
+
|
|
39
|
+
FONT_PATH =r"C:/Windows/Fonts/msmincho.ttc"
|
|
40
|
+
|
|
41
|
+
TXT_NAME = "rashomon"
|
|
42
|
+
|
|
43
|
+
|
|
44
|
+
|
|
45
|
+
|
|
46
|
+
|
|
47
|
+
def get_word_str(text):
|
|
48
|
+
|
|
49
|
+
import MeCab
|
|
50
|
+
|
|
51
|
+
import re
|
|
52
|
+
|
|
53
|
+
|
|
54
|
+
|
|
55
|
+
mecab = MeCab.Tagger()
|
|
56
|
+
|
|
57
|
+
parsed = mecab.parse(text)
|
|
58
|
+
|
|
59
|
+
lines = parsed.split('\n')
|
|
60
|
+
|
|
61
|
+
lines = lines[0:-2]
|
|
62
|
+
|
|
63
|
+
word_list = []
|
|
64
|
+
|
|
65
|
+
|
|
66
|
+
|
|
67
|
+
for line in lines:
|
|
68
|
+
|
|
69
|
+
tmp = re.split('\t|,', line)
|
|
70
|
+
|
|
71
|
+
|
|
72
|
+
|
|
73
|
+
# 名詞のみ対象
|
|
74
|
+
|
|
75
|
+
if tmp[1] in ["名詞"]:
|
|
76
|
+
|
|
77
|
+
# さらに絞り込み
|
|
78
|
+
|
|
79
|
+
if tmp[2] in ["一般", "固有名詞"]:
|
|
80
|
+
|
|
81
|
+
word_list.append(tmp[0])
|
|
82
|
+
|
|
83
|
+
|
|
84
|
+
|
|
85
|
+
return " " . join(word_list)
|
|
86
|
+
|
|
87
|
+
|
|
88
|
+
|
|
89
|
+
|
|
90
|
+
|
|
91
|
+
# テキストファイル読み込み
|
|
92
|
+
|
|
93
|
+
read_text = open(TXT_NAME + ".txt", encoding="utf8").read()
|
|
94
|
+
|
|
95
|
+
# print(read_text)
|
|
96
|
+
|
|
97
|
+
|
|
98
|
+
|
|
99
|
+
# 文字列取得
|
|
100
|
+
|
|
101
|
+
word_str = get_word_str(read_text)
|
|
102
|
+
|
|
103
|
+
print(word_str)
|
|
104
|
+
|
|
105
|
+
|
|
106
|
+
|
|
107
|
+
# 画像作成
|
|
108
|
+
|
|
109
|
+
wc = WordCloud(font_path=FONT_PATH, max_font_size=100, width=900, height=500).generate(word_str)
|
|
110
|
+
|
|
111
|
+
|
|
112
|
+
|
|
113
|
+
# 画像保存（テキストファイル名で）
|
|
114
|
+
|
|
115
|
+
wc.to_file(TXT_NAME + ".png")
|
|
116
|
+
|
|
117
|
+
|
|
118
|
+
|
|
119
|
+
# Wordクラウド化
|
|
120
|
+
|
|
121
|
+
plt.figure(figsize=(15,12))
|
|
122
|
+
|
|
123
|
+
plt.imshow(wc)
|
|
124
|
+
|
|
125
|
+
plt.axis("off")
|
|
126
|
+
|
|
127
|
+
plt.show()
|
|
128
|
+
|
|
129
|
+
|
|
130
|
+
|
|
131
|
+
```
|
|
28
132
|
|
|
29
133
|
|
|
30
134
|
|