回答編集履歴
2
コード例修正
answer
CHANGED
|
@@ -2,12 +2,13 @@
|
|
|
2
2
|
```Python
|
|
3
3
|
from sklearn.feature_extraction.text import TfidfVectorizer
|
|
4
4
|
vectorizer = TfidfVectorizer()
|
|
5
|
-
X = vectorizer.fit_transform(['今日
|
|
5
|
+
X = vectorizer.fit_transform(['今日 から 働く きっと 働く', '明日 から また 天気 が よく なる', 'これから 頑張る'])
|
|
6
6
|
data = X.data
|
|
7
7
|
features = vectorizer.get_feature_names()
|
|
8
8
|
#output = [(data[i], features[i]) for i in range(len(data))]
|
|
9
|
-
print(data) # [
|
|
9
|
+
print(data) # [0.38988801 0.29651988 0.77977602 0.38988801 0.32200242 0.42339448
|
|
10
|
+
# 0.42339448 0.42339448 0.42339448 0.42339448 0.70710678 0.70710678]
|
|
10
|
-
print(features) # ['から', 'きっと', '今日', '
|
|
11
|
+
print(features) # ['から', 'きっと', 'これから', 'なる', 'また', 'よく', '今日', '働く', '天気', '明日', '頑張る']
|
|
11
|
-
print(len(data)) #
|
|
12
|
+
print(len(data)) # 12
|
|
12
|
-
print(len(features)) #
|
|
13
|
+
print(len(features)) # 11
|
|
13
14
|
```
|
1
コード修正
answer
CHANGED
|
@@ -7,6 +7,7 @@
|
|
|
7
7
|
features = vectorizer.get_feature_names()
|
|
8
8
|
#output = [(data[i], features[i]) for i in range(len(data))]
|
|
9
9
|
print(data) # [1. 1. 1. 1. 1.]
|
|
10
|
+
print(features) # ['から', 'きっと', '今日', '歩く']
|
|
10
11
|
print(len(data)) # 5
|
|
11
12
|
print(len(features)) # 4
|
|
12
13
|
```
|