回答編集履歴
2
修正
test
CHANGED
|
@@ -1,6 +1,8 @@
|
|
|
1
1
|
[countvectorizer](https://scikit-learn.org/stable/modules/generated/sklearn.feature_extraction.text.CountVectorizer.html#sklearn.feature_extraction.text.CountVectorizer)を利用することで本題の質問の本質を解決しました。
|
|
2
2
|
|
|
3
3
|
|
|
4
|
+
|
|
5
|
+
tfのデータ個数は以下。
|
|
4
6
|
|
|
5
7
|
```python
|
|
6
8
|
|
|
@@ -25,3 +27,21 @@
|
|
|
25
27
|
print(word, count)
|
|
26
28
|
|
|
27
29
|
```
|
|
30
|
+
|
|
31
|
+
|
|
32
|
+
|
|
33
|
+
idfのデータ個数は以下。
|
|
34
|
+
|
|
35
|
+
```
|
|
36
|
+
|
|
37
|
+
from sklearn.feature_extraction.text import TfidfVectorizer
|
|
38
|
+
|
|
39
|
+
t_vec = TfidfVectorizer(token_pattern=r"(?u)\b\w\w+\b")
|
|
40
|
+
|
|
41
|
+
|
|
42
|
+
|
|
43
|
+
len(t_vec.vocabulary_)
|
|
44
|
+
|
|
45
|
+
len(t_vec.idf_)
|
|
46
|
+
|
|
47
|
+
```
|
1
誤字
test
CHANGED
|
@@ -22,6 +22,6 @@
|
|
|
22
22
|
|
|
23
23
|
for word, count in zip(c_vec.get_feature_names(), one_hot_vector_count):
|
|
24
24
|
|
|
25
|
-
print(word
|
|
25
|
+
print(word, count)
|
|
26
26
|
|
|
27
27
|
```
|