質問編集履歴
9
誤記修正
title
CHANGED
File without changes
|
body
CHANGED
@@ -45,7 +45,7 @@
|
|
45
45
|
print(type(count))
|
46
46
|
print(count.shape)
|
47
47
|
```
|
48
|
-
>
|
48
|
+
>test5.py
|
49
49
|
(0, 1) 1
|
50
50
|
(0, 7) 1
|
51
51
|
(0, 5) 1
|
8
質問に情報を追加
title
CHANGED
File without changes
|
body
CHANGED
@@ -16,52 +16,51 @@
|
|
16
16
|
以下、count.csvファイルをエディタ等で開いた表示
|
17
17
|
" (0, 0) 29
|
18
18
|
(0, 1) 22
|
19
|
-
|
19
|
+
省略
|
20
|
-
(0, 4) 25
|
21
|
-
(0, 7) 1
|
22
|
-
(0, 9) 5
|
23
|
-
(0, 10) 10
|
24
|
-
(0, 11) 110
|
25
|
-
(0, 12) 2
|
26
|
-
(0, 13) 6
|
27
|
-
(0, 14) 40
|
28
|
-
(0, 15) 33
|
29
|
-
(0, 16) 11
|
30
|
-
(0, 17) 8
|
31
|
-
(0, 20) 28
|
32
|
-
(0, 22) 1
|
33
|
-
(0, 23) 1
|
34
|
-
(0, 24) 10
|
35
|
-
(0, 25) 13
|
36
|
-
(0, 26) 5
|
37
|
-
(0, 27) 14
|
38
|
-
(0, 29) 40
|
39
|
-
(0, 30) 7
|
40
20
|
(0, 31) 6
|
41
21
|
(0, 32) 6
|
42
22
|
: :
|
43
23
|
(0, 28745) 11
|
44
24
|
(0, 28749) 3
|
45
|
-
|
25
|
+
省略
|
46
|
-
(0, 28751) 1
|
47
|
-
(0, 28753) 5
|
48
|
-
(0, 28757) 1
|
49
|
-
(0, 28759) 10
|
50
|
-
(0, 28760) 1
|
51
|
-
(0, 28764) 2
|
52
|
-
(0, 28766) 6
|
53
|
-
(0, 28767) 93
|
54
|
-
(0, 28768) 1
|
55
|
-
(0, 28770) 12
|
56
|
-
(0, 28771) 25
|
57
|
-
(0, 28774) 2
|
58
|
-
(0, 28775) 7
|
59
|
-
(0, 28779) 58
|
60
|
-
(0, 28780) 21
|
61
|
-
(0, 28782) 2
|
62
|
-
(0, 28784) 13
|
63
|
-
(0, 28785) 7
|
64
|
-
(0, 28787) 1
|
65
|
-
(0, 28790) 2
|
66
26
|
(0, 28791) 1
|
67
|
-
(0, 28793) 26"
|
27
|
+
(0, 28793) 26"
|
28
|
+
|
29
|
+
実際のdetaは、test5.pyのサンプルにように単語がブランクで区切られた文字列の配列です。
|
30
|
+
countの型とサイズは以下の通りです。
|
31
|
+
print(type(count)): <class 'scipy.sparse.csr.csr_matrix'>
|
32
|
+
print(count.shape):(1, 28799)
|
33
|
+
|
34
|
+
<test5.py>
|
35
|
+
```python
|
36
|
+
from sklearn.feature_extraction.text import CountVectorizer
|
37
|
+
import csv
|
38
|
+
data = ['Twinkle twinkle little star' 'How I wonder what you are' 'Up above the world so high' 'Like a diamond in the sky' 'Twinkle twinkle little star' 'How I wonder what you are']
|
39
|
+
csvc_vec = CountVectorizer()
|
40
|
+
count = csvc_vec.fit_transform(data)
|
41
|
+
with open('count.csv', 'wt') as f:
|
42
|
+
writer = csv.writer(f)
|
43
|
+
writer.writerows(count)
|
44
|
+
print(count)
|
45
|
+
print(type(count))
|
46
|
+
print(count.shape)
|
47
|
+
```
|
48
|
+
>115.test5.py
|
49
|
+
(0, 1) 1
|
50
|
+
(0, 7) 1
|
51
|
+
(0, 5) 1
|
52
|
+
(0, 3) 1
|
53
|
+
(0, 4) 1
|
54
|
+
(0, 8) 1
|
55
|
+
(0, 14) 1
|
56
|
+
(0, 10) 2
|
57
|
+
(0, 0) 1
|
58
|
+
(0, 2) 1
|
59
|
+
(0, 15) 2
|
60
|
+
(0, 12) 2
|
61
|
+
(0, 13) 2
|
62
|
+
(0, 9) 2
|
63
|
+
(0, 6) 2
|
64
|
+
(0, 11) 3
|
65
|
+
<class 'scipy.sparse.csr.csr_matrix'>
|
66
|
+
(1, 16)
|
7
出力の説明を補足
title
CHANGED
File without changes
|
body
CHANGED
@@ -13,7 +13,7 @@
|
|
13
13
|
writer = csv.writer(f)
|
14
14
|
writer.writerows(count)
|
15
15
|
```
|
16
|
-
以下、count.csvファイルを開いた
|
16
|
+
以下、count.csvファイルをエディタ等で開いた表示
|
17
17
|
" (0, 0) 29
|
18
18
|
(0, 1) 22
|
19
19
|
(0, 2) 2
|
6
出力結果の説明補足
title
CHANGED
File without changes
|
body
CHANGED
@@ -13,7 +13,7 @@
|
|
13
13
|
writer = csv.writer(f)
|
14
14
|
writer.writerows(count)
|
15
15
|
```
|
16
|
-
|
16
|
+
以下、count.csvファイルを開いた内容
|
17
17
|
" (0, 0) 29
|
18
18
|
(0, 1) 22
|
19
19
|
(0, 2) 2
|
5
サンプルコード修正
title
CHANGED
File without changes
|
body
CHANGED
@@ -4,10 +4,13 @@
|
|
4
4
|
全データを出力するにはどうすれば良いでしょうか?
|
5
5
|
|
6
6
|
```python
|
7
|
+
from sklearn.feature_extraction.text import CountVectorizer
|
8
|
+
import csv
|
9
|
+
|
7
|
-
|
10
|
+
csvc_vec = CountVectorizer()
|
8
11
|
count = c_vec.fit_transform(data)
|
9
12
|
with open('count.csv', 'wt') as f:
|
10
|
-
|
13
|
+
writer = csv.writer(f)
|
11
14
|
writer.writerows(count)
|
12
15
|
```
|
13
16
|
|
4
コードのインデントを修正
title
CHANGED
File without changes
|
body
CHANGED
@@ -7,7 +7,7 @@
|
|
7
7
|
import csvc_vec = CountVectorizer()
|
8
8
|
count = c_vec.fit_transform(data)
|
9
9
|
with open('count.csv', 'wt') as f:
|
10
|
-
|
10
|
+
writer = csv.writer(f)
|
11
11
|
writer.writerows(count)
|
12
12
|
```
|
13
13
|
|
3
コードをMarkdown記法を適用
title
CHANGED
File without changes
|
body
CHANGED
@@ -3,12 +3,13 @@
|
|
3
3
|
|
4
4
|
全データを出力するにはどうすれば良いでしょうか?
|
5
5
|
|
6
|
+
```python
|
6
7
|
import csvc_vec = CountVectorizer()
|
7
8
|
count = c_vec.fit_transform(data)
|
8
9
|
with open('count.csv', 'wt') as f:
|
9
|
-
|
10
|
+
writer = csv.writer(f)
|
10
11
|
writer.writerows(count)
|
11
|
-
|
12
|
+
```
|
12
13
|
|
13
14
|
" (0, 0) 29
|
14
15
|
(0, 1) 22
|
2
サンプルコードを修正
title
CHANGED
File without changes
|
body
CHANGED
File without changes
|
1
サンプルコードの入力ミスを修正
title
CHANGED
File without changes
|
body
CHANGED
@@ -4,10 +4,10 @@
|
|
4
4
|
全データを出力するにはどうすれば良いでしょうか?
|
5
5
|
|
6
6
|
import csvc_vec = CountVectorizer()
|
7
|
-
|
7
|
+
count = c_vec.fit_transform(data)
|
8
|
-
with open('
|
8
|
+
with open('count.csv', 'wt') as f:
|
9
9
|
writer = csv.writer(f)
|
10
|
-
writer.writerows(
|
10
|
+
writer.writerows(count)
|
11
11
|
|
12
12
|
|
13
13
|
" (0, 0) 29
|