質問編集履歴
2
エラー文の全文掲載
test
CHANGED
|
File without changes
|
test
CHANGED
|
@@ -12,7 +12,45 @@
|
|
|
12
12
|
|
|
13
13
|
```
|
|
14
14
|
|
|
15
|
+
(base) C:\jikken>python genModel.py
|
|
16
|
+
|
|
17
|
+
C:\Anaconda\lib\site-packages\gensim\utils.py:1212: UserWarning: detected Windows; aliasing chunkize to chunkize_serial
|
|
18
|
+
|
|
19
|
+
warnings.warn("detected Windows; aliasing chunkize to chunkize_serial")
|
|
20
|
+
|
|
21
|
+
Traceback (most recent call last):
|
|
22
|
+
|
|
23
|
+
File "genModel.py", line 5, in <module>
|
|
24
|
+
|
|
25
|
+
model = word2vec.Word2Vec(data, size=200)
|
|
26
|
+
|
|
27
|
+
File "C:\Anaconda\lib\site-packages\gensim\models\word2vec.py", line 767, in __init__
|
|
28
|
+
|
|
29
|
+
fast_version=FAST_VERSION)
|
|
30
|
+
|
|
31
|
+
File "C:\Anaconda\lib\site-packages\gensim\models\base_any2vec.py", line 759, in __init__
|
|
32
|
+
|
|
33
|
+
self.build_vocab(sentences=sentences, corpus_file=corpus_file, trim_rule=trim_rule)
|
|
34
|
+
|
|
35
|
+
File "C:\Anaconda\lib\site-packages\gensim\models\base_any2vec.py", line 936, in build_vocab
|
|
36
|
+
|
|
37
|
+
sentences=sentences, corpus_file=corpus_file, progress_per=progress_per, trim_rule=trim_rule)
|
|
38
|
+
|
|
39
|
+
File "C:\Anaconda\lib\site-packages\gensim\models\word2vec.py", line 1571, in scan_vocab
|
|
40
|
+
|
|
41
|
+
total_words, corpus_count = self._scan_vocab(sentences, progress_per, trim_rule)
|
|
42
|
+
|
|
43
|
+
File "C:\Anaconda\lib\site-packages\gensim\models\word2vec.py", line 1540, in _scan_vocab
|
|
44
|
+
|
|
45
|
+
for sentence_no, sentence in enumerate(sentences):
|
|
46
|
+
|
|
47
|
+
File "C:\Anaconda\lib\site-packages\gensim\models\word2vec.py", line 1363, in __iter__
|
|
48
|
+
|
|
49
|
+
text = rest + fin.read(8192) # avoid loading the entire file (=1 line) into RAM
|
|
50
|
+
|
|
15
51
|
UnicodeDecodeError: 'cp932' codec can't decode byte 0xef in position 0: illegal multibyte sequence
|
|
52
|
+
|
|
53
|
+
|
|
16
54
|
|
|
17
55
|
```
|
|
18
56
|
|
1
追記
test
CHANGED
|
File without changes
|
test
CHANGED
|
@@ -57,3 +57,5 @@
|
|
|
57
57
|
|
|
58
58
|
|
|
59
59
|
tweet.csvは文字コードをutf-8で保存してあります。
|
|
60
|
+
|
|
61
|
+
また、csvファイルの中身はすべて日本語のツイートのみです。
|