質問編集履歴
2
写真追加
title
CHANGED
|
File without changes
|
body
CHANGED
|
@@ -15,9 +15,11 @@
|
|
|
15
15
|
|
|
16
16
|
以下が作成した簡略辞書です「100.csv」
|
|
17
17
|
|
|
18
|
+
|
|
19
|
+
|
|
20
|
+
|
|
18
21
|
この辞書を読み込ませると
|
|
19
22
|
```
|
|
20
|
-
|
|
21
23
|
#作成した辞書使う場合
|
|
22
24
|
---------------------------------------------------------------------------
|
|
23
25
|
ValueError Traceback (most recent call last)
|
1
エラー内容追記
title
CHANGED
|
File without changes
|
body
CHANGED
|
@@ -19,9 +19,36 @@
|
|
|
19
19
|
```
|
|
20
20
|
|
|
21
21
|
#作成した辞書使う場合
|
|
22
|
+
---------------------------------------------------------------------------
|
|
23
|
+
ValueError Traceback (most recent call last)
|
|
24
|
+
<ipython-input-13-13ce50d97c07> in <module>()
|
|
25
|
+
53 #t = Tokenizer()
|
|
26
|
+
54 #作成した辞書使う場合
|
|
22
|
-
t = Tokenizer(r'C:\Users\Desktop\100.csv', udic_type='simpledic', udic_enc="utf8")
|
|
27
|
+
---> 55 t = Tokenizer(r'C:\Users\Desktop\100.csv', udic_type='simpledic', udic_enc="utf8")
|
|
28
|
+
56
|
|
29
|
+
57 ret = []
|
|
23
30
|
|
|
31
|
+
~\AppData\Local\Continuum\anaconda3\lib\site-packages\janome\tokenizer.py in __init__(self, udic, udic_enc, udic_type, max_unknown_length, wakati, mmap)
|
|
32
|
+
166 if udic.endswith('.csv'):
|
|
33
|
+
167 # build user dictionary from CSV
|
|
34
|
+
--> 168 self.user_dic = UserDictionary(udic, udic_enc, udic_type, connections)
|
|
35
|
+
169 elif os.path.isdir(udic):
|
|
36
|
+
170 # load compiled user dictionary
|
|
24
37
|
|
|
38
|
+
~\AppData\Local\Continuum\anaconda3\lib\site-packages\janome\dic.py in __init__(self, user_dict, enc, type, connections)
|
|
39
|
+
372 """
|
|
40
|
+
373 build_method = getattr(self, 'build' + type)
|
|
41
|
+
--> 374 compiledFST, entries = build_method(user_dict, enc)
|
|
42
|
+
375 Dictionary.__init__(self, [compiledFST], entries, connections)
|
|
43
|
+
376
|
|
44
|
+
|
|
45
|
+
~\AppData\Local\Continuum\anaconda3\lib\site-packages\janome\dic.py in buildsimpledic(self, user_dict, enc)
|
|
46
|
+
402 for line in f:
|
|
47
|
+
403 line = line.rstrip()
|
|
48
|
+
--> 404 surface, pos_major, reading = line.split(',')
|
|
49
|
+
405 part_of_speech = ','.join([pos_major, u'*', u'*', u'*'])
|
|
50
|
+
406 morph_id = len(surfaces)
|
|
51
|
+
|
|
25
52
|
ValueError: not enough values to unpack (expected 3, got 1)
|
|
26
53
|
```
|
|
27
54
|
というエラーが発生しどこが原因か分からず悩んでいます
|