質問編集履歴
2
追記
test
CHANGED
|
File without changes
|
test
CHANGED
|
@@ -143,3 +143,11 @@
|
|
|
143
143
|
print("system covers"+str(100*counter2/counter1)+"%")
|
|
144
144
|
|
|
145
145
|
```
|
|
146
|
+
|
|
147
|
+
追記２
|
|
148
|
+
|
|
149
|
+
実はパソコンを初期化してから試したのですが、違うエラーになりました
|
|
150
|
+
|
|
151
|
+
|
|
152
|
+
|
|
153
|
+
|
1
追記
test
CHANGED
|
File without changes
|
test
CHANGED
|
@@ -7,3 +7,139 @@
|
|
|
7
7
|
前は使えていたのですが、vscodeを使おうとあれこれいじっていたら使えなくなってしまいました
|
|
8
8
|
|
|
9
9
|
解決法を教えてください、、
|
|
10
|
+
|
|
11
|
+
|
|
12
|
+
|
|
13
|
+
追記
|
|
14
|
+
|
|
15
|
+
前はpythonコマンドだけで動いていたのですが、今はpython３コマンドでないと動きません、、
|
|
16
|
+
|
|
17
|
+
python3コマンドでも長いコードだと下の謎のエラーが発生します
|
|
18
|
+
|
|
19
|
+
shinya@shinyanoMacBook-Air Colab Notebooks % python3 probability.py
|
|
20
|
+
|
|
21
|
+
Traceback (most recent call last):
|
|
22
|
+
|
|
23
|
+
File "/Volumes/GoogleDrive/マイドライブ/Colab Notebooks/probability.py", line 1, in <module>
|
|
24
|
+
|
|
25
|
+
from nltk.stem import WordNetLemmatizer
|
|
26
|
+
|
|
27
|
+
File "/opt/homebrew/lib/python3.9/site-packages/nltk/__init__.py", line 133, in <module>
|
|
28
|
+
|
|
29
|
+
from nltk.text import *
|
|
30
|
+
|
|
31
|
+
File "/opt/homebrew/lib/python3.9/site-packages/nltk/text.py", line 30, in <module>
|
|
32
|
+
|
|
33
|
+
from nltk.tokenize import sent_tokenize
|
|
34
|
+
|
|
35
|
+
File "/opt/homebrew/lib/python3.9/site-packages/nltk/tokenize/__init__.py", line 66, in <module>
|
|
36
|
+
|
|
37
|
+
from nltk.tokenize.casual import TweetTokenizer, casual_tokenize
|
|
38
|
+
|
|
39
|
+
File "/opt/homebrew/lib/python3.9/site-packages/nltk/tokenize/casual.py", line 38, in <module>
|
|
40
|
+
|
|
41
|
+
import regex # https://github.com/nltk/nltk/issues/2409
|
|
42
|
+
|
|
43
|
+
File "/opt/homebrew/lib/python3.9/site-packages/regex/__init__.py", line 1, in <module>
|
|
44
|
+
|
|
45
|
+
from .regex import *
|
|
46
|
+
|
|
47
|
+
File "/opt/homebrew/lib/python3.9/site-packages/regex/regex.py", line 419, in <module>
|
|
48
|
+
|
|
49
|
+
import regex._regex_core as _regex_core
|
|
50
|
+
|
|
51
|
+
File "/opt/homebrew/lib/python3.9/site-packages/regex/_regex_core.py", line 21, in <module>
|
|
52
|
+
|
|
53
|
+
import regex._regex as _regex
|
|
54
|
+
|
|
55
|
+
ImportError: dlopen(/opt/homebrew/lib/python3.9/site-packages/regex/_regex.cpython-39-darwin.so, 2): no suitable image found. Did find:
|
|
56
|
+
|
|
57
|
+
/opt/homebrew/lib/python3.9/site-packages/regex/_regex.cpython-39-darwin.so: mach-o, but wrong architecture
|
|
58
|
+
|
|
59
|
+
/opt/homebrew/lib/python3.9/site-packages/regex/_regex.cpython-39-darwin.so: mach-o, but wrong architecture
|
|
60
|
+
|
|
61
|
+
```python3
|
|
62
|
+
|
|
63
|
+
from nltk.stem import WordNetLemmatizer
|
|
64
|
+
|
|
65
|
+
lemmatizer=WordNetLemmatizer()
|
|
66
|
+
|
|
67
|
+
qlist=["単語２０４７個"]
|
|
68
|
+
|
|
69
|
+
ty=input("which type?")
|
|
70
|
+
|
|
71
|
+
import os,pytesseract,enchant,nltk
|
|
72
|
+
|
|
73
|
+
from PIL import Image
|
|
74
|
+
|
|
75
|
+
counter1=0
|
|
76
|
+
|
|
77
|
+
counter2=0
|
|
78
|
+
|
|
79
|
+
os.chdir(f"/Volumes/GoogleDrive/マイドライブ/Colab Notebooks/{ty}")
|
|
80
|
+
|
|
81
|
+
for im in os.listdir(".")[1:]:
|
|
82
|
+
|
|
83
|
+
img=Image.open(im)
|
|
84
|
+
|
|
85
|
+
text=pytesseract.image_to_string(img,lang="eng")
|
|
86
|
+
|
|
87
|
+
text=text.replace("\n","")
|
|
88
|
+
|
|
89
|
+
text=nltk.word_tokenize(text)
|
|
90
|
+
|
|
91
|
+
text=nltk.pos_tag(text)
|
|
92
|
+
|
|
93
|
+
for word,type in list(set(text)):
|
|
94
|
+
|
|
95
|
+
if type in ["JJ","JJR","JJS"]:
|
|
96
|
+
|
|
97
|
+
counter1+=1
|
|
98
|
+
|
|
99
|
+
if lemmatizer.lemmatize(word,pos="a") in qlist:
|
|
100
|
+
|
|
101
|
+
counter2+=1
|
|
102
|
+
|
|
103
|
+
else:
|
|
104
|
+
|
|
105
|
+
print(word+" leaked")
|
|
106
|
+
|
|
107
|
+
elif type in ["NN","NNS","NNP","NNPS"]:
|
|
108
|
+
|
|
109
|
+
counter1+=1
|
|
110
|
+
|
|
111
|
+
if lemmatizer.lemmatize(word,pos="n"):
|
|
112
|
+
|
|
113
|
+
counter2+=1
|
|
114
|
+
|
|
115
|
+
else:
|
|
116
|
+
|
|
117
|
+
print(word+" leaked")
|
|
118
|
+
|
|
119
|
+
elif type in ["RB","RBS","RBR"]:
|
|
120
|
+
|
|
121
|
+
counter1+=1
|
|
122
|
+
|
|
123
|
+
if lemmatizer.lemmatize(word,pos="r") in qlist:
|
|
124
|
+
|
|
125
|
+
counter2+=1
|
|
126
|
+
|
|
127
|
+
else:
|
|
128
|
+
|
|
129
|
+
print(word+" leaked")
|
|
130
|
+
|
|
131
|
+
elif type in ["VB","VBD","VBG","VBN","VBP","VBZ"]:
|
|
132
|
+
|
|
133
|
+
counter1+=1
|
|
134
|
+
|
|
135
|
+
if lemmatizer.lemmatize(word,pos="v") in qlist:
|
|
136
|
+
|
|
137
|
+
counter2+=1
|
|
138
|
+
|
|
139
|
+
else:
|
|
140
|
+
|
|
141
|
+
print(word+" leaked")
|
|
142
|
+
|
|
143
|
+
print("system covers"+str(100*counter2/counter1)+"%")
|
|
144
|
+
|
|
145
|
+
```
|