Spaces:
Sleeping
Sleeping
75% to 70%
Browse files
__pycache__/language_detection.cpython-39.pyc
CHANGED
|
Binary files a/__pycache__/language_detection.cpython-39.pyc and b/__pycache__/language_detection.cpython-39.pyc differ
|
|
|
flagged/log.csv
ADDED
|
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
text,Result,Cleaned text,flag,username,timestamp
|
| 2 |
+
Edit review not workibg please do something,UN,No cleaned text,,,2023-06-04 14:34:38.389497
|
language_detection.py
CHANGED
|
@@ -257,9 +257,11 @@ def en_hi_detection(text):
|
|
| 257 |
# print(f"{word} ({pos}): {lemmatizer.lemmatize(word, pos)}")
|
| 258 |
lem_word = lemmatizer.lemmatize(word, pos)
|
| 259 |
if lem_word in wordnet.words():
|
|
|
|
| 260 |
count_en+=1
|
| 261 |
break
|
| 262 |
elif lem_word in stop_words:
|
|
|
|
| 263 |
count_en+=1
|
| 264 |
break
|
| 265 |
#print("total english words found :", count_en)
|
|
@@ -282,7 +284,7 @@ def en_hi_detection(text):
|
|
| 282 |
#print(f"Word '{word}' does not contain any Hindi letters.")
|
| 283 |
|
| 284 |
#print(count/len(words)*100, "% Hindi words found")
|
| 285 |
-
if count_en/len(words)*100>
|
| 286 |
return "eng"
|
| 287 |
elif count/len(words)*100>75:
|
| 288 |
return "hi"
|
|
|
|
| 257 |
# print(f"{word} ({pos}): {lemmatizer.lemmatize(word, pos)}")
|
| 258 |
lem_word = lemmatizer.lemmatize(word, pos)
|
| 259 |
if lem_word in wordnet.words():
|
| 260 |
+
print("wordnet :",lem_word)
|
| 261 |
count_en+=1
|
| 262 |
break
|
| 263 |
elif lem_word in stop_words:
|
| 264 |
+
print("stop_words :",lem_word)
|
| 265 |
count_en+=1
|
| 266 |
break
|
| 267 |
#print("total english words found :", count_en)
|
|
|
|
| 284 |
#print(f"Word '{word}' does not contain any Hindi letters.")
|
| 285 |
|
| 286 |
#print(count/len(words)*100, "% Hindi words found")
|
| 287 |
+
if count_en/len(words)*100>70:
|
| 288 |
return "eng"
|
| 289 |
elif count/len(words)*100>75:
|
| 290 |
return "hi"
|