Spaces:
Runtime error
Runtime error
File size: 3,622 Bytes
f3d8098 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 |
import nltk
from nltk.corpus import wordnet
import re
from nltk.stem import WordNetLemmatizer
stop_words = ['i',
'me',
'my',
'myself',
'we',
'our',
'ours',
'ourselves',
'you',
"you're",
"you've",
"you'll",
"you'd",
'your',
'yours',
'yourself',
'yourselves',
'he',
'him',
'his',
'himself',
'she',
"she's",
'her',
'hers',
'herself',
'it',
"it's",
'its',
'itself',
'they',
'them',
'their',
'theirs',
'themselves',
'what',
'which',
'who',
'whom',
'this',
'that',
"that'll",
'these',
'those',
'am',
'is',
'are',
'was',
'were',
'be',
'been',
'being',
'have',
'has',
'had',
'having',
'do',
'does',
'did',
'doing',
'a',
'an',
'the',
'and',
'but',
'if',
'or',
'because',
'as',
'until',
'while',
'of',
'at',
'by',
'for',
'with',
'about',
'against',
'between',
'into',
'through',
'during',
'before',
'after',
'above',
'below',
'to',
'from',
'up',
'down',
'in',
'out',
'on',
'off',
'over',
'under',
'again',
'further',
'then',
'once',
'here',
'there',
'when',
'where',
'why',
'how',
'all',
'any',
'both',
'each',
'few',
'more',
'most',
'other',
'some',
'such',
'no',
'nor',
'not',
'only',
'own',
'same',
'so',
'than',
'too',
'very',
's',
't',
'can',
'will',
'just',
'don',
"don't",
'should',
"should've",
'now',
'd',
'll',
'm',
'o',
're',
've',
'y',
'ain',
'aren',
"aren't",
'couldn',
"couldn't",
'didn',
"didn't",
'doesn',
"doesn't",
'hadn',
"hadn't",
'hasn',
"hasn't",
'haven',
"haven't",
'isn',
"isn't",
'ma',
'mightn',
"mightn't",
'mustn',
"mustn't",
'needn',
"needn't",
'shan',
"shan't",
'shouldn',
"shouldn't",
'wasn',
"wasn't",
'weren',
"weren't",
'won',
"won't",
'wouldn',
"wouldn't"]
# Create a lemmatizer object
lemmatizer = WordNetLemmatizer()
#from english_words import get_english_words_set
#web2lowerset = get_english_words_set(['web2'], lower=True)
# Define the Unicode range for Hindi letters
HINDI_UNICODE_RANGE = (0x0900, 0x097F)
# Function to check if a given character is a Hindi letter
def is_hindi_letter(c):
return ord(c) >= HINDI_UNICODE_RANGE[0] and ord(c) <= HINDI_UNICODE_RANGE[1]
# In[8]:
def en_hi_detection(text):
text = re.sub(r'[^\w\s]', ' ', text)
words = text.lower().strip().split()
count_en = 0
# Lemmatize words for all POS
for word in words:
for pos in [wordnet.NOUN, wordnet.VERB, wordnet.ADJ, wordnet.ADV]:
# print(f"{word} ({pos}): {lemmatizer.lemmatize(word, pos)}")
lem_word = lemmatizer.lemmatize(word, pos)
if lem_word in nltk.corpus.wordnet.words():
count_en+=1
break
elif lem_word in stop_words:
count_en+=1
break
#print("total english words found :", count_en)
#print("length of sentence :", len(words))
#print(count_en/len(words)*100, "% english words found")
count = 0
# Check each word for Hindi letters and print the results
for word in words:
hindi_letters = []
for c in word:
if is_hindi_letter(c):
hindi_letters.append(c)
if hindi_letters:
#print(f"Word '{word}' contains Hindi letters: {' '.join(hindi_letters)}")
count+=1
else:
pass
#print(f"Word '{word}' does not contain any Hindi letters.")
#print(count/len(words)*100, "% Hindi words found")
if count_en/len(words)*100>75:
return "eng"
elif count/len(words)*100>75:
return "hi"
else :
return "unknown"
|