corrected regex for occurences search

preprocessing.py

@@ -8,7 +8,7 @@ def extract_verbs_occurences_from_articles(verbs, articles):
 
 
 	for i in tqdm(range(len(verbs))):
 	for i in tqdm(range(len(verbs))):
 		# finish the pattern
 		# finish the pattern
-		pattern = '.*\W' + verbs[8][i] + '.*'
+		pattern = '^(.*\W)*' + verbs[8][i] + '(?!(mi|ja)).*$'
 		occurences = list(set([sentence + '.' for sentence in articles.split('.') if re.match(pattern, sentence)]))
 		occurences = list(set([sentence + '.' for sentence in articles.split('.') if re.match(pattern, sentence)]))
 		verbs['occurences'][i] = filter_wrong_occurences(verbs.iloc[i], occurences)
 		verbs['occurences'][i] = filter_wrong_occurences(verbs.iloc[i], occurences)
 	save_csv(verbs, "with_approximate_occurences.csv")
 	save_csv(verbs, "with_approximate_occurences.csv")
@@ -20,7 +20,7 @@ def filter_wrong_occurences(verb, occurences):
 	for occurence in occurences:
 	for occurence in occurences:
 		found = False
 		found = False
 		for form in all_forms:
 		for form in all_forms:
-			pattern = '.*\W'+form+'\W.*'
+			pattern = '^(.*\W)*'+form+'(\W.*)*$'
 			if re.match(pattern, occurence):
 			if re.match(pattern, occurence):
 				verified_occurences.append(occurence)
 				verified_occurences.append(occurence)
 				found = True
 				found = True