Update pipeline.py

pipeline.py

@@ -23,6 +23,7 @@ import nltk
 nltk.download('punkt')
 nltk.download('stopwords')
 nltk.download('wordnet')
+nltk.download('omw-1.4')
 import html
 
 from config import config_file
@@ -297,21 +298,15 @@ class Branch_Classifier(object):
 	def format_data(self,data:list)-> list:
 		try:
 			X = text_cleaning.text_cleaning(data, steam=False, lemma=True,single_input=True)[0]
-			print("\n1: ",X)
 			### Add Bigrams and keep only the good ones(pre-selected)
 			X_bigrmas  = self.phrase_bigrams[X] 
-			print("\n2: ",X_bigrmas)
 			
 			data_clean = self.clean_bigram(X_bigrmas)
-			print("\n3: ",data_clean)
 			X_bigrams_clean = ' '.join(map(str, data_clean)) 
-			print("\n4: ",X_bigrams_clean)
 			pre_processed = self.vectorizer.transform([X_bigrams_clean]).toarray(),X_bigrams_clean
-			print("\n5: ",pre_processed)
 
 		except Exception as e:
 			logging.exception("Error occurred while formatting and cleaning data" +" Info: " + str(e))
-			raise e
 			exit()
 
 		return pre_processed