Update app.py

app.py

@@ -22,25 +22,20 @@ nltk.download('wordnet')
 
 
 
+with open("sentiment_analysis_model.pkl", "rb") as file:
+    pipe2 = pickle.load(file)
 
+def preprocess_nltk(text):
+    lemmatizer = WordNetLemmatizer()
+    tokens = word_tokenize(text.lower())  # Tokenization
+    stop_words = set(stopwords.words("english"))
+    filtered_tokens = [lemmatizer.lemmatize(token) for token in tokens if token.isalnum() and token not in stop_words]
+    return " ".join(filtered_tokens)
 
 
 
 
 def prediction(text):
-    
-    
-    def preprocess_nltk(text):
-        
-        
-        lemmatizer = WordNetLemmatizer()
-        tokens = word_tokenize(text.lower())  # Tokenization
-        stop_words = set(stopwords.words("english"))
-        filtered_tokens = [lemmatizer.lemmatize(token) for token in tokens if token.isalnum() and token not in stop_words]
-        return " ".join(filtered_tokens)
-    
-    with open("sentiment_analysis_model.pkl", "rb") as file:
-        pipe2 = pickle.load(file)
     text_processed=(preprocess_nltk(text))
     ans=pipe2.predict([text_processed])
     classes = ['Irrelevant', 'Natural', 'Negative', 'Positive']