Update app.py

app.py

@@ -18,12 +18,6 @@ from nltk.stem import WordNetLemmatizer
 nltk.download('punkt')
 nltk.download('stopwords')
 nltk.download('wordnet')
-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)
 
 
 
@@ -31,14 +25,23 @@ def preprocess_nltk(text):
 
 
 
-with open("sentiment_analysis_model.pkl", "rb") as file:
-    pipe2 = pickle.load(file)
+
+
 def prediction(text):
-  text_processed=(preprocess_nltk(text))
-  ans=pipe2.predict([text_processed])
-  classes = ['Irrelevant', 'Natural', 'Negative', 'Positive']
-  predicted_label = ans[0]
-  return(f"The above text is:{classes[predicted_label]}" )
+    
+    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']
+      predicted_label = ans[0]
+      return(f"The above text is:{classes[predicted_label]}" )
 
 pre = gr.Interface(
     fn=prediction,