Update app.py

app.py

@@ -13,8 +13,6 @@ nltk.download('punkt')
 
 import streamlit as st 
 
-import functions
-
 
 # Preprocess function
 from nltk.corpus import stopwords
@@ -72,10 +70,46 @@ model_NB = joblib.load(model_NB_path)
 model_LR_path = './model_LR.sav'
 model_LR = joblib.load(model_LR_path)
 
+def sentiment_analysis_LR(input):
+    # Assuming you have a Logistic Regression model and TfidfVectorizer in the pipeline
+    input = preprocess_text(input)
+
+    vectorizer = model_LR.named_steps['tfidfvectorizer']
+    lr_classifier = model_LR.named_steps['logisticregression']
+
+    # Transform the user input using the TF-IDF vectorizer
+    user_input_tfidf = vectorizer.transform([input])
+
+    # Make predictions
+    user_pred = lr_classifier.predict(user_input_tfidf)
+
+    # Display the prediction
+    if user_pred[0] == 0:
+        return 0
+    else:
+        return 1
+
+def sentiment_analysis_NB(input):
+  input = preprocess_text(input)
+
+  vectorizer = model_NB.named_steps['tfidf']
+  nb_classifier = model_NB.named_steps['nb']
+
+  # Transform the user input using the TF-IDF vectorizer
+  user_input_tfidf = vectorizer.transform([input])
+
+  # Make predictions
+  user_pred = nb_classifier.predict(user_input_tfidf)
+
+  # Display the prediction
+  if user_pred[0] == 0:
+      return 0
+  else:
+      return 1 
 
 text = st.text_area('Enter some text !!! (English text : D )')
 if text:
-    out = functions.sentiment_analysis_LR(text)
+    out = sentiment_analysis_LR(text)
     if out == 0:
         out = 'negative'
         st.json(out)