Update app.py

app.py

@@ -1,40 +1,40 @@
-import streamlit as st
-import pickle
-import numpy as np
-
-
-with open("Model/vectorizer_text.pkl", "rb") as f:
-    vectorizer_text = pickle.load(f)
-
-with open("Model/vectorizer_title.pkl", "rb") as f:
-    vectorizer_title = pickle.load(f)
-
-with open("Model/logistic_regression_model.pkl", "rb") as f:
-    logistic_regression_model = pickle.load(f)
-
-
-# Streamlit app header
-st.header("Fake News Prediction")
-st.subheader("Created by Snehangshu Bhuin")
-
-# Input fields for user
-title = st.text_input("News Title")
-text = st.text_area("Description")
-
-# Prediction button
-if st.button("Predict"):
-    # Transform the input text
-    title_transformed = vectorizer_title.transform([title])
-    text_transformed = vectorizer_text.transform([text])
-    
-
-    input_features = np.hstack((title_transformed.toarray(), text_transformed.toarray()))
-    
-    # Make prediction
-    prediction = logistic_regression_model.predict(input_features)
-    print(prediction)
-    # Display the prediction result
-    if prediction == 1:
-        st.success("The news is likely Real")
-    else:
+import streamlit as st
+import pickle
+import numpy as np
+
+
+with open("vectorizer_text.pkl", "rb") as f:
+    vectorizer_text = pickle.load(f)
+
+with open("vectorizer_title.pkl", "rb") as f:
+    vectorizer_title = pickle.load(f)
+
+with open("logistic_regression_model.pkl", "rb") as f:
+    logistic_regression_model = pickle.load(f)
+
+
+# Streamlit app header
+st.header("Fake News Prediction")
+st.subheader("Created by Snehangshu Bhuin")
+
+# Input fields for user
+title = st.text_input("News Title")
+text = st.text_area("Description")
+
+# Prediction button
+if st.button("Predict"):
+    # Transform the input text
+    title_transformed = vectorizer_title.transform([title])
+    text_transformed = vectorizer_text.transform([text])
+    
+
+    input_features = np.hstack((title_transformed.toarray(), text_transformed.toarray()))
+    
+    # Make prediction
+    prediction = logistic_regression_model.predict(input_features)
+    print(prediction)
+    # Display the prediction result
+    if prediction == 1:
+        st.success("The news is likely Real")
+    else:
         st.error("The news is likely Fake")