Update app.py

app.py

@@ -12,8 +12,9 @@ with open("preprocessing.pkl", "rb") as f:
     clean_text = pickle.load(f)
 
 # Load TF-IDF Vectorizer
-with open("tfidf_vectorizer.pkl", "rb") as f:
-    vectorizer = pickle.load(f)import streamlit as st
+with open("text_vectorizer.pkl", "rb") as f:
+    vectorizer = pickle.load(f)
+import streamlit as st
 import tensorflow as tf
 import pickle
 import numpy as np
@@ -31,10 +32,10 @@ with open("vectorizer.pkl", "rb") as f:
     vectorizer = pickle.load(f)
 
 # Define News Categories
-news_categories = ["World", "Sports", "Business", "Sci/Tech"]
+news_categories = ["Business", "Sci/Tech","Sports","World"]
 
 # Streamlit UI
-st.title("📰 News Classification with Simple RNN + TF-IDF")
+st.title("📰 News Classification with Simple RNN")
 st.write("Enter a news headline to predict its category.")
 
 user_input = st.text_area("Enter News Text:", "")
@@ -44,39 +45,16 @@ if st.button("Classify"):
         # Preprocess Input
         processed_text = clean_text(user_input)
 
-        # Convert text to vector
-        text_vector = vectorizer.transform([processed_text]).toarray()
-
-        # Prediction
-        prediction = model.predict(text_vector)
-        category = np.argmax(prediction)
-
-        st.success(f"Predicted Category: {news_categories[category]}")
-    else:
-        st.warning("Please enter a news headline.")
-
-
-# Define News Categories
-news_categories = ["World", "Sports", "Business", "Sci/Tech"]
-
-# Streamlit UI
-st.title("📰 News Classification with Simple RNN + TF-IDF")
-st.write("Enter a news headline to predict its category.")
-
-user_input = st.text_area("Enter News Text:", "")
-
-if st.button("Classify"):
-    if user_input:
-        # Preprocess Input
-        processed_text = clean_text(user_input)
+        # Convert text to integer sequence
+        text_sequence = tokenizer.texts_to_sequences([processed_text])
 
-        # Convert text to vector
-        text_vector = vectorizer.transform([processed_text]).toarray()
+        # Pad the sequence to match model input size
+        text_padded = tf.keras.preprocessing.sequence.pad_sequences(text_sequence, maxlen=100)
 
         # Prediction
-        prediction = model.predict(text_vector)
+        prediction = model.predict(text_padded)
         category = np.argmax(prediction)
 
         st.success(f"Predicted Category: {news_categories[category]}")
     else:
-        st.warning("Please enter a news headline.")
+        st.warning("Please enter a news headline.")