Update app.py

app.py

@@ -1,21 +1,20 @@
 import streamlit as st
 import tensorflow as tf
 import numpy as np
+import dill
 
-# Load the trained model
-model = tf.keras.models.load_model("news_classification_rnn1.h5")
+# Load the trained model with custom layers
+from tensorflow.keras.layers import TextVectorization
+model = tf.keras.models.load_model("news_classification_rnn1.h5", 
+                                   custom_objects={"TextVectorization": TextVectorization})
 
 # Load Preprocessing Function
-import dill
 with open("preprocessing1.pkl", "rb") as f:
     clean_text = dill.load(f)
 
-# Load Text Vectorization Layer from SavedModel
-import pickle
-
+# Load Text Vectorization Layer
 with open("vector.pkl", "rb") as f:
-    vectorizer = pickle.load(f)
-
+    vectorizer = dill.load(f)
 
 # Define News Categories
 news_categories = ["Business", "Sci/Tech", "Sports", "World"]
@@ -31,11 +30,8 @@ if st.button("Classify"):
         # Preprocess input
         processed_text = clean_text(user_input)
 
-        # Convert text to integer sequence
-        text_sequence = vectorizer([processed_text])
-
-        # Convert to numpy array (model expects batch input)
-        
+        # Vectorize input and convert to numpy array
+        text_sequence = np.array(vectorizer([processed_text]))
 
         # Predict Category
         prediction = model.predict(text_sequence)