Update app.py

app.py

@@ -1,23 +1,21 @@
 import streamlit as st
 import tensorflow as tf
-import pickle
+import dill  # Use dill instead of pickle for preprocessing function
 import numpy as np
-import pandas as pd
 
-
-# Load Model
+# Load Trained Model
 model = tf.keras.models.load_model("news_classification_rnn.h5")
 
 # Load Preprocessing Function
 with open("preprocessing1.pkl", "rb") as f:
-    clean_text = pickle.load(f)
+    clean_text = dill.load(f)
 
-# Load TF-IDF Vectorizer
-with open("text_vectorizer(1)).pkl", "rb") as f:
-    vectorizer = pickle.load(f)
+# Load Text Vectorization Layer
+with open("text_vectorizer.pkl", "rb") as f:
+    vectorizer = dill.load(f)
 
 # Define News Categories
-news_categories = ["Business", "Sci/Tech","Sports","World"]
+news_categories = ["Business", "Sci/Tech", "Sports", "World"]
 
 # Streamlit UI
 st.title("📰 News Classification with Simple RNN")
@@ -26,20 +24,20 @@ 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)
+    if user_input.strip():
+        # Preprocess Input
+        processed_text = clean_text(user_input)
 
-        # Convert text to integer sequence
-        text_sequence = tokenizer.texts_to_sequences([processed_text])
+        # Vectorize Input (Convert text to integer sequence)
+        text_sequence = vectorizer([processed_text])  # Directly vectorizes text
 
-        # Pad the sequence to match model input size
-        text_padded = tf.keras.preprocessing.sequence.pad_sequences(text_sequence, maxlen=100)
+        # Ensure correct shape (model expects batch input)
+        text_sequence = np.array(text_sequence)
 
-        # Prediction
-        prediction = model.predict(text_padded)
+        # Make Prediction
+        prediction = model.predict(text_sequence)
         category = np.argmax(prediction)
 
-        st.success(f"Predicted Category: {news_categories[category]}")
+        st.success(f"Predicted Category: **{news_categories[category]}**")
     else:
-        st.warning("Please enter a news headline.")
+        st.warning("⚠ Please enter a news headline.")