Update app.py

app.py

@@ -8,6 +8,7 @@ import nltk
 from nltk.tokenize import word_tokenize
 from nltk.stem import WordNetLemmatizer
 from nltk.corpus import stopwords  
+from tensorflow.keras.preprocessing.sequence import pad_sequences
 
 # Ensure necessary downloads
 nltk.download("punkt")
@@ -33,29 +34,22 @@ def pre_process(text):
     return " ".join(words)
 
 @st.cache_resource
-def load_label_encoder():
-    with open("label_encoder.pkl", "rb") as f:
-        return pickle.load(f)
+def load_model():
+    model = tf.keras.models.load_model("model_m3_new.keras")
+    vectorizer = tf.keras.models.load_model("vec_text_m3_new.keras")
+    with open("label_encoder_m5.pkl", 'rb') as file:
+        label_encoder = pickle.load(file)
+    return model, vectorizer, label_encoder
 
-@st.cache_resource
-def load_text_vectorizer():
-    return tf.keras.models.load_model("news_tv_model.keras")
-
-@st.cache_resource
-def load_news_model():
-    return tf.keras.models.load_model("news_model.keras")
-
-# Load resources
-label_encoder = load_label_encoder()
-text_vectorizer = load_text_vectorizer()
-news_model = load_news_model()
+# Load models
+model, vectorizer, label_encoder = load_model()
 
 def predict_category(text):
     processed_text = [pre_process(text)]
-    vectorized_text = text_vectorizer(processed_text)
-    prediction = news_model.predict(vectorized_text)
-    predicted_label_index = np.argmax(prediction, axis=1)[0]
-    return label_encoder.inverse_transform([predicted_label_index])[0]
+    text_vectorized = pad_sequences(vectorizer(processed_text).numpy().tolist(), padding='pre', maxlen=128)
+    prediction = model.predict(text_vectorized)
+    category_idx = np.argmax(prediction, axis=1)[0]
+    return label_encoder.inverse_transform([category_idx])[0]
 
 # Streamlit UI
 st.title("News Classification App")