Update src/streamlit_app.py

src/streamlit_app.py

@@ -4,15 +4,14 @@ import pickle
 from tensorflow.keras.preprocessing.sequence import pad_sequences
 import numpy as np
 
-# --- 1. CONFIGURATION & SETUP ---
 st.set_page_config(page_title="IMDb Sentiment Analysis", page_icon="🎬")
 
-# Constants (Must match training parameters)
+#Training parameters
 MAX_LEN = 200
 MODEL_PATH = "src/sentiment_lstm_model.h5"
 TOKENIZER_PATH = "src/tokenizer.pickle"
 
-# --- 2. LOAD RESOURCES (Cached for performance) ---
+#Load Resources
 @st.cache_resource
 def load_model():
     model = tf.keras.models.load_model(MODEL_PATH)
@@ -27,16 +26,12 @@ def load_tokenizer():
 try:
     model = load_model()
     tokenizer = load_tokenizer()
-    st.success("System loaded successfully! 🚀")
 except Exception as e:
     st.error(f"Error loading files: {e}")
     st.stop()
 
-# --- 3. PREDICTION FUNCTION ---
+#Predicion
 def predict_sentiment(review_text):
-    # Preprocess the text
-    # Note: Text cleaning is handled implicitly by the tokenizer to some extent,
-    # but for best results, basic lowercase/strip is recommended.
     review_seq = tokenizer.texts_to_sequences([review_text])
     review_pad = pad_sequences(review_seq, maxlen=MAX_LEN)
     
@@ -51,7 +46,6 @@ def predict_sentiment(review_text):
 # --- 4. STREAMLIT UI ---
 st.title("🎬 Movie Review Sentiment Analysis")
 st.markdown("Enter a movie review below to check if it's **Positive** or **Negative**.")
-st.markdown("*(Powered by LSTM & Word2Vec)*")
 
 # Text Input
 user_input = st.text_area("Write your review here (English):", height=150)