Update app.py

app.py

@@ -4,27 +4,30 @@ from tensorflow.keras.preprocessing.text import tokenizer_from_json
 from tensorflow.keras.preprocessing.sequence import pad_sequences
 import json
 import numpy as np
+import lime
 from lime.lime_text import LimeTextExplainer
-from io import BytesIO
 import matplotlib.pyplot as plt
+import base64
+from io import BytesIO
 
-# --- Load resources ---
+# --- Load tokenizer ---
 @st.cache_resource
 def load_tokenizer():
     with open("tokenizer.json", "r") as f:
         data = json.load(f)
     return tokenizer_from_json(json.dumps(data))
 
+# --- Load model ---
 @st.cache_resource
 def load_sentiment_model():
     return load_model("review_amazon_sentiment5.h5")
 
-# --- Predict function for LIME ---
+# --- Predict function ---
 def predict_proba(texts):
     sequences = tokenizer.texts_to_sequences(texts)
     padded = pad_sequences(sequences, maxlen=max_tokens)
     preds = model.predict(padded)
-    return np.hstack([1 - preds, preds])
+    return np.hstack([1 - preds, preds])  # For LIME binary classifier
 
 # --- Visualize explanation ---
 def plot_explanation(exp):
@@ -33,39 +36,32 @@ def plot_explanation(exp):
     fig.savefig(buf, format="png", bbox_inches="tight")
     st.image(buf.getvalue(), use_container_width=True)
 
-# --- Initialization ---
+# --- Initialize ---
 tokenizer = load_tokenizer()
 model = load_sentiment_model()
 max_tokens = 166
 explainer = LimeTextExplainer(class_names=["Positive", "Negative"])
 
 # --- Streamlit UI ---
-st.set_page_config(page_title="Amazon Sentiment Analyzer", page_icon="🔍", layout="centered")
-st.title("🛍️ Amazon Review Sentiment Analyzer")
-st.markdown("Analyze the sentiment of any Amazon product review using a deep learning model. 🔍")
+st.title("Amazon Review Sentiment Analyzer")
+user_input = st.text_area("Enter an Amazon product review:")
 
-# --- User Input ---
-user_input = st.text_area("✏️ Enter an Amazon review", height=150, placeholder="Type or paste your review here...")
-
-# --- Analyze Button ---
-if st.button("🔎 Analyze"):
+if st.button("Analyze"):
     if user_input.strip():
-        # Prediction
+        # Predict
         sequence = tokenizer.texts_to_sequences([user_input])
         padded = pad_sequences(sequence, maxlen=max_tokens)
         pred_prob = model.predict(padded)[0][0]
-
         sentiment = "🟢 Positive" if pred_prob < 0.5 else "🔴 Negative"
-        confidence = 1 - pred_prob if pred_prob < 0.5 else pred_prob
 
-        # Display Result
-        st.markdown(f"### Sentiment: {sentiment}")
-        st.progress(confidence, text=f"Confidence: {confidence:.2%}")
+        # Show Result
+        st.markdown(f"**Sentiment:** {sentiment}")
+        st.markdown(f"**Confidence:** {pred_prob:.2f}")
 
-        # LIME Explanation
-        with st.spinner("🧠 Explaining why the model made this prediction..."):
+        # Explain with LIME
+        with st.spinner("Explaining prediction..."):
             explanation = explainer.explain_instance(user_input, predict_proba, num_features=10)
-            with st.expander("🔬 Why this prediction? (LIME Explanation)", expanded=False):
-                plot_explanation(explanation)
+            st.markdown("### 🔍 Why this prediction?")
+            plot_explanation(explanation)
     else:
-        st.warning("⚠️ Please enter a review to analyze...")
+        st.warning("Please enter some text to analyze.")