Update app.py

app.py

@@ -1,56 +1,67 @@
 import pickle
 import streamlit as st
-import os
-import numpy as np
 
-# 💡 Define the custom tokenizer exactly as used during training
-def custom_tokenizer(text):
-    # Modify this function to match your original tokenizer logic
-    return text.lower().split()
-
-
-
-# 🔃 Load model files
-try:
-    with open("vectorizer.pkl", "rb") as f:
-        vectorizer = pickle.load(f)
-
-    with open("model (2).pkl", "rb") as f:
-        model = pickle.load(f)
+# --- Load Model Components ---
+@st.cache_resource
+def load_components():
+    try:
+        with open("vectorizer.pkl", "rb") as f:
+            vectorizer = pickle.load(f)
+        with open("model (2).pkl", "rb") as f:
+            model = pickle.load(f)
+        with open("binarizer.pkl", "rb") as f:
+            mlb = pickle.load(f)
+        return vectorizer, model, mlb
+    except Exception as e:
+        st.error(f"🚨 Failed to load model files: {e}")
+        st.stop()
 
-    with open("binarizer.pkl", "rb") as f:
-        mlb = pickle.load(f)
+vectorizer, model, mlb = load_components()
 
-except Exception as e:
-    st.error(f"❌ Error loading model files: {str(e)}")
-    st.stop()
+# --- Custom Tokenizer (if used in training) ---
+def custom_tokenizer(text):
+    return text.lower().split()
 
-# 🧠 Prediction function
+# --- Tag Prediction ---
 def predict_tags(title, description):
-    try:
-        if not title.strip() or not description.strip():
-            return "⚠️ Please enter both title and description."
+    if not title.strip() or not description.strip():
+        return "⚠️ Please enter both title and description."
 
-        input_text = title + " " + description
+    try:
+        input_text = title.strip() + " " + description.strip()
         input_vector = vectorizer.transform([input_text])
         prediction = model.predict(input_vector)
         predicted_tags = mlb.inverse_transform(prediction)
 
         if predicted_tags and predicted_tags[0]:
-            return "✅ Predicted Tags: " + ", ".join(predicted_tags[0])
+            tag_list = ", ".join(predicted_tags[0])
+            return f"🎯 **Predicted Tags:** `{tag_list}`"
         else:
             return "ℹ️ No tags predicted. Try refining your question."
 
     except Exception as e:
         return f"❌ Error during prediction: {str(e)}"
 
-# 🚀 Streamlit UI
-st.title("🔖 Stack Overflow Tags Predictor")
-st.markdown("Enter a question title and description to predict relevant tags.")
+# --- Streamlit UI ---
+st.set_page_config(page_title="Stack Overflow Tag Predictor", page_icon="🔖")
+
+st.markdown(
+    """
+    <style>
+    .title { font-size: 36px; font-weight: 700; color: #4A90E2; }
+    .desc { font-size: 18px; margin-bottom: 20px; }
+    .result-box { background-color: #f9f9f9; padding: 15px; border-radius: 8px; margin-top: 20px; }
+    </style>
+    """,
+    unsafe_allow_html=True
+)
+
+st.markdown('<div class="title">🔖 Stack Overflow Tag Predictor</div>', unsafe_allow_html=True)
+st.markdown('<div class="desc">Enter a Stack Overflow question title and description to get the most relevant tags.</div>', unsafe_allow_html=True)
 
-title = st.text_input("📌 Enter Question Title")
-description = st.text_area("📝 Enter Question Description", height=150)
+title = st.text_input("📌 Question Title")
+description = st.text_area("📝 Question Description", height=150)
 
-if st.button("Predict Tags"):
+if st.button("🚀 Predict Tags"):
     result = predict_tags(title, description)
-    st.markdown(result)
+    st.markdown(f'<div class="result-box">{result}</div>', unsafe_allow_html=True)