Update app.py

app.py

@@ -1,8 +1,15 @@
-import streamlit as st
 import pickle
+import streamlit as st
+import os
+import numpy as np
 
-# ✅ Set Streamlit page config (must be first command)
-st.set_page_config(page_title="🔖 Stack Overflow Multi-Tag Predictor", page_icon="🧠")
+# 💡 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()
+
+# 🧠 Debug: Show current directory contents to verify files
+st.write("📂 Files in current directory:", os.listdir())
 
 # 🔃 Load model files
 try:
@@ -12,7 +19,7 @@ try:
     with open("model (3).pkl", "rb") as f:
         model = pickle.load(f)
 
-    with open("mlb (1).pkl", "rb") as f:
+    with open("mlb (2).pkl", "rb") as f:
         mlb = pickle.load(f)
 
 except Exception as e:
@@ -28,11 +35,10 @@ def predict_tags(title, description):
         input_text = title + " " + description
         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])
+            return "✅ Predicted Tags: " + ", ".join(predicted_tags[0])
         else:
             return "ℹ️ No tags predicted. Try refining your question."
 
@@ -40,12 +46,12 @@ def predict_tags(title, description):
         return f"❌ Error during prediction: {str(e)}"
 
 # 🚀 Streamlit UI
-st.title("💬 Stack Overflow Multi-Tag Predictor")
-st.markdown("Enter a question title and description to get multiple relevant tags.")
+st.title("🔖 Stack Overflow Tags Predictor")
+st.markdown("Enter a question title and description to predict relevant tags.")
 
 title = st.text_input("📌 Enter Question Title")
 description = st.text_area("📝 Enter Question Description", height=150)
 
-if st.button("🎯 Predict Tags"):
+if st.button("Predict Tags"):
     result = predict_tags(title, description)
-    st.markdown(result)
+    st.markdown(result)