Update app.py

app.py

@@ -1,14 +1,19 @@
 import pickle
 import streamlit as st
 import os
+import numpy as np
 
-# Show current working directory and files for debugging
-st.write("📂 Current directory:", os.getcwd())
-st.write("📁 Files found:", os.listdir())
+# 💡 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 the pickle files safely
+# 🧠 Debug: Show current directory contents to verify files
+st.write("📂 Files in current directory:", os.listdir())
+
+# 🔃 Load model files
 try:
-    with open("tfidf_vectorizer (1).pkl", "rb") as f:
+    with open("tfidf_vectorizer (1_.pkl", "rb") as f:
         vectorizer = pickle.load(f)
 
     with open("model (1).pkl", "rb") as f:
@@ -17,34 +22,36 @@ try:
     with open("mlb.pkl", "rb") as f:
         mlb = pickle.load(f)
 
-except FileNotFoundError as e:
-    st.error(f"❌ File not found: {e.filename}")
-    st.stop()
 except Exception as e:
     st.error(f"❌ Error loading model files: {str(e)}")
     st.stop()
 
-# Streamlit UI
+# 🧠 Prediction function
+def predict_tags(title, description):
+    try:
+        if not title.strip() or not description.strip():
+            return "⚠️ Please enter both title and 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])
+        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 Stack Overflow question title and description to get predicted tags.")
+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)
+title = st.text_input("📌 Enter Question Title")
+description = st.text_area("📝 Enter Question Description", height=150)
 
 if st.button("Predict Tags"):
-    if not title.strip() or not description.strip():
-        st.warning("⚠️ Please enter both title and description.")
-    else:
-        try:
-            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]:
-                st.success("✅ Predicted Tags: " + ", ".join(predicted_tags[0]))
-            else:
-                st.info("ℹ️ No tags predicted. Try refining your question.")
-
-        except Exception as e:
-            st.error(f"❌ Error during prediction: {str(e)}")
+    result = predict_tags(title, description)
+    st.markdown(result)