Update app.py

app.py

@@ -1,56 +1,49 @@
-import pickle
 import streamlit as st
-import os
-import numpy as np
+import joblib
 
-# 💡 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()
+# ✅ MUST be first Streamlit command
+st.set_page_config(page_title="Stack Overflow Tag Predictor", layout="centered")
 
+# ✅ Define your custom tokenizer BEFORE loading the vectorizer
+def customs_tokenization(text):
+    return text.split()
 
+# --- Load model and vectorizers ---
+@st.cache_resource
+def load_pickle(path):
+    return joblib.load(path)
 
-# 🔃 Load model files
-try:
-    with open("tfidf_vectorizer (2).pkl", "rb") as f:
-        vectorizer = pickle.load(f)
+model = load_pickle("compressed_logistic_reg1 (1).pkl")
+vectorizer = load_pickle("tfidf_vectorizer (2).pkl")
+mlb = load_pickle("multilabel_binarizer (1).pkl")
 
-    with open("compressed_logistic_reg1 (1).pkl", "rb") as f:
-        model = pickle.load(f)
+# --- Prediction Function ---
+def predict_tags(title, description):
+    title, description = title.strip(), description.strip()
 
-    with open("multilabel_binarizer (1).pkl", "rb") as f:
-        mlb = pickle.load(f)
+    if not title or not description:
+        return "⚠️ Please enter both title and description."
 
-except Exception as e:
-    st.error(f"❌ Error loading model files: {str(e)}")
-    st.stop()
+    full_text = title + " " + description
+    vectorized = vectorizer.transform([full_text])
+    prediction = model.predict(vectorized)
+    tags = mlb.inverse_transform(prediction)
 
-# 🧠 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)
-        st.write(predicted_tags)
-        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 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 tags and tags[0]:
+        return "✅ Predicted Tags: " + ", ".join(tags[0])
+    else:
+        return "ℹ️ No tags predicted. Try refining your question."
+
+
+# --- Streamlit UI ---
+st.title("🔖 Stack Overflow Tag Predictor")
+st.markdown("Enter a question title and description to receive relevant tag suggestions.")
+
+# Input fields
+title_input = st.text_input("Question Title", placeholder="e.g. How to merge dictionaries in Python?")
+desc_input = st.text_area("Question Description", placeholder="e.g. I have two dictionaries and I want to merge them...")
 
+# Predict button
 if st.button("Predict Tags"):
-    result = predict_tags(title, description)
-    st.markdown(result)
+    result = predict_tags(title_input, desc_input)
+    st.markdown(f"### Result:\n{result}")