Upload app (1).py

app (1).py

@@ -0,0 +1,159 @@
+import streamlit as st
+import joblib
+import pandas as pd
+import re
+from unidecode import unidecode
+import emoji
+import string
+import contractions
+from nltk.stem import PorterStemmer
+import numpy as np
+from sklearn.feature_extraction.text import ENGLISH_STOP_WORDS
+
+# Custom CSS Styling
+st.markdown("""
+<style>
+    .stApp {
+        background-color: #f9fbfc;
+        font-family: 'Segoe UI', sans-serif;
+    }
+    .custom-header {
+        background-color: #1e293b;
+        color: white;
+        padding: 2rem;
+        border-radius: 0.5rem;
+        text-align: center;
+        margin-bottom: 2rem;
+    }
+    .custom-header h1 {
+        font-size: 2rem;
+        margin-bottom: 0.5rem;
+    }
+    .custom-header p {
+        font-size: 1rem;
+        color: #cbd5e1;
+    }
+    .input-box, .output-box {
+        background-color: white;
+        padding: 1.5rem;
+        border-radius: 0.5rem;
+        box-shadow: 0 0 10px rgba(0, 0, 0, 0.04);
+        margin-bottom: 2rem;
+    }
+    .tag-pill {
+        display: inline-block;
+        background-color: #e0f2fe;
+        color: #0369a1;
+        padding: 0.4em 0.8em;
+        margin: 0.25em;
+        border-radius: 999px;
+        font-weight: 600;
+        font-size: 0.9rem;
+    }
+    .footer {
+        text-align: center;
+        font-size: 0.85rem;
+        color: #64748b;
+        margin-top: 2rem;
+    }
+</style>
+""", unsafe_allow_html=True)
+
+# Header
+st.markdown("""
+<div class="custom-header">
+    <h1>📌 StackOverflow Tag Predictor</h1>
+    <p>Enter a programming question to see predicted tags</p>
+</div>
+""", unsafe_allow_html=True)
+
+# Initialize components
+stemmer = PorterStemmer()
+stop_words = set(ENGLISH_STOP_WORDS)
+chat_words = {
+    "brb": "be right back", "btw": "by the way", "lol": "laugh out loud",
+    "afaik": "as far as i know", "imo": "in my opinion", "tbh": "to be honest",
+    "idk": "i don't know", "asap": "as soon as possible", "np": "no problem",
+    "thx": "thanks", "pls": "please", "fyi": "for your information"
+}
+
+def preprocess_text(text):
+    if not isinstance(text, str) or not text.strip():
+        return ""
+    try:
+        text = re.sub(r'<[^>]+>', '', text)
+        text = re.sub(r'https?://\S+|www\.\S+', '', text)
+        text = emoji.demojize(text, delimiters=(" ", " "))
+        text = unidecode(text)
+        text = contractions.fix(text)
+        text = text.lower()
+        words = text.split()
+        text = " ".join([chat_words.get(word.lower(), word) for word in words])
+        text = text.translate(str.maketrans('', '', string.punctuation))
+        tokens = re.findall(r'\b\w+\b', text)
+        tokens = [word for word in tokens if word not in stop_words]
+        tokens = [stemmer.stem(word) for word in tokens]
+        return " ".join(tokens)
+    except Exception as e:
+        st.error(f"Preprocessing error: {e}")
+        return ""
+
+@st.cache_resource
+def load_models():
+    try:
+        model = joblib.load("tag_model.joblib")
+        mlb = joblib.load("tag_binarizer.joblib")
+        return model, mlb
+    except Exception as e:
+        st.error(f"Error loading model: {e}")
+        return None, None
+
+model, mlb = load_models()
+
+# Input
+st.markdown('<div class="input-box">', unsafe_allow_html=True)
+user_input = st.text_area("✍️ Paste your programming question below:", height=200, placeholder="e.g., How to reverse a list in Python?")
+st.markdown('</div>', unsafe_allow_html=True)
+
+# Prediction
+if st.button("🚀 Predict Tags"):
+    if not user_input.strip():
+        st.warning("Please enter your question to get predictions.")
+    elif model is None or mlb is None:
+        st.error("Model loading failed.")
+    else:
+        with st.spinner("Processing..."):
+            processed = preprocess_text(user_input)
+            if processed:
+                try:
+                    input_df = pd.DataFrame({'processed_excerpt': [processed]})
+                    if hasattr(model, "predict_proba"):
+                        probs = model.predict_proba(input_df)[0]
+                        top_idx = np.argsort(probs)[-5:][::-1]
+                        tags = [mlb.classes_[i] for i in top_idx]
+                        confs = [int(probs[i] * 100) for i in top_idx]
+                    elif hasattr(model, "decision_function"):
+                        scores = model.decision_function(input_df)[0]
+                        top_idx = np.argsort(scores)[-5:][::-1]
+                        tags = [mlb.classes_[i] for i in top_idx]
+                        confs = [None] * 5
+                    else:
+                        preds = model.predict(input_df)
+                        tags = mlb.inverse_transform(preds)[0]
+                        confs = [None] * len(tags)
+
+                    # Output
+                    st.markdown('<div class="output-box"><h4>🏷️ Predicted Tags:</h4>', unsafe_allow_html=True)
+                    for tag, conf in zip(tags, confs):
+                        confidence = f" ({conf}%)" if conf is not None else ""
+                        st.markdown(f'<span class="tag-pill">{tag}{confidence}</span>', unsafe_allow_html=True)
+                    st.markdown('</div>', unsafe_allow_html=True)
+                except Exception as e:
+                    st.error(f"Prediction error: {e}")
+
+# Footer
+st.markdown("""
+<div class="footer">
+    🔎 This ML tool predicts tags based on programming question content.
+</div>
+""", unsafe_allow_html=True)