Create main.py

main.py

@@ -0,0 +1,47 @@
+from flask import Flask, render_template, request, jsonify
+import joblib
+import re
+
+app = Flask(__name__)
+
+# Load Model & Vectorizer
+lr = joblib.load(open('tag_predictor_lr.pkl','rb'))
+mlb_classes = joblib.load(open('mlb_classes.pkl','rb'))
+tfidf = joblib.load(open('tfidf_vectorizer.pkl','rb'))
+
+def preprocess_text(text):
+    text = text.lower()
+    text = re.sub(r'[^a-zA-Z\s]', '', text)
+    text = re.sub(r'\s+', ' ', text).strip()
+    return text
+
+def predict_tags(text, model=lr, threshold=0.1):
+    clean_text = preprocess_text(text)
+    text_tfidf = tfidf.transform([clean_text])
+
+    if hasattr(model, 'predict_proba'):
+        probas = model.predict_proba(text_tfidf)
+        tags = []
+        p = []
+        for i, class_name in enumerate(mlb_classes):
+            if probas[i][0][1] > threshold:
+                tags.append(class_name)
+                p.append(probas[i][0][1])
+        return tags, p
+    else:
+        preds = model.predict(text_tfidf)
+        tags = [mlb_classes[i] for i, val in enumerate(preds[0]) if val == 1]
+        return tags, preds[0]
+
+@app.route('/')
+def index():
+    return render_template('index.html')
+
+@app.route('/predict', methods=['POST'])
+def predict():
+    query = request.form.get("query")
+    tags, probabilities = predict_tags(query)
+    return jsonify({"tags": tags, "probabilities": probabilities})
+
+if __name__ == '__main__':
+    app.run(debug=True)