Create app.py

app.py

@@ -0,0 +1,59 @@
+import numpy as np
+import pandas as pd
+from flask import Flask, request, jsonify
+import joblib
+
+# Initialize Flask app
+sales_prediction_api = Flask(__name__)
+
+# 👇 REQUIRED for Hugging Face Gunicorn
+application = sales_prediction_api
+
+# Load models
+dt_model = joblib.load("decision_tree_model.pkl")
+xgb_model = joblib.load("xgboost_model.pkl")
+
+# Home route
+@sales_prediction_api.route("/")
+def home():
+    return "✅ SuperKart Sales Prediction API is running"
+
+# Prediction route
+@sales_prediction_api.route("/predict", methods=["POST"])
+def predict():
+    try:
+        data = request.get_json()
+
+        # Model choice
+        model_choice = data.get("model", "dt")
+
+        # Extract features (MATCHES STREAMLIT KEYS)
+        sample = {
+            "Product_Weight": data["Product_Weight"],
+            "Product_Sugar_Content": data["Product_Sugar_Content"],
+            "Product_Allocated_Area": data["Product_Allocated_Area"],
+            "Product_Type": data["Product_Type"],
+            "Product_MRP": data["Product_MRP"],
+            "Store_Size": data["Store_Size"],
+            "Store_Location_City_Type": data["Store_Location_City_Type"],
+            "Store_Type": data["Store_Type"],
+            "Store_Age": data["Store_Age"]
+        }
+
+        sample_df = pd.DataFrame([sample])
+
+        # Select model
+        if model_choice == "dt":
+            prediction = dt_model.predict(sample_df)[0]
+        elif model_choice == "xgb":
+            prediction = xgb_model.predict(sample_df)[0]
+        else:
+            return jsonify({"error": "Invalid model choice"}), 400
+
+        return jsonify({
+            "Prediction": float(prediction),
+            "ModelUsed": model_choice
+        })
+
+    except Exception as e:
+        return jsonify({"error": str(e)}), 500