Upload app.py with huggingface_hub

app.py

@@ -1,80 +1,39 @@
-import os
-import requests
-import streamlit as st
-import pandas as pd
 
-st.set_page_config(page_title="SuperKart Sales Forecast", layout="centered")
-st.title("🛒 SuperKart Sales Forecast")
+from flask import Flask, request, jsonify
+import joblib
+import pandas as pd
 
-# Read backend URL from secret or sidebar input
-DEFAULT_BACKEND = os.getenv("BACKEND_URL", "").strip()
-backend_url = st.sidebar.text_input(
-    "Backend /predict URL",
-    value=DEFAULT_BACKEND,
-    help="From BACKEND_URL secret; you can override here."
-)
-st.sidebar.caption("Example: https://rizwan9--backend.hf.space/predict")
+app = Flask(__name__)
 
-# Health check button
-if st.sidebar.button("🔗 Check Backend Connection"):
-    if not backend_url:
-        st.sidebar.error("Please enter backend URL first.")
-    else:
-        try:
-            health_url = backend_url.replace("/predict", "/")
-            r = requests.get(health_url, timeout=10)
-            if r.status_code == 200:
-                st.sidebar.success("✅ Backend is reachable!")
-            else:
-                st.sidebar.warning(f"⚠️ Backend responded with {r.status_code}")
-        except Exception as e:
-            st.sidebar.error(f"❌ Could not connect: {e}")
+# Load the serialized model
+model = joblib.load('best_sales_forecasting_model.pkl')
 
-st.markdown("Enter product & store details, then click **Predict**.")
+@app.route('/')
+def home():
+    return "Sales Forecasting Backend is running!"
 
-col1, col2 = st.columns(2)
-with col1:
-    Product_Weight = st.number_input("Product_Weight", min_value=0.0, value=12.65)
-    Product_Allocated_Area = st.number_input("Product_Allocated_Area", min_value=0.0, value=0.07)
-    Product_MRP = st.number_input("Product_MRP", min_value=0.0, value=147.0)
-    Store_Establishment_Year = st.number_input("Store_Establishment_Year", min_value=1900, max_value=2100, value=2005)
-with col2:
-    Product_Sugar_Content = st.selectbox("Product_Sugar_Content", ["Low Sugar", "Regular", "No Sugar"])
-    Product_Type = st.text_input("Product_Type", "Dairy")
-    Store_Size = st.selectbox("Store_Size", ["High", "Medium", "Low"])
-    Store_Location_City_Type = st.selectbox("Store_Location_City_Type", ["Tier 1", "Tier 2", "Tier 3"])
-    Store_Type = st.selectbox("Store_Type", ["Departmental Store", "Supermarket Type 1", "Supermarket Type 2", "Food Mart"])
+@app.route('/predict', methods=['POST'])
+def predict():
+    try:
+        data = request.get_json(force=True)
+        # Convert the incoming data to a pandas DataFrame
+        # Assuming the incoming data is a list of dictionaries, where each dictionary is a data point
+        input_data = pd.DataFrame(data)
 
-payload = {
-    "Product_Weight": Product_Weight,
-    "Product_Sugar_Content": Product_Sugar_Content,
-    "Product_Allocated_Area": Product_Allocated_Area,
-    "Product_Type": Product_Type,
-    "Product_MRP": Product_MRP,
-    "Store_Establishment_Year": int(Store_Establishment_Year),
-    "Store_Size": Store_Size,
-    "Store_Location_City_Type": Store_Location_City_Type,
-    "Store_Type": Store_Type
-}
+        # Ensure the columns are in the same order as the training data
+        # This assumes you have access to the columns from your training data (X_train)
+        # You might need to adjust this part based on how you handle feature ordering
+        # For demonstration, let's assume the input data has the same columns in the same order
+        # In a real application, you might need to reorder columns or handle missing ones
 
-st.markdown("#### Request Payload (Preview)")
-st.code(pd.DataFrame([payload]).to_json(orient="records", indent=2))
+        # Make predictions
+        predictions = model.predict(input_data)
 
-if st.button("🔮 Predict"):
-    if not backend_url:
-        st.error("Please set backend URL in sidebar.")
-    else:
-        try:
-            resp = requests.post(backend_url, json=[payload], timeout=20)
-            if resp.ok:
-                data = resp.json()
-                preds = data.get("predictions") or data.get("prediction")
-                if isinstance(preds, list):
-                    st.success(f"**Predicted Sales:** {preds[0]:,.2f}")
-                else:
-                    st.success(f"**Prediction:** {preds}")
-            else:
-                st.error(f"Backend error {resp.status_code}: {resp.text}")
-        except Exception as e:
-            st.error(f"Request failed: {e}")
+        # Return predictions as a JSON response
+        return jsonify(predictions.tolist())
+    except Exception as e:
+        return jsonify({'error': str(e)})
 
+if __name__ == '__main__':
+    # Running on 0.0.0.0 makes it accessible externally, useful for deployment
+    app.run(host='0.0.0.0', port=5000)