Upload folder using huggingface_hub

Dockerfile

@@ -10,6 +10,13 @@ COPY . .
 RUN pip install --upgrade pip
 RUN pip install --no-cache-dir -r requirements.txt
 
+# Verify model file exists
+RUN if [ ! -f "superkart_sales_forecast_model_v1_1.joblib" ]; then \
+        echo "❌ Model file not found!" && exit 1; \
+    else \
+        echo "✅ Model file exists, proceeding"; \
+    fi
+
 # expose port (Spaces listens on 7860)
 ENV PORT=7860
 EXPOSE 7860

app.py

@@ -1,54 +1,4 @@
 
-# backend_files/app.py
-import numpy as np
-import pandas as pd
-import joblib
-from flask import Flask, request, jsonify
-
-# initiate flask application
-app = Flask("SuperKart Sales Price Prediction API")
-
-# Load the trained model (ensure file exists in the correct path)
-model = joblib.load("superkart_prediction.joblib")
-
-# HOME ROUTE
-@app.route("/", methods=["GET"])
-def home():
-    return "Welcome to the SuperKart Sales Prediction API!"
-
-# SINGLE SALES PREDICTION
-@app.route("/v1/sales", methods=["POST"])
-def predict_sales_single():
-    try:
-        sales_data = request.get_json(force=True)
-        sample = {
-            'Product_Id': sales_data.get('Product_Id'),
-            'Product_Weight': sales_data.get('Product_Weight'),
-            'Product_Sugar_Content': sales_data.get('Product_Sugar_Content'),
-            'Product_Allocated_Area': sales_data.get('Product_Allocated_Area'),
-            'Product_Type': sales_data.get('Product_Type'),
-            'Product_MRP': sales_data.get('Product_MRP'),
-            'Store_Id': sales_data.get('Store_Id'),
-            'Store_Establishment_Year': sales_data.get('Store_Establishment_Year'),
-            'Store_Size': sales_data.get('Store_Size'),
-            'Store_Location_City_Type': sales_data.get('Store_Location_City_Type'),
-            'Store_Type': sales_data.get('Store_Type')
-        }
-        input_df = pd.DataFrame([sample])
-        log_pred = model.predict(input_df)[0]
-        predicted_sale = round(float(np.exp(log_pred)), 2)
-        return jsonify({"predicted_sales_in_dollars": predicted_sale}), 200
-    except Exception as e:
-        return jsonify({"error": str(e)}), 400
-
-
-
-# Main runner for local testing (not used by Gunicorn)
-if __name__ == "__main__":
-    app.run(host="0.0.0.0", port=7860, debug=True)
-
-
-
 
 import numpy as np
 import joblib
@@ -120,7 +70,7 @@ def predict_sales():
     except Exception as e:
         print("❌ Error during prediction:", str(e))
         return jsonify({'error': f"Prediction failed: {str(e)}"}), 500
-        
+
 # BATCH SALES PREDICTION
 @app.route("/v1/sales_batch", methods=["POST"])
 def predict_sales_batch():