Upload folder using huggingface_hub

app.py

@@ -8,7 +8,12 @@ from flask import Flask, request, jsonify  # For creating the Flask API
 store_sales_predictor_api = Flask("SuperKart Store Sales Predictor")
 
 # Load the trained machine learning model SuperKart_Project_model_v1_0.joblib
-model = joblib.load("SuperKart_Project_model_v1_0.joblib")
+#model = joblib.load("SuperKart_Project_model_v1_0.joblib")
+try:
+    model = joblib.load("SuperKart_Project_model_v1_0.joblib")
+except Exception as e:
+    model = None
+    print("⚠️ Failed to load model:", e)
 
 # Define a route for the home page (GET request)
 @store_sales_predictor_api.get('/')
@@ -49,11 +54,11 @@ def predict_store_sales():
     # Make prediction (get store_sales)
     predicted_store_sales = model.predict(input_data)[0]
 
-    # Calculate actual sales
-    predicted_sales = np.exp(predicted_store_sales)
+    # Calculate actual sales (convert to plain Python float and round)
+    predicted_sales = round(float(np.exp(predicted_store_sales)), 2)
 
-    # Convert predicted_sales to Python float
-    predicted_salese = round(float(predicted_sales), 2)
+    # Return the actual sales
+    return jsonify({'Predicted Sales (in dollars)': predicted_sales})
     # The conversion above is needed as we convert the model prediction (store sales) to actual sales using np.exp, which returns predictions as NumPy float32 values.
     # When we send this value directly within a JSON response, Flask's jsonify function encounters a datatype error
 
@@ -71,6 +76,8 @@ def predict_store_sales_batch():
     """
     # Get the uploaded CSV file from the request
     file = request.files['file']
+    if file is None:
+      return jsonify({"error": "No file uploaded. Please upload a CSV file with key 'file'."}), 400
 
     # Read the CSV file into a Pandas DataFrame
     input_data = pd.read_csv(file)
@@ -79,10 +86,10 @@ def predict_store_sales_batch():
     predicted_store_sales = model.predict(input_data).tolist()
 
     # Calculate actual sales
-    predicted_sales = [round(float(np.exp(store_sales)), 2) for log_price in predicted_store_sales]
+    predicted_sales = [round(float(np.exp(store_sales)), 2) for store_sales in predicted_store_sales]
 
     # Create a dictionary of predictions with store IDs as keys
-    store_ids = input_data['id'].tolist()  # Assuming 'id' is the store ID column
+    store_ids = input_data['Store_Id'].tolist()  # Assuming 'id' is the store ID column
     output_dict = dict(zip(store_ids, predicted_sales))  # Use actual sales
 
     # Return the predictions dictionary as a JSON response