Upload folder using huggingface_hub

app.py

@@ -62,35 +62,39 @@ def predict_sales():
 
 
 # Define an endpoint for batch prediction (POST request)
+sales_predictor_api = Flask(__name__)
 @sales_predictor_api.post('/v1/salesbatch')
 def sales_price_batch():
     """
-    This function handles POST requests to the '/v1/salesbatch' endpoint.
-    It expects a CSV file containing property details for multiple properties
-    and returns the predicted rental prices as a dictionary in the JSON response.
+    Endpoint to handle batch predictions from uploaded CSV.
+    Returns predicted sales for each (Product_Id, Store_Id) pair.
     """
-    # Get the uploaded CSV file from the request
-    file = request.files['file']
+    try:
+        # Get the uploaded CSV file
+        file = request.files['file']
 
-    # Read the CSV file into a Pandas DataFrame
-    input_data_batch = pd.read_csv(file)
-    input_data_batch['Store_Age'] = 2025 - input_data_batch['Store_Establishment_Year']
+        # Load and process data
+        input_data_batch = pd.read_csv(file)
+        input_data_batch['Store_Age'] = 2025 - input_data_batch['Store_Establishment_Year']
 
-    product_ids = input_data_batch['Product_Id'].tolist()  # Assuming 'Id' is the product ID column
-    store_ids = input_data_batch['Store_Id'].tolist()  # Assuming 'Id' is the store ID column
-    input_data_batch = input_data_batch.drop(['Product_Id', 'Store_Id', 'Store_Establishment_Year'], axis=1)
+        # Extract identifiers
+        product_ids = input_data_batch['Product_Id'].tolist()
+        store_ids = input_data_batch['Store_Id'].tolist()
 
-    # Apply same transformations
-    #input_transformed = preprocessor.transform(input_data)
+        # Drop unused columns
+        input_data_batch = input_data_batch.drop(['Product_Id', 'Store_Id', 'Store_Establishment_Year'], axis=1)
 
-    # Make predictions for all properties in the DataFrame (get log_prices)
-    predictions = model.predict(input_data_batch).tolist()
+        # Apply preprocessing if needed
+        # input_data_transformed = preprocessor.transform(input_data_batch)
+        # predictions = model.predict(input_data_transformed)
 
-     # Round predictions
-    predicted_sales = [round(float(x), 2) for x in predictions]
+        predictions = model.predict(input_data_batch)  # Assuming already preprocessed or numeric
 
-    # Structure output as a list of dicts
-        output_dict = [
+        # Round predictions
+        predicted_sales = [round(float(x), 2) for x in predictions]
+
+        # Structure output as a list of dicts
+        output = [
             {
                 "Product_Id": pid,
                 "Store_Id": sid,
@@ -98,8 +102,12 @@ def sales_price_batch():
             }
             for pid, sid, psale in zip(product_ids, store_ids, predicted_sales)
         ]
-        return jsonify({"predictions": output_dict})
 
-# Run the Flask application in debug mode if this script is executed directly
+        return jsonify({"predictions": output})
+
+    except Exception as e:
+        return jsonify({"error": str(e)}), 500
+
+
 if __name__ == '__main__':
     sales_predictor_api.run(debug=True)