Upload folder using huggingface_hub

app.py

@@ -8,7 +8,7 @@ from flask import Flask, request, jsonify  # For creating the Flask API
 sales_total_predictor_api = Flask("SuperKart  Sales Total Predictor")
 
 # Load the trained machine learning model
-model = joblib.load("product_stores_sales_total_prediction_model_v1_0.joblib")
+model = joblib.load("/content/drive/MyDrive/Colab Notebooks/Model Deployment/deployment_files/product_stores_sales_total_prediction_model_v1_0.joblib")
 
 # Define a route for the home page (GET request)
 @sales_total_predictor_api.get('/')
@@ -72,14 +72,13 @@ def predict_sales_total_batch():
     # Read the CSV file into a Pandas DataFrame
     input_data = pd.read_csv(file)
 
-    # Make predictions for all product and store in the DataFrame 
+    # Make predictions for all product and store in the DataFrame
     predicted_prices = model.predict(input_data).tolist()
 
     # Create a dictionary of predictions with property IDs as keys
-    product_store_ids = input_data[['Product_Id', 'Store_Id']].values.tolist()  
-    keys = [f"{pid}_{sid}" for pid, sid in product_store_ids]
-    output_dict = dict(zip(keys, predicted_prices))
-    
+    product_store_ids = input_data[['Product_Id', 'Store_Id']].values.tolist()
+    output_dict = dict(zip(product_store_ids, predicted_prices))  # Use actual prices
+
     # Return the predictions dictionary as a JSON response
     return output_dict