Upload folder using huggingface_hub

app.py

@@ -46,19 +46,14 @@ def predict_product_revenue_price():
 
     # Convert the extracted data into a Pandas DataFrame
     input_data = pd.DataFrame([sample])
-    print("input_data:", input_data)
 
     # Make prediction (get log_price)
     predicted_log_price = model.predict(input_data)[0]
-    print("predicted_log_price:", predicted_log_price)
     # Calculate actual price
- #   predicted_price = np.exp(predicted_log_price)
     predicted_price = predicted_log_price
-    print("predicted_price:", predicted_price)
 
     # Convert predicted_price to Python float
-    predicted_price = round(float(predicted_price), 2)
-    print("predicted_price:", predicted_price)
+    predicted_price = round(float(predicted_price), 6)
     # The conversion above is needed as we convert the model prediction (log price) to actual price 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
 
@@ -82,18 +77,12 @@ def predict_product_revenue_price_batch():
 
     # Make predictions for all properties in the DataFrame (get log_prices)
     predicted_log_prices = model.predict(input_data).tolist()
-    print("input_data:", input_data)
-    print("predicted_log_prices:", predicted_log_prices)
 
     # Calculate actual prices
-   # predicted_prices = [round(float(np.exp(log_price)), 2) for log_price in predicted_log_prices]
-    predicted_prices = [round(float(log_price), 2) for log_price in predicted_log_prices]
-
-    print("predicted_prices:", predicted_prices)
+    predicted_prices = [round(float(log_price), 6) for log_price in predicted_log_prices]
 
     # Create a dictionary of predictions with property IDs as keys
     property_ids = input_data['Product_Id'].tolist()  # Assuming 'id' is the property ID column
-    print("property_ids:", property_ids)
 
     output_dict = dict(zip(property_ids, predicted_prices))  # Use actual prices