Upload 5 files

prediction.py

@@ -1,31 +1,30 @@
-# prediction.py
-
 import joblib
 import pandas as pd
 
-# Load the pipeline and model
+# Load the preprocessing pipeline
 pipeline = joblib.load('full_pipeline_with_unit_price.pkl')
+
+# Load the model
 model = joblib.load('best_model.pkl')
 
-def make_prediction(features):
+def make_prediction(input_features):
     """
-    Takes an array of original features, transforms it using the pipeline, 
+    Takes a dictionary of features, transforms it using the pipeline, 
     and makes a prediction with the model.
     
     Parameters:
-    - features: array-like, shape [n_features]
+    - input_features: dict, where keys are feature names and values are the corresponding values
     
     Returns:
     - The predicted value as a float.
     """
-    # Convert the features array into a DataFrame expected by the pipeline
-    # Note: You need to ensure the columns match those expected by the pipeline
-    features_df = pd.DataFrame([features], columns=['sales', 'quantity', 'discount', 'sub_category'])
+    # Convert the input features dictionary into a DataFrame
+    features_df = pd.DataFrame([input_features])
     
     # Process features through the pipeline
     processed_features = pipeline.transform(features_df)
     
-    # Make a prediction
+    # Make a prediction with the processed features using the model
     prediction = model.predict(processed_features)
     
     return prediction[0]  # Assuming we want a single prediction value