Spaces:
Sleeping
Sleeping
Upload 5 files
Browse files- prediction.py +9 -10
prediction.py
CHANGED
@@ -1,31 +1,30 @@
|
|
1 |
-
# prediction.py
|
2 |
-
|
3 |
import joblib
|
4 |
import pandas as pd
|
5 |
|
6 |
-
# Load the pipeline
|
7 |
pipeline = joblib.load('full_pipeline_with_unit_price.pkl')
|
|
|
|
|
8 |
model = joblib.load('best_model.pkl')
|
9 |
|
10 |
-
def make_prediction(
|
11 |
"""
|
12 |
-
Takes
|
13 |
and makes a prediction with the model.
|
14 |
|
15 |
Parameters:
|
16 |
-
-
|
17 |
|
18 |
Returns:
|
19 |
- The predicted value as a float.
|
20 |
"""
|
21 |
-
# Convert the features
|
22 |
-
|
23 |
-
features_df = pd.DataFrame([features], columns=['sales', 'quantity', 'discount', 'sub_category'])
|
24 |
|
25 |
# Process features through the pipeline
|
26 |
processed_features = pipeline.transform(features_df)
|
27 |
|
28 |
-
# Make a prediction
|
29 |
prediction = model.predict(processed_features)
|
30 |
|
31 |
return prediction[0] # Assuming we want a single prediction value
|
|
|
|
|
|
|
1 |
import joblib
|
2 |
import pandas as pd
|
3 |
|
4 |
+
# Load the preprocessing pipeline
|
5 |
pipeline = joblib.load('full_pipeline_with_unit_price.pkl')
|
6 |
+
|
7 |
+
# Load the model
|
8 |
model = joblib.load('best_model.pkl')
|
9 |
|
10 |
+
def make_prediction(input_features):
|
11 |
"""
|
12 |
+
Takes a dictionary of features, transforms it using the pipeline,
|
13 |
and makes a prediction with the model.
|
14 |
|
15 |
Parameters:
|
16 |
+
- input_features: dict, where keys are feature names and values are the corresponding values
|
17 |
|
18 |
Returns:
|
19 |
- The predicted value as a float.
|
20 |
"""
|
21 |
+
# Convert the input features dictionary into a DataFrame
|
22 |
+
features_df = pd.DataFrame([input_features])
|
|
|
23 |
|
24 |
# Process features through the pipeline
|
25 |
processed_features = pipeline.transform(features_df)
|
26 |
|
27 |
+
# Make a prediction with the processed features using the model
|
28 |
prediction = model.predict(processed_features)
|
29 |
|
30 |
return prediction[0] # Assuming we want a single prediction value
|