Binary Classification 1

🚧 Note

For more information on uploading a model artifact to Fiddler, see Uploading a Model Artifact.

Suppose you would like to upload a model artifact for a binary classification model.

Following is an example of what the package.py script may look like.

import pickle
from pathlib import Path
import pandas as pd

PACKAGE_PATH = Path(__file__).parent

OUTPUT_COLUMN = ['probability_over_50k']

class MyModel:

    def __init__(self):
        
        # Load the model
        with open(f'{PACKAGE_PATH}/model.pkl', 'rb') as pkl_file:
            self.model = pickle.load(pkl_file)

    def predict(self, input_df):
        
        # Store predictions in a DataFrame
        return pd.DataFrame(self.model.predict_proba(input_df)[:, 1], columns=OUTPUT_COLUMN)

def get_model():
    return MyModel()

Here, we are assuming that the model prediction column that has been specified in the ModelSpec object is called probability_over_50k.