fairlearn

import pandas as pd from fairlearn.metrics import MetricFrame, accuracy_score from sklearn.linear_model import LogisticRegression from sklearn.model_selection import train_test_split from sklearn.preprocessing import StandardScaler, OneHotEncoder from sklearn.compose import ColumnTransformer from sklearn.pipeline import Pipeline # 1. Create dummy data data = { 'feature_1': [10, 12, 11, 15, 13, 9, 14, 16, 11, 13], 'feature_2': [1, 0, 1, 0, 1, 0, 1, 0, 1, 0], 'sensitive_feature': ['A', 'B', 'A', 'B', 'A', 'B', 'A', 'B', 'A', 'B'], 'target': [1, 0, 1, 1, 0, 0, 1, 0, 1, 0] } df = pd.DataFrame(data) X = df[['feature_1', 'feature_2']] y = df['target'] sensitive_features = df['sensitive_feature'] X_train, X_test, y_train, y_test, sf_train, sf_test = train_test_split( X, y, sensitive_features, test_size=0.5, random_state=42 ) # 2. Preprocessing pipeline preprocessor = ColumnTransformer( transformers=[ ('num', StandardScaler(), ['feature_1']), ('cat', OneHotEncoder(handle_unknown='ignore'), ['feature_2']) ], remainder='passthrough' ) # 3. Train a model model = Pipeline(steps=[ ('preprocessor', preprocessor), ('classifier', LogisticRegression(solver='liblinear', random_state=42)) ]) model.fit(X_train, y_train) # 4. Predict and assess fairness using MetricFrame y_pred = model.predict(X_test) metric_frame = MetricFrame( metrics=accuracy_score, y_true=y_test, y_pred=y_pred, sensitive_features=sf_test ) print(f"Overall accuracy: {metric_frame.overall}") print(f"Accuracy by sensitive feature group:\n{metric_frame.by_group}") print("Fairlearn quickstart executed successfully.")