LTT_2.py

exog_perf = [] # Exogenous performance

# Iterate rows of exclusion matrix and estimate model on reduced data
for row in trange(excl_mat.shape[0]):
    # Get exclusion mask and invert to inclusion mask (True = included)
    # Inversion is necessary for numpy indexing with boolean arrays
    mask = invert(squeeze(excl_mat[row].toarray()))

    # Fit arbtitrary estimator
    est = LinearRegression(n_jobs=-1)
    est.fit(
        data["train_noise"].X[mask],
        data["train_noise"].y[mask],
    )

    # Evaluate estimator on exogenous performance and store result
    # Here we use the MSE on the validation data as exogenous performance.
    exog_perf.append(
        mean_squared_error(
            est.predict(data["val"]. X), 
            data["val"].y,
        )
    )

exog_perf = array(exog_perf)