def test_BaseTRegressor(generate_regression_data):
y, X, treatment, tau, b, e = generate_regression_data()
learner = BaseTRegressor(learner=XGBRegressor())
# check the accuracy of the ATE estimation
ate_p, lb, ub = learner.estimate_ate(X=X, treatment=treatment, y=y)
assert (ate_p >= lb) and (ate_p <= ub)
assert ape(tau.mean(), ate_p) < ERROR_THRESHOLD
# check the accuracy of the CATE estimation with the bootstrap CI
cate_p, _, _ = learner.fit_predict(X=X,
treatment=treatment,
y=y,
return_ci=True,
n_bootstraps=10)
auuc_metrics = pd.DataFrame({
'cate_p': cate_p.flatten(),
'W': treatment,
'y': y,
'treatment_effect_col': tau
})
cumgain = get_cumgain(auuc_metrics,
outcome_col='y',
treatment_col='W',
treatment_effect_col='tau')
# Check if the cumulative gain when using the model's prediction is
# higher than it would be under random targeting
assert cumgain['cate_p'].sum() > cumgain['Random'].sum()
def test_BaseTRegressor(generate_regression_data):
y, X, treatment, tau, b, e = generate_regression_data()
learner = BaseTRegressor(learner=XGBRegressor())
# check the accuracy of the ATE estimation
ate_p, lb, ub = learner.estimate_ate(X=X, treatment=treatment, y=y)
assert (ate_p >= lb) and (ate_p <= ub)
assert ape(tau.mean(), ate_p) < ERROR_THRESHOLD
# check the accuracy of the CATE estimation with the bootstrap CI
cate_p, _, _ = learner.fit_predict(X=X, treatment=treatment, y=y, return_ci=True, n_bootstraps=10)
assert gini(tau, cate_p.flatten()) > .5
def test_BaseTRegressor(generate_regression_data):
y, X, treatment, tau, b, e = generate_regression_data()
learner = BaseTRegressor(learner=XGBRegressor())
# check the accuracy of the ATE estimation
ate_p, lb, ub = learner.estimate_ate(X=X, treatment=treatment, y=y)
assert (ate_p >= lb) and (ate_p <= ub)
assert ape(tau.mean(), ate_p) < ERROR_THRESHOLD
# check pre-train model
ate_p_pt, lb_pt, ub_pt = learner.estimate_ate(X=X,
treatment=treatment,
y=y,
pretrain=True)
assert (ate_p_pt == ate_p) and (lb_pt == lb) and (ub_pt == ub)
# check the accuracy of the CATE estimation with the bootstrap CI
cate_p, _, _ = learner.fit_predict(X=X,
treatment=treatment,
y=y,
return_ci=True,
n_bootstraps=10)
auuc_metrics = pd.DataFrame({
"cate_p": cate_p.flatten(),
"W": treatment,
"y": y,
"treatment_effect_col": tau,
})
cumgain = get_cumgain(auuc_metrics,
outcome_col="y",
treatment_col="W",
treatment_effect_col="tau")
# Check if the cumulative gain when using the model's prediction is
# higher than it would be under random targeting
assert cumgain["cate_p"].sum() > cumgain["Random"].sum()
predictions[
'predictions_randomized_trial_test'] = predictions_randomized_trial_test
predictions['predictions_easy_propensity'] = predictions_easy_propensity
predictions[
'predictions_easy_propensity_test'] = predictions_easy_propensity_test
return predictions
estimators_R = { #'learner_dtr': BaseRRegressor(learner=DecisionTreeRegressor()),
'learner_xgb': BaseRRegressor(learner=XGBRegressor()),
'learner_lr': BaseRRegressor(learner=LinearRegression())
}
estimators_T = {
'learner_xgb': BaseTRegressor(learner=XGBRegressor()),
'learner_lr': BaseTRegressor(learner=LinearRegression())
}
import stacking_helpers
predictions_R = generate_predicitons_by_learner(estimators_R)
predictions_T = generate_predicitons_by_learner(estimators_T)
pred_R = predictions_R['predictions_randomized_trial']
pred_R_test = predictions_R['predictions_randomized_trial_test']
plt.figure(figsize=(15, 6))
##final r rand is predictions made using the ensemble weights
final_R_rand = stacking_helpers.fit_and_eval_learners(
pred_R, pred_R_test, 'Randomized Trial R learner')