def test_nonparam_dml(self):
y, T, X, W = self._get_data()
dml = NonParamDML(model_y=LinearRegression(),
model_t=LinearRegression(),
model_final=WeightedLasso(),
random_state=123)
dml.fit(y, T, X=X, W=W)
with pytest.raises(Exception):
dml.refit_final()
dml.fit(y, T, X=X, W=W, cache_values=True)
dml.model_final = DebiasedLasso(fit_intercept=False)
dml.refit_final()
assert isinstance(dml.model_cate, DebiasedLasso)
dml.effect_interval(X[:1])
dml.featurizer = PolynomialFeatures(degree=2, include_bias=False)
dml.refit_final()
assert isinstance(dml.featurizer_, PolynomialFeatures)
dml.effect_interval(X[:1])
dml.discrete_treatment = True
dml.featurizer = None
dml.linear_first_stages = True
dml.model_t = LogisticRegression()
dml.model_final = DebiasedLasso()
dml.fit(y, T, X=X, W=W)
newdml = NonParamDML(model_y=LinearRegression(),
model_t=LogisticRegression(),
model_final=DebiasedLasso(),
discrete_treatment=True,
random_state=123).fit(y, T, X=X, W=W)
np.testing.assert_array_equal(dml.effect(X[:1]), newdml.effect(X[:1]))
np.testing.assert_array_equal(dml.effect_interval(X[:1])[0], newdml.effect_interval(X[:1])[0])
def test_inference_with_none_stderr(self):
Y, T, X, W = TestInference.Y, TestInference.T, TestInference.X, TestInference.W
est = DML(model_y=LinearRegression(),
model_t=LinearRegression(),
model_final=Lasso(alpha=0.1, fit_intercept=False),
featurizer=PolynomialFeatures(degree=1, include_bias=False),
random_state=123)
est.fit(Y, T, X=X, W=W)
est.summary()
est.coef__inference().summary_frame()
est.intercept__inference().summary_frame()
est.effect_inference(X).summary_frame()
est.effect_inference(X).population_summary()
est.const_marginal_effect_inference(X).summary_frame()
est.marginal_effect_inference(T, X).summary_frame()
est = NonParamDML(model_y=LinearRegression(),
model_t=LinearRegression(),
model_final=LinearRegression(fit_intercept=False),
featurizer=PolynomialFeatures(degree=1, include_bias=False),
random_state=123)
est.fit(Y, T, X=X, W=W)
est.effect_inference(X).summary_frame()
est.effect_inference(X).population_summary()
est.const_marginal_effect_inference(X).summary_frame()
est.marginal_effect_inference(T, X).summary_frame()
est = DRLearner(model_regression=LinearRegression(),
model_propensity=LogisticRegression(),
model_final=LinearRegression())
est.fit(Y, T, X=X, W=W)
est.effect_inference(X).summary_frame()
est.effect_inference(X).population_summary()
est.const_marginal_effect_inference(X).summary_frame()
est.marginal_effect_inference(T, X).summary_frame()
def test_auto_inference(self):
Y, T, X, W = TestInference.Y, TestInference.T, TestInference.X, TestInference.W
est = DRLearner(model_regression=LinearRegression(),
model_propensity=LogisticRegression(),
model_final=StatsModelsLinearRegression())
est.fit(Y, T, X=X, W=W)
est.effect_inference(X).summary_frame()
est.effect_inference(X).population_summary()
est.const_marginal_effect_inference(X).summary_frame()
est.marginal_effect_inference(T, X).summary_frame()
est = DRLearner(model_regression=LinearRegression(),
model_propensity=LogisticRegression(),
model_final=LinearRegression(),
multitask_model_final=True)
est.fit(Y, T, X=X, W=W)
with pytest.raises(AttributeError):
est.effect_inference(X)
est = DML(model_y=LinearRegression(),
model_t=LinearRegression(),
model_final=StatsModelsLinearRegression(fit_intercept=False),
random_state=123)
est.fit(Y, T, X=X, W=W)
est.summary()
est.coef__inference().summary_frame()
assert est.coef__inference().stderr is not None
est.intercept__inference().summary_frame()
assert est.intercept__inference().stderr is not None
est.effect_inference(X).summary_frame()
assert est.effect_inference(X).stderr is not None
est.effect_inference(X).population_summary()
est.const_marginal_effect_inference(X).summary_frame()
assert est.const_marginal_effect_inference(X).stderr is not None
est.marginal_effect_inference(T, X).summary_frame()
assert est.marginal_effect_inference(T, X).stderr is not None
est = NonParamDML(model_y=LinearRegression(),
model_t=LinearRegression(),
model_final=DebiasedLasso(),
random_state=123)
est.fit(Y, T, X=X, W=W)
est.effect_inference(X).summary_frame()
assert est.effect_inference(X).stderr is not None
est.effect_inference(X).population_summary()
est.const_marginal_effect_inference(X).summary_frame()
assert est.const_marginal_effect_inference(X).stderr is not None
est.marginal_effect_inference(T, X).summary_frame()
assert est.marginal_effect_inference(T, X).stderr is not None
def test_dml_random_state(self):
Y, T, X, W, X_test = TestRandomState._make_data(500, 2)
for est in [
NonParamDML(model_y=RandomForestRegressor(n_estimators=10,
max_depth=4,
random_state=123),
model_t=RandomForestClassifier(n_estimators=10,
max_depth=4,
random_state=123),
model_final=RandomForestRegressor(
max_depth=3,
n_estimators=10,
min_samples_leaf=100,
bootstrap=True,
random_state=123),
discrete_treatment=True,
n_splits=2,
random_state=123),
CausalForestDML(
model_y=RandomForestRegressor(n_estimators=10,
max_depth=4,
random_state=123),
model_t=RandomForestClassifier(n_estimators=10,
max_depth=4,
random_state=123),
n_estimators=8,
discrete_treatment=True,
cv=2,
random_state=123),
LinearDML(model_y=RandomForestRegressor(n_estimators=10,
max_depth=4,
random_state=123),
model_t=RandomForestClassifier(n_estimators=10,
max_depth=4,
random_state=123),
discrete_treatment=True,
n_splits=2,
random_state=123),
SparseLinearDML(discrete_treatment=True,
n_splits=2,
random_state=123),
KernelDML(discrete_treatment=True,
n_splits=2,
random_state=123)
]:
TestRandomState._test_random_state(est, X_test, Y, T, X=X, W=W)
def dml(outcome, treatment, data, method='GBR'):
if method == 'GBR':
est = NonParamDML(model_y=GradientBoostingRegressor(),
model_t=GradientBoostingClassifier(),
model_final=GradientBoostingRegressor(),
discrete_treatment=True)
est.fit(data[outcome],
data[treatment],
X=data.drop(columns=[outcome, treatment]),
W=data.drop(columns=[outcome, treatment]))
point = est.ate(data.drop(columns=[outcome, treatment]), T0=0, T1=1)
if method == 'linear':
est = LinearDML(discrete_treatment=True)
est.fit(data[outcome],
data[treatment],
X=data.drop(columns=[outcome, treatment]),
W=data.drop(columns=[outcome, treatment]))
point = est.ate(data.drop(columns=[outcome, treatment]), T0=0, T1=1)
return point
def test_comparison(self):
def reg():
return LinearRegression()
def clf():
return LogisticRegression()
y, T, X, true_eff = self._get_data()
(X_train, X_val, T_train, T_val, Y_train, Y_val, _,
true_eff_val) = train_test_split(X, T, y, true_eff, test_size=.4)
models = [
('ldml',
LinearDML(model_y=reg(),
model_t=clf(),
discrete_treatment=True,
linear_first_stages=False,
cv=3)),
('sldml',
SparseLinearDML(model_y=reg(),
model_t=clf(),
discrete_treatment=True,
featurizer=PolynomialFeatures(degree=2,
include_bias=False),
linear_first_stages=False,
cv=3)),
('xlearner',
XLearner(models=reg(), cate_models=reg(),
propensity_model=clf())),
('dalearner',
DomainAdaptationLearner(models=reg(),
final_models=reg(),
propensity_model=clf())),
('slearner', SLearner(overall_model=reg())),
('tlearner', TLearner(models=reg())),
('drlearner',
DRLearner(model_propensity=clf(),
model_regression=reg(),
model_final=reg(),
cv=3)),
('rlearner',
NonParamDML(model_y=reg(),
model_t=clf(),
model_final=reg(),
discrete_treatment=True,
cv=3)),
('dml3dlasso',
DML(model_y=reg(),
model_t=clf(),
model_final=reg(),
discrete_treatment=True,
featurizer=PolynomialFeatures(degree=3),
linear_first_stages=False,
cv=3))
]
models = Parallel(n_jobs=-1, verbose=1)(
delayed(_fit_model)(name, mdl, Y_train, T_train, X_train)
for name, mdl in models)
scorer = RScorer(model_y=reg(),
model_t=clf(),
discrete_treatment=True,
cv=3,
mc_iters=2,
mc_agg='median')
scorer.fit(Y_val, T_val, X=X_val)
rscore = [scorer.score(mdl) for _, mdl in models]
rootpehe_score = [
np.sqrt(
np.mean(
(true_eff_val.flatten() - mdl.effect(X_val).flatten())**2))
for _, mdl in models
]
assert LinearRegression().fit(
np.array(rscore).reshape(-1, 1),
np.array(rootpehe_score)).coef_ < 0.5
mdl, _ = scorer.best_model([mdl for _, mdl in models])
rootpehe_best = np.sqrt(
np.mean((true_eff_val.flatten() - mdl.effect(X_val).flatten())**2))
assert rootpehe_best < 1.2 * np.min(rootpehe_score)
mdl, _ = scorer.ensemble([mdl for _, mdl in models])
rootpehe_ensemble = np.sqrt(
np.mean((true_eff_val.flatten() - mdl.effect(X_val).flatten())**2))
assert rootpehe_ensemble < 1.2 * np.min(rootpehe_score)