def test_sklearn_in_tmle_missing(self, mf):
log = LogisticRegression(C=1.0)
tmle = TMLE(mf, exposure='art', outcome='dead')
tmle.exposure_model('male + age0 + cd40 + dvl0',
custom_model=log,
print_results=False)
tmle.missing_model('male + age0 + cd40 + dvl0',
custom_model=log,
print_results=False)
tmle.outcome_model('art + male + age0 + cd40 + dvl0',
custom_model=log,
print_results=False)
tmle.fit()
# Testing RD match
npt.assert_allclose(tmle.risk_difference, -0.090086, rtol=1e-5)
npt.assert_allclose(tmle.risk_difference_ci, [-0.160371, -0.019801],
rtol=1e-4)
# Testing RR match
npt.assert_allclose(tmle.risk_ratio, 0.507997, rtol=1e-5)
npt.assert_allclose(tmle.risk_ratio_ci, [0.256495, 1.006108],
rtol=1e-4)
# Testing OR match
npt.assert_allclose(tmle.odds_ratio, 0.457541, rtol=1e-5)
npt.assert_allclose(tmle.odds_ratio_ci, [0.213980, 0.978331],
rtol=1e-4)
def test_missing_binary_outcome(self, mf):
r_rd = -0.08168098
r_rd_ci = -0.15163818, -0.01172378
r_rr = 0.5495056
r_rr_ci = 0.2893677, 1.0435042
r_or = 0.4996546
r_or_ci = 0.2435979, 1.0248642
tmle = TMLE(mf, exposure='art', outcome='dead')
tmle.exposure_model(
'male + age0 + age_rs1 + age_rs2 + cd40 + cd4_rs1 + cd4_rs2 + dvl0',
print_results=False)
tmle.outcome_model(
'art + male + age0 + age_rs1 + age_rs2 + cd40 + cd4_rs1 + cd4_rs2 + dvl0',
print_results=False)
tmle.missing_model(
'art + male + age0 + age_rs1 + age_rs2 + cd40 + cd4_rs1 + cd4_rs2 + dvl0',
print_results=False)
tmle.fit()
npt.assert_allclose(tmle.risk_difference, r_rd)
npt.assert_allclose(tmle.risk_difference_ci, r_rd_ci, rtol=1e-5)
npt.assert_allclose(tmle.risk_ratio, r_rr)
npt.assert_allclose(tmle.risk_ratio_ci, r_rr_ci, rtol=1e-5)
npt.assert_allclose(tmle.odds_ratio, r_or)
npt.assert_allclose(tmle.odds_ratio_ci, r_or_ci, rtol=1e-5)
def test_no_missing_data(self, df):
tmle = TMLE(df, exposure='art', outcome='dead')
tmle.exposure_model('male + age0 + age_rs1 + age_rs2 + cd40 + cd4_rs1 + cd4_rs2 + dvl0',
print_results=False)
tmle.outcome_model('art + male + age0 + age_rs1 + age_rs2 + cd40 + cd4_rs1 + cd4_rs2 + dvl0',
print_results=False)
with pytest.raises(ValueError):
tmle.missing_model('art + male + age0 + age_rs1 + age_rs2 + cd40 + cd4_rs1 + cd4_rs2 + dvl0',
print_results=False)
def test_missing_continuous_outcome(self, mcf):
r_ate = 211.8295
r_ci = 107.7552, 315.9038
tmle = TMLE(mcf, exposure='art', outcome='cd4_wk45')
tmle.exposure_model('male + age0 + age_rs1 + age_rs2 + cd40 + cd4_rs1 + cd4_rs2 + dvl0',
print_results=False)
tmle.outcome_model('art + male + age0 + age_rs1 + age_rs2 + cd40 + cd4_rs1 + cd4_rs2 + dvl0',
print_results=False)
tmle.missing_model('art + male + age0 + age_rs1 + age_rs2 + cd40 + cd4_rs1 + cd4_rs2 + dvl0',
print_results=False)
tmle.fit()
npt.assert_allclose(tmle.average_treatment_effect, r_ate, rtol=1e-3)
npt.assert_allclose(tmle.average_treatment_effect_ci, r_ci, rtol=1e-3)
# Outcome model
aipw.outcome_model('art + male + age0 + age_rs1 + age_rs2 + cd40 + cd4_rs1 + cd4_rs2 + dvl0',
print_results=False)
# Calculating estimate
aipw.fit()
# Printing summary results
aipw.summary()
#############################
# TMLE
from zepid.causal.doublyrobust import TMLE
tmle = TMLE(df, exposure='art', outcome='dead')
tmle.exposure_model('male + age0 + age_rs1 + age_rs2 + cd40 + cd4_rs1 + cd4_rs2 + dvl0',
print_results=False, bound=0.01)
tmle.missing_model('art + male + age0 + cd40 + cd4_rs1 + cd4_rs2 + dvl0',
print_results=False)
tmle.outcome_model('art + male + age0 + age_rs1 + age_rs2 + cd40 + cd4_rs1 + cd4_rs2 + dvl0',
print_results=False)
tmle.fit()
tmle.summary()
#############################
# Cross-fitting
from sklearn.ensemble import RandomForestClassifier
from zepid.superlearner import GLMSL, StepwiseSL, SuperLearner
from zepid.causal.doublyrobust import SingleCrossfitTMLE
# SuperLearner set-up
labels = ["LogR", "Step.int", "RandFor"]
candidates = [GLMSL(sm.families.family.Binomial()),
StepwiseSL(sm.families.family.Binomial(), selection="forward", order_interaction=0),
