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_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)
def test_compare_tmle_continuous(self, cf):
cf['cd4_wk45'] = np.log(cf['cd4_wk45'])
stmle = StochasticTMLE(cf, exposure='art', outcome='cd4_wk45')
stmle.exposure_model(
'male + age0 + age_rs1 + age_rs2 + cd40 + cd4_rs1 + cd4_rs2 + dvl0'
)
stmle.outcome_model(
'art + male + age0 + age_rs1 + age_rs2 + cd40 + cd4_rs1 + cd4_rs2 + dvl0'
)
stmle.fit(p=1.0, samples=1)
all_treat = stmle.marginal_outcome
stmle.fit(p=0.0, samples=1)
non_treat = stmle.marginal_outcome
tmle = TMLE(cf, 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.fit()
expected = tmle.average_treatment_effect
npt.assert_allclose(expected, all_treat - non_treat, atol=1e-3)
def test_match_r_epsilons(self, df):
r_epsilons = [-0.016214091, 0.003304079]
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)
tmle.fit()
npt.assert_allclose(tmle._epsilon, r_epsilons, rtol=1e-5)
def test_match_r_epsilons_continuous(self, cf):
r_epsilons = [-0.0046411652, 0.0002270186]
tmle = TMLE(cf, 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.fit()
npt.assert_allclose(tmle._epsilon, r_epsilons, rtol=1e-4, atol=1e-4)
def test_match_r_tmle_riskdifference(self, df):
r_rd = -0.08440622
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)
tmle.fit()
npt.assert_allclose(tmle.risk_difference, r_rd)
def test_match_r_tmle_rd_ci(self, df):
r_ci = -0.1541104, -0.01470202
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)
tmle.fit()
npt.assert_allclose(tmle.risk_difference_ci, r_ci, rtol=1e-5)
def test_match_r_tmle_riskratio(self, df):
r_rr = 0.5344266
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)
tmle.fit()
npt.assert_allclose(tmle.risk_ratio, r_rr)
def test_match_r_tmle_rr_ci(self, df):
r_ci = 0.2773936, 1.0296262
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)
tmle.fit()
npt.assert_allclose(tmle.risk_ratio_ci, r_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_no_ate_with_binary(self, df):
tmle = TMLE(df, exposure='art', outcome='dead')
tmle.exposure_model('male + age0 + age_rs1 + age_rs2 + cd40 + cd4_rs1 + cd4_rs2 + dvl0',
bound=[0.025, 0.9], print_results=False)
tmle.outcome_model('art + male + age0 + age_rs1 + age_rs2 + cd40 + cd4_rs1 + cd4_rs2 + dvl0',
print_results=False)
tmle.fit()
assert tmle.average_treatment_effect is None
assert tmle.average_treatment_effect_ci is None
def test_sklearn_in_tmle2(self, cf):
log = LogisticRegression(C=1.0)
lin = LinearRegression()
tmle = TMLE(cf, exposure='art', outcome='cd4_wk45')
tmle.exposure_model('male + age0 + cd40 + dvl0', custom_model=log)
tmle.outcome_model('art + male + age0 + cd40 + dvl0', custom_model=lin)
tmle.fit()
npt.assert_allclose(tmle.average_treatment_effect, 236.049719, rtol=1e-5)
npt.assert_allclose(tmle.average_treatment_effect_ci, [135.999264, 336.100175], rtol=1e-5)
def tmle(outcome, treatment, data):
tml = TMLE(data, exposure=treatment, outcome=outcome)
cols = data.drop(columns=[outcome, treatment]).columns
s = str(cols[0])
for j in range(1, len(cols)):
s = s + ' + ' + str(cols[j])
tml.exposure_model(s)
tml.outcome_model(s)
tml.fit()
return tml.average_treatment_effect
def test_asymmetric_bounds_on_gW(self, df):
r_rd = -0.08433208
r_ci = -0.1541296, -0.01453453
tmle = TMLE(df, exposure='art', outcome='dead')
tmle.exposure_model('male + age0 + age_rs1 + age_rs2 + cd40 + cd4_rs1 + cd4_rs2 + dvl0',
bound=[0.025, 0.9], print_results=False)
tmle.outcome_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_ci, rtol=1e-5)
def test_symmetric_bounds_on_gW(self, df):
r_rd = -0.08203143
r_ci = -0.1498092, -0.01425363
tmle = TMLE(df, exposure='art', outcome='dead')
tmle.exposure_model('male + age0 + age_rs1 + age_rs2 + cd40 + cd4_rs1 + cd4_rs2 + dvl0',
bound=0.1, print_results=False)
tmle.outcome_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_ci, rtol=1e-5)
def test_match_r_continuous_poisson(self, cf):
r_ate = 223.4648
r_ci = 118.6276, 328.3019
tmle = TMLE(cf, 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, continuous_distribution='poisson')
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)
def test_match_r_continuous_outcome(self, cf):
r_ate = 223.4022
r_ci = 118.6037, 328.2008
tmle = TMLE(cf, 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.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)
def test_match_r_continuous_outcome_gbounds(self, cf):
r_ate = 223.3958
r_ci = 118.4178, 328.3737
tmle = TMLE(cf, exposure='art', outcome='cd4_wk45')
tmle.exposure_model('male + age0 + age_rs1 + age_rs2 + cd40 + cd4_rs1 + cd4_rs2 + dvl0',
bound=[0.025, 0.9], print_results=False)
tmle.outcome_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)
def test_no_risk_with_continuous(self, cf):
tmle = TMLE(cf, exposure='art', outcome='cd4_wk45')
tmle.exposure_model('male + age0 + age_rs1 + age_rs2 + cd40 + cd4_rs1 + cd4_rs2 + dvl0',
bound=[0.025, 0.9], print_results=False)
tmle.outcome_model('art + male + age0 + age_rs1 + age_rs2 + cd40 + cd4_rs1 + cd4_rs2 + dvl0',
print_results=False)
tmle.fit()
assert tmle.risk_difference is None
assert tmle.risk_ratio is None
assert tmle.odds_ratio is None
assert tmle.risk_difference_ci is None
assert tmle.risk_ratio_ci is None
assert tmle.odds_ratio_ci is None
def test_error_when_no_models_specified3(self, df):
tmle = TMLE(df, exposure='art', outcome='dead')
tmle.outcome_model(
'art + male + age0 + age_rs1 + age_rs2 + cd40 + cd4_rs1 + cd4_rs2 + dvl0',
print_results=False)
with pytest.raises(ValueError):
tmle.fit()
def test_sklearn_in_tmle(self, df):
log = LogisticRegression(C=1.0)
tmle = TMLE(df, exposure='art', outcome='dead')
tmle.exposure_model('male + age0 + cd40 + dvl0', custom_model=log)
tmle.outcome_model('art + male + age0 + cd40 + dvl0', custom_model=log)
tmle.fit()
# Testing RD match
npt.assert_allclose(tmle.risk_difference, -0.091372098)
npt.assert_allclose(tmle.risk_difference_ci, [-0.1595425678, -0.0232016282], rtol=1e-5)
# Testing RR match
npt.assert_allclose(tmle.risk_ratio, 0.4998833415)
npt.assert_allclose(tmle.risk_ratio_ci, [0.2561223823, 0.9756404452], rtol=1e-5)
# Testing OR match
npt.assert_allclose(tmle.odds_ratio, 0.4496171689)
npt.assert_allclose(tmle.odds_ratio_ci, [0.2139277755, 0.944971255], rtol=1e-5)
def test_compare_tmle_binary(self, df):
stmle = StochasticTMLE(df, exposure='art', outcome='dead')
stmle.exposure_model(
'male + age0 + age_rs1 + age_rs2 + cd40 + cd4_rs1 + cd4_rs2 + dvl0'
)
stmle.outcome_model(
'art + male + age0 + age_rs1 + age_rs2 + cd40 + cd4_rs1 + cd4_rs2 + dvl0'
)
stmle.fit(p=1.0, samples=1)
all_treat = stmle.marginal_outcome
stmle.fit(p=0.0, samples=1)
non_treat = stmle.marginal_outcome
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)
tmle.fit()
expected = tmle.risk_difference
npt.assert_allclose(expected, all_treat - non_treat, atol=1e-4)
def causal_check():
data = load_sample_data(False).drop(columns=['cd4_wk45'])
data[['cd4_rs1', 'cd4_rs2']] = spline(data,
'cd40',
n_knots=3,
term=2,
restricted=True)
data[['age_rs1', 'age_rs2']] = spline(data,
'age0',
n_knots=3,
term=2,
restricted=True)
# Check TimeFixedGFormula diagnostics
g = TimeFixedGFormula(data, exposure='art', outcome='dead')
g.outcome_model(
model=
'art + male + age0 + age_rs1 + age_rs2 + cd40 + cd4_rs1 + cd4_rs2 + dvl0'
)
g.run_diagnostics(decimal=3)
# Check IPTW plots
ipt = IPTW(data, treatment='art', outcome='dead')
ipt.treatment_model(
'male + age0 + age_rs1 + age_rs2 + cd40 + cd4_rs1 + cd4_rs2 + dvl0',
stabilized=True)
ipt.marginal_structural_model('art')
ipt.fit()
ipt.plot_love()
plt.tight_layout()
plt.show()
ipt.plot_kde()
plt.show()
ipt.plot_kde(measure='logit')
plt.show()
ipt.plot_boxplot()
plt.show()
ipt.plot_boxplot(measure='logit')
plt.show()
ipt.run_diagnostics()
# Check AIPTW Diagnostics
aipw = AIPTW(data, exposure='art', outcome='dead')
aipw.exposure_model(
'male + age0 + age_rs1 + age_rs2 + cd40 + cd4_rs1 + cd4_rs2 + dvl0')
aipw.outcome_model(
'art + male + age0 + age_rs1 + age_rs2 + cd40 + cd4_rs1 + cd4_rs2 + dvl0'
)
aipw.fit()
aipw.run_diagnostics()
aipw.plot_kde(to_plot='exposure')
plt.show()
aipw.plot_kde(to_plot='outcome')
plt.show()
aipw.plot_love()
plt.show()
# Check TMLE diagnostics
tmle = TMLE(data, exposure='art', outcome='dead')
tmle.exposure_model(
'male + age0 + age_rs1 + age_rs2 + cd40 + cd4_rs1 + cd4_rs2 + dvl0')
tmle.outcome_model(
'art + male + age0 + age_rs1 + age_rs2 + cd40 + cd4_rs1 + cd4_rs2 + dvl0'
)
tmle.fit()
tmle.run_diagnostics()
tmle.plot_kde(to_plot='exposure')
plt.show()
tmle.plot_kde(to_plot='outcome')
plt.show()
tmle.plot_love()
plt.show()
# Check SurvivalGFormula plots
df = load_sample_data(False).drop(columns=['cd4_wk45'])
df['t'] = np.round(df['t']).astype(int)
df = pd.DataFrame(np.repeat(df.values, df['t'], axis=0),
columns=df.columns)
df['t'] = df.groupby('id')['t'].cumcount() + 1
df.loc[((df['dead'] == 1) & (df['id'] != df['id'].shift(-1))), 'd'] = 1
df['d'] = df['d'].fillna(0)
df['t_sq'] = df['t']**2
df['t_cu'] = df['t']**3
sgf = SurvivalGFormula(df,
idvar='id',
exposure='art',
outcome='d',
time='t')
sgf.outcome_model(
model='art + male + age0 + cd40 + dvl0 + t + t_sq + t_cu')
sgf.fit(treatment='all')
sgf.plot()
plt.show()
sgf.plot(c='r', linewidth=3, alpha=0.8)
plt.show()
# Treatment model
aipw.exposure_model('male + age0 + age_rs1 + age_rs2 + cd40 + cd4_rs1 + cd4_rs2 + dvl0',
print_results=False, bound=0.01)
# 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
def test_error_when_no_models_specified1(self, df):
tmle = TMLE(df, exposure='art', outcome='dead')
with pytest.raises(ValueError):
tmle.fit()
def test_drop_missing_data(self):
df = ze.load_sample_data(False)
tmle = TMLE(df, exposure='art', outcome='dead')
assert df.dropna(subset=['cd4_wk45']).shape[0] == tmle.df.shape[0]
