def test_match_rr(self, df):
aipw = AIPTW(df, exposure='art', outcome='dead')
aipw.exposure_model('male + age0 + age_rs1 + age_rs2 + cd40 + cd4_rs1 + cd4_rs2 + dvl0', print_results=False)
aipw.outcome_model('art + male + age0 + age_rs1 + age_rs2 + cd40 + cd4_rs1 + cd4_rs2 + dvl0',
print_results=False)
aipw.fit()
npt.assert_allclose(aipw.risk_ratio, 0.5319812235)
def test_match_rd(self, df):
aipw = AIPTW(df, exposure='art', outcome='dead')
aipw.exposure_model('male + age0 + age_rs1 + age_rs2 + cd40 + cd4_rs1 + cd4_rs2 + dvl0', print_results=False)
aipw.outcome_model('art + male + age0 + age_rs1 + age_rs2 + cd40 + cd4_rs1 + cd4_rs2 + dvl0',
print_results=False)
aipw.fit()
npt.assert_allclose(aipw.risk_difference, -0.0848510605)
def test_error_when_no_models_specified3(self, df):
aipw = AIPTW(df, exposure='art', outcome='dead')
aipw.outcome_model(
'art + male + age0 + age_rs1 + age_rs2 + cd40 + cd4_rs1 + cd4_rs2 + dvl0',
print_results=False)
with pytest.raises(ValueError):
aipw.fit()
def test_poisson_outcomes(self, cf):
aipw = AIPTW(cf, exposure='art', outcome='cd4_wk45')
aipw.exposure_model('male + age0 + age_rs1 + age_rs2 + cd40 + cd4_rs1 + cd4_rs2 + dvl0', print_results=False)
aipw.outcome_model('art + male + age0 + age_rs1 + age_rs2 + cd40 + cd4_rs1 + cd4_rs2 + dvl0',
continuous_distribution='poisson', print_results=False)
aipw.fit()
npt.assert_allclose(aipw.average_treatment_effect, 225.13767, rtol=1e-3)
npt.assert_allclose(aipw.average_treatment_effect_ci, [118.64677, 331.62858], rtol=1e-3)
def test_weighted_continuous_outcomes(self, cf):
cf['weights'] = 2
aipw = AIPTW(cf, exposure='art', outcome='cd4_wk45', weights='weights')
aipw.exposure_model('male + age0 + age_rs1 + age_rs2 + cd40 + cd4_rs1 + cd4_rs2 + dvl0', print_results=False)
aipw.outcome_model('art + male + age0 + age_rs1 + age_rs2 + cd40 + cd4_rs1 + cd4_rs2 + dvl0',
print_results=False)
aipw.fit()
npt.assert_allclose(aipw.average_treatment_effect, 225.13767, rtol=1e-3)
assert aipw.average_treatment_effect_ci is None
def test_bounds2(self, df):
aipw = AIPTW(df, exposure='art', outcome='dead')
aipw.exposure_model('male + age0 + age_rs1 + age_rs2 + cd40 + cd4_rs1 + cd4_rs2 + dvl0',
bound=[0.2, 0.9], print_results=False)
aipw.outcome_model('art + male + age0 + age_rs1 + age_rs2 + cd40 + cd4_rs1 + cd4_rs2 + dvl0',
print_results=False)
aipw.fit()
npt.assert_allclose(aipw.risk_difference, -0.0700780176)
npt.assert_allclose(aipw.risk_difference_ci, (-0.1277925885, -0.0123634468))
def test_bounds(self, df):
aipw = AIPTW(df, exposure='art', outcome='dead')
aipw.exposure_model('male + age0 + age_rs1 + age_rs2 + cd40 + cd4_rs1 + cd4_rs2 + dvl0',
bound=0.1, print_results=False)
aipw.outcome_model('art + male + age0 + age_rs1 + age_rs2 + cd40 + cd4_rs1 + cd4_rs2 + dvl0',
print_results=False)
aipw.fit()
npt.assert_allclose(aipw.risk_difference, -0.0819506956)
npt.assert_allclose(aipw.risk_difference_ci, (-0.1498808287, -0.0140205625))
def test_double_robustness(self, dat):
aipw = AIPTW(dat, exposure='A', outcome='Y')
aipw.exposure_model('L', print_results=False)
aipw.outcome_model('L + A + A:L', print_results=False)
aipw.fit()
both_correct_rd = aipw.risk_difference
both_correct_rr = aipw.risk_ratio
aipw = AIPTW(dat, exposure='A', outcome='Y')
aipw.exposure_model('L', print_results=False)
aipw.outcome_model('A + L', print_results=False)
aipw.fit()
wrong_y_rd = aipw.risk_difference
wrong_y_rr = aipw.risk_ratio
# Testing
npt.assert_allclose(both_correct_rd, wrong_y_rd)
npt.assert_allclose(both_correct_rr, wrong_y_rr)
aipw = AIPTW(dat, exposure='A', outcome='Y')
aipw.exposure_model('1', print_results=False)
aipw.outcome_model('A + L + A:L', print_results=False)
aipw.fit()
wrong_a_rd = aipw.risk_difference
wrong_a_rr = aipw.risk_ratio
# Testing
npt.assert_allclose(both_correct_rd, wrong_a_rd)
npt.assert_allclose(both_correct_rr, wrong_a_rr)
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()
iptw.treatment_model('male + age0 + age_rs1 + age_rs2 + cd40 + cd4_rs1 + cd4_rs2 + dvl0',
bound=0.01, print_results=False)
iptw.marginal_structural_model('art')
iptw.fit()
iptw.summary()
#############################
# AIPTW
from zepid.causal.doublyrobust import AIPTW
aipw = AIPTW(df, exposure='art', outcome='dead')
# 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',