def test_monte_carlo_for_single_t(self, sim_t_fixed_data):
# Estimating monte carlo for single t
gt = MonteCarloGFormula(sim_t_fixed_data, idvar='id', exposure='A', outcome='Y', time_out='t', time_in='t0')
gt.outcome_model('A + W1_sq + W2 + W3', print_results=False)
gt.exposure_model('W1_sq', print_results=False)
gt.fit(treatment="all", sample=1000000) # Keep this a high number to reduce simulation errors
print(gt.predicted_outcomes)
# Estimating with TimeFixedGFormula
gf = TimeFixedGFormula(sim_t_fixed_data, exposure='A', outcome='Y')
gf.outcome_model(model='A + W1_sq + W2 + W3', print_results=False)
gf.fit(treatment='all')
# Expected behavior; same results between the estimation methods
npt.assert_allclose(gf.marginal_outcome, np.mean(gt.predicted_outcomes['Y']), rtol=1e-3)
def test_complete_mc_procedure_completes(self):
df = load_sample_data(timevary=True)
df['lag_art'] = df['art'].shift(1)
df['lag_art'] = np.where(df.groupby('id').cumcount() == 0, 0, df['lag_art'])
df['lag_cd4'] = df['cd4'].shift(1)
df['lag_cd4'] = np.where(df.groupby('id').cumcount() == 0, df['cd40'], df['lag_cd4'])
df['lag_dvl'] = df['dvl'].shift(1)
df['lag_dvl'] = np.where(df.groupby('id').cumcount() == 0, df['dvl0'], df['lag_dvl'])
df[['age_rs0', 'age_rs1', 'age_rs2']] = spline(df, 'age0', n_knots=4, term=2, restricted=True) # age spline
df['cd40_sq'] = df['cd40'] ** 2
df['cd40_cu'] = df['cd40'] ** 3
df['cd4_sq'] = df['cd4'] ** 2
df['cd4_cu'] = df['cd4'] ** 3
df['enter_sq'] = df['enter'] ** 2
df['enter_cu'] = df['enter'] ** 3
g = MonteCarloGFormula(df, idvar='id', exposure='art', outcome='dead', time_in='enter', time_out='out')
exp_m = '''male + age0 + age_rs0 + age_rs1 + age_rs2 + cd40 + cd40_sq + cd40_cu + dvl0 + cd4 + cd4_sq +
cd4_cu + dvl + enter + enter_sq + enter_cu'''
g.exposure_model(exp_m, restriction="g['lag_art']==0")
out_m = '''art + male + age0 + age_rs0 + age_rs1 + age_rs2 + cd40 + cd40_sq + cd40_cu + dvl0 + cd4 +
cd4_sq + cd4_cu + dvl + enter + enter_sq + enter_cu'''
g.outcome_model(out_m, restriction="g['drop']==0")
dvl_m = '''male + age0 + age_rs0 + age_rs1 + age_rs2 + cd40 + cd40_sq + cd40_cu + dvl0 + lag_cd4 +
lag_dvl + lag_art + enter + enter_sq + enter_cu'''
g.add_covariate_model(label=1, covariate='dvl', model=dvl_m, var_type='binary')
cd4_m = '''male + age0 + age_rs0 + age_rs1 + age_rs2 + cd40 + cd40_sq + cd40_cu + dvl0 + lag_cd4 +
lag_dvl + lag_art + enter + enter_sq + enter_cu'''
cd4_recode_scheme = ("g['cd4'] = np.maximum(g['cd4'],1);"
"g['cd4_sq'] = g['cd4']**2;"
"g['cd4_cu'] = g['cd4']**3")
g.add_covariate_model(label=2, covariate='cd4', model=cd4_m, recode=cd4_recode_scheme, var_type='continuous')
cens_m = """male + age0 + age_rs0 + age_rs1 + age_rs2 + cd40 + cd40_sq + cd40_cu + dvl0 + lag_cd4 +
lag_dvl + lag_art + enter + enter_sq + enter_cu"""
g.censoring_model(cens_m)
g.fit(treatment="((g['art']==1) | (g['lag_art']==1))",
lags={'art': 'lag_art',
'cd4': 'lag_cd4',
'dvl': 'lag_dvl'},
sample=5000, t_max=None,
in_recode=("g['enter_sq'] = g['enter']**2;"
"g['enter_cu'] = g['enter']**3"))
assert isinstance(g.predicted_outcomes, type(pd.DataFrame()))
def mc_gformula_check():
df = load_sample_data(timevary=True)
df['lag_art'] = df['art'].shift(1)
df['lag_art'] = np.where(df.groupby('id').cumcount() == 0, 0, df['lag_art'])
df['lag_cd4'] = df['cd4'].shift(1)
df['lag_cd4'] = np.where(df.groupby('id').cumcount() == 0, df['cd40'], df['lag_cd4'])
df['lag_dvl'] = df['dvl'].shift(1)
df['lag_dvl'] = np.where(df.groupby('id').cumcount() == 0, df['dvl0'], df['lag_dvl'])
df[['age_rs0', 'age_rs1', 'age_rs2']] = spline(df, 'age0', n_knots=4, term=2, restricted=True) # age spline
df['cd40_sq'] = df['cd40'] ** 2 # cd4 baseline cubic
df['cd40_cu'] = df['cd40'] ** 3
df['cd4_sq'] = df['cd4'] ** 2 # cd4 current cubic
df['cd4_cu'] = df['cd4'] ** 3
df['enter_sq'] = df['enter'] ** 2 # entry time cubic
df['enter_cu'] = df['enter'] ** 3
g = MonteCarloGFormula(df, idvar='id', exposure='art', outcome='dead', time_in='enter', time_out='out')
exp_m = '''male + age0 + age_rs0 + age_rs1 + age_rs2 + cd40 + cd40_sq + cd40_cu + dvl0 + cd4 + cd4_sq +
cd4_cu + dvl + enter + enter_sq + enter_cu'''
g.exposure_model(exp_m, restriction="g['lag_art']==0")
out_m = '''art + male + age0 + age_rs0 + age_rs1 + age_rs2 + cd40 + cd40_sq + cd40_cu + dvl0 + cd4 +
cd4_sq + cd4_cu + dvl + enter + enter_sq + enter_cu'''
g.outcome_model(out_m, restriction="g['drop']==0")
dvl_m = '''male + age0 + age_rs0 + age_rs1 + age_rs2 + cd40 + cd40_sq + cd40_cu + dvl0 + lag_cd4 +
lag_dvl + lag_art + enter + enter_sq + enter_cu'''
g.add_covariate_model(label=1, covariate='dvl', model=dvl_m, var_type='binary')
cd4_m = '''male + age0 + age_rs0 + age_rs1 + age_rs2 + cd40 + cd40_sq + cd40_cu + dvl0 + lag_cd4 +
lag_dvl + lag_art + enter + enter_sq + enter_cu'''
cd4_recode_scheme = ("g['cd4'] = np.maximum(g['cd4'],1);"
"g['cd4_sq'] = g['cd4']**2;"
"g['cd4_cu'] = g['cd4']**3")
g.add_covariate_model(label=2, covariate='cd4', model=cd4_m,recode=cd4_recode_scheme, var_type='continuous')
g.fit(treatment="((g['art']==1) | (g['lag_art']==1))",
lags={'art': 'lag_art',
'cd4': 'lag_cd4',
'dvl': 'lag_dvl'},
sample=10000, t_max=None,
in_recode=("g['enter_sq'] = g['enter']**2;"
"g['enter_cu'] = g['enter']**3"))
gf = g.predicted_outcomes
kmn = KaplanMeierFitter()
kmn.fit(durations=gf['out'], event_observed=gf['dead'])
kmo = KaplanMeierFitter()
kmo.fit(durations=df['out'], event_observed=df['dead'], entry=df['enter'])
cens_m = """male + age0 + age_rs0 + age_rs1 + age_rs2 + cd40 + cd40_sq + cd40_cu + dvl0 + lag_cd4 +
lag_dvl + lag_art + enter + enter_sq + enter_cu"""
g.censoring_model(cens_m)
g.fit(treatment="((g['art']==1) | (g['lag_art']==1))",
lags={'art': 'lag_art',
'cd4': 'lag_cd4',
'dvl': 'lag_dvl'},
sample=10000, t_max=None,
in_recode=("g['enter_sq'] = g['enter']**2;"
"g['enter_cu'] = g['enter']**3"))
gf = g.predicted_outcomes
kmc = KaplanMeierFitter()
kmc.fit(durations=gf['out'], event_observed=gf['dead'])
plt.step(kmn.event_table.index, 1 - kmn.survival_function_, c='g', where='post', label='Natural')
plt.step(kmn.event_table.index, 1 - kmc.survival_function_, c='orange', where='post', label='Censor')
plt.step(kmo.event_table.index, 1 - kmo.survival_function_, c='k', where='post', label='True')
plt.legend()
plt.show()
df['cd4_cu'] = df['cd4']**3
df['enter_sq'] = df['enter']**2 # entry time cubic
df['enter_cu'] = df['enter']**3
mcgf = MonteCarloGFormula(
df, # Data set
idvar='id', # ID variable
exposure='art', # Exposure
outcome='dead', # Outcome
time_in='enter', # Start of study period
time_out='out') # End of time per study period
# Pooled Logistic Model: Treatment
exp_m = (
'male + age0 + age_rs0 + age_rs1 + age_rs2 + cd40 + cd40_sq + cd40_cu + dvl0 + '
'cd4 + cd4_sq + cd4_cu + dvl + enter + enter_sq + enter_cu')
mcgf.exposure_model(exp_m, print_results=False, restriction="g['lag_art']==0"
) # Restricts to only untreated (for ITT assumption)
# Pooled Logistic Model: Outcome
out_m = (
'art + male + age0 + age_rs0 + age_rs1 + age_rs2 + cd40 + cd40_sq + cd40_cu + dvl0 + '
'cd4 + cd4_sq + cd4_cu + dvl + enter + enter_sq + enter_cu')
mcgf.outcome_model(
out_m, print_results=False,
restriction="g['drop']==0") # Restricting to only uncensored individuals
# Pooled Logistic Model: Detectable viral load
dvl_m = (
'male + age0 + age_rs0 + age_rs1 + age_rs2 + cd40 + cd40_sq + cd40_cu + dvl0 + '
'lag_cd4 + lag_dvl + lag_art + enter + enter_sq + enter_cu')
mcgf.add_covariate_model(
label=1, # Order to fit time-varying models in
covariate='dvl', # Time-varying confounder
print_results=False,