def fit(self, X, treatment, y):
"""Fit the inference model
Args:
X (np.matrix or np.array or pd.Dataframe): a feature matrix
treatment (np.array or pd.Series): a treatment vector
y (np.array or pd.Series): an outcome vector
"""
X, treatment, y = convert_pd_to_np(X, treatment, y)
check_treatment_vector(treatment, self.control_name)
self.t_groups = np.unique(treatment[treatment != self.control_name])
self.t_groups.sort()
self._classes = {group: i for i, group in enumerate(self.t_groups)}
self.models_c = {group: deepcopy(self.model_c) for group in self.t_groups}
self.models_t = {group: deepcopy(self.model_t) for group in self.t_groups}
for group in self.t_groups:
mask = (treatment == group) | (treatment == self.control_name)
treatment_filt = treatment[mask]
X_filt = X[mask]
y_filt = y[mask]
w = (treatment_filt == group).astype(int)
self.models_c[group].fit(X_filt[w == 0], y_filt[w == 0])
self.models_t[group].fit(X_filt[w == 1], y_filt[w == 1])
def fit(self, X, p, treatment, y, verbose=True):
"""Fit the treatment effect and outcome models of the R learner.
Args:
X (np.matrix or np.array or pd.Dataframe): a feature matrix
p (np.ndarray or pd.Series or dict): an array of propensity scores of float (0,1) in the single-treatment
case; or, a dictionary of treatment groups that map to propensity vectors of float (0,1)
treatment (np.array or pd.Series): a treatment vector
y (np.array or pd.Series): an outcome vector
"""
X, treatment, y = convert_pd_to_np(X, treatment, y)
check_treatment_vector(treatment, self.control_name)
self.t_groups = np.unique(treatment[treatment != self.control_name])
self.t_groups.sort()
check_p_conditions(p, self.t_groups)
if isinstance(p, (np.ndarray, pd.Series)):
treatment_name = self.t_groups[0]
p = {treatment_name: convert_pd_to_np(p)}
elif isinstance(p, dict):
p = {
treatment_name: convert_pd_to_np(_p)
for treatment_name, _p in p.items()
}
self._classes = {group: i for i, group in enumerate(self.t_groups)}
self.models_tau = {
group: deepcopy(self.model_tau)
for group in self.t_groups
}
self.vars_c = {}
self.vars_t = {}
if verbose:
logger.info('generating out-of-fold CV outcome estimates')
yhat = cross_val_predict(self.model_mu,
X,
y,
cv=self.cv,
method='predict_proba',
n_jobs=-1)[:, 1]
for group in self.t_groups:
mask = (treatment == group) | (treatment == self.control_name)
treatment_filt = treatment[mask]
X_filt = X[mask]
y_filt = y[mask]
yhat_filt = yhat[mask]
p_filt = p[group][mask]
w = (treatment_filt == group).astype(int)
if verbose:
logger.info(
'training the treatment effect model for {} with R-loss'.
format(group))
self.models_tau[group].fit(X_filt,
(y_filt - yhat_filt) / (w - p_filt),
sample_weight=(w - p_filt)**2)
self.vars_c[group] = (y_filt[w == 0] - yhat_filt[w == 0]).var()
self.vars_t[group] = (y_filt[w == 1] - yhat_filt[w == 1]).var()
def fit(self, X, treatment, y, p=None, verbose=True):
"""Fit the treatment effect and outcome models of the R learner.
Args:
X (np.matrix or np.array or pd.Dataframe): a feature matrix
treatment (np.array or pd.Series): a treatment vector
y (np.array or pd.Series): an outcome vector
p (np.ndarray or pd.Series or dict, optional): an array of propensity scores of float (0,1) in the
single-treatment case; or, a dictionary of treatment groups that map to propensity vectors of
float (0,1); if None will run ElasticNetPropensityModel() to generate the propensity scores.
verbose (bool, optional): whether to output progress logs
"""
X, treatment, y = convert_pd_to_np(X, treatment, y)
check_treatment_vector(treatment, self.control_name)
self.t_groups = np.unique(treatment[treatment != self.control_name])
self.t_groups.sort()
if p is None:
self._set_propensity_models(X=X, treatment=treatment, y=y)
p = self.propensity
else:
p = self._format_p(p, self.t_groups)
self._classes = {group: i for i, group in enumerate(self.t_groups)}
self.models_tau = {
group: deepcopy(self.model_tau)
for group in self.t_groups
}
self.vars_c = {}
self.vars_t = {}
if verbose:
logger.info('generating out-of-fold CV outcome estimates')
yhat = cross_val_predict(self.model_mu,
X,
y,
cv=self.cv,
method='predict_proba',
n_jobs=-1)[:, 1]
for group in self.t_groups:
mask = (treatment == group) | (treatment == self.control_name)
treatment_filt = treatment[mask]
X_filt = X[mask]
y_filt = y[mask]
yhat_filt = yhat[mask]
p_filt = p[group][mask]
w = (treatment_filt == group).astype(int)
if verbose:
logger.info(
'training the treatment effect model for {} with R-loss'.
format(group))
self.models_tau[group].fit(X_filt,
(y_filt - yhat_filt) / (w - p_filt),
sample_weight=(w - p_filt)**2)
self.vars_c[group] = (y_filt[w == 0] - yhat_filt[w == 0]).var()
self.vars_t[group] = (y_filt[w == 1] - yhat_filt[w == 1]).var()
def fit(self, X, treatment, y):
"""Fit the inference model.
Args:
X (np.matrix or np.array or pd.Dataframe): a feature matrix
treatment (np.array or pd.Series): a treatment vector
y (np.array or pd.Series): an outcome vector
"""
X, treatment, y = convert_pd_to_np(X, treatment, y)
check_treatment_vector(treatment, self.control_name)
self.t_groups = np.unique(treatment[treatment != self.control_name])
self.t_groups.sort()
self._classes = {group: i for i, group in enumerate(self.t_groups)}
self.models_mu_c = {
group: deepcopy(self.model_mu_c)
for group in self.t_groups
}
self.models_mu_t = {
group: deepcopy(self.model_mu_t)
for group in self.t_groups
}
self.models_tau_c = {
group: deepcopy(self.model_tau_c)
for group in self.t_groups
}
self.models_tau_t = {
group: deepcopy(self.model_tau_t)
for group in self.t_groups
}
self.vars_c = {}
self.vars_t = {}
for group in self.t_groups:
mask = (treatment == group) | (treatment == self.control_name)
treatment_filt = treatment[mask]
X_filt = X[mask]
y_filt = y[mask]
w = (treatment_filt == group).astype(int)
# Train outcome models
self.models_mu_c[group].fit(X_filt[w == 0], y_filt[w == 0])
self.models_mu_t[group].fit(X_filt[w == 1], y_filt[w == 1])
# Calculate variances and treatment effects
var_c = (y_filt[w == 0] -
self.models_mu_c[group].predict(X_filt[w == 0])).var()
self.vars_c[group] = var_c
var_t = (y_filt[w == 1] -
self.models_mu_t[group].predict(X_filt[w == 1])).var()
self.vars_t[group] = var_t
# Train treatment models
d_c = self.models_mu_t[group].predict(
X_filt[w == 0]) - y_filt[w == 0]
d_t = y_filt[w == 1] - self.models_mu_c[group].predict(
X_filt[w == 1])
self.models_tau_c[group].fit(X_filt[w == 0], d_c)
self.models_tau_t[group].fit(X_filt[w == 1], d_t)
def fit(self, X, treatment, y):
"""Fit the inference model
Args:
X (np.matrix, np.array, or pd.Dataframe): a feature matrix
treatment (np.array or pd.Series): a treatment vector
y (np.array or pd.Series): an outcome vector
"""
X, treatment, y = convert_pd_to_np(X, treatment, y)
check_treatment_vector(treatment, self.control_name)
self.t_groups = np.unique(treatment[treatment != self.control_name])
self.t_groups.sort()
self._classes = {group: i for i, group in enumerate(self.t_groups)}
self.models = {group: deepcopy(self.model) for group in self.t_groups}
for group in self.t_groups:
mask = (treatment == group) | (treatment == self.control_name)
treatment_filt = treatment[mask]
X_filt = X[mask]
y_filt = y[mask]
w = (treatment_filt == group).astype(int)
X_new = np.hstack((w.reshape((-1, 1)), X_filt))
self.models[group].fit(X_new, y_filt)
def fit(self, X, treatment, y, p=None):
"""Fit the inference model.
Args:
X (np.matrix or np.array or pd.Dataframe): a feature matrix
treatment (np.array or pd.Series): a treatment vector
y (np.array or pd.Series): an outcome vector
p (np.ndarray or pd.Series or dict, optional): an array of propensity scores of float (0,1) in the
single-treatment case; or, a dictionary of treatment groups that map to propensity vectors of
float (0,1); if None will run ElasticNetPropensityModel() to generate the propensity scores.
"""
X, treatment, y = convert_pd_to_np(X, treatment, y)
check_treatment_vector(treatment, self.control_name)
self.t_groups = np.unique(treatment[treatment != self.control_name])
self.t_groups.sort()
if p is None:
logger.info('Generating propensity score')
p = dict()
p_model = dict()
for group in self.t_groups:
mask = (treatment == group) | (treatment == self.control_name)
treatment_filt = treatment[mask]
X_filt = X[mask]
w_filt = (treatment_filt == group).astype(int)
w = (treatment == group).astype(int)
p[group], p_model[group] = compute_propensity_score(
X=X_filt, treatment=w_filt, X_pred=X, treatment_pred=w)
self.propensity_model = p_model
self.propensity = p
else:
check_p_conditions(p, self.t_groups)
if isinstance(p, (np.ndarray, pd.Series)):
treatment_name = self.t_groups[0]
p = {treatment_name: convert_pd_to_np(p)}
elif isinstance(p, dict):
p = {
treatment_name: convert_pd_to_np(_p)
for treatment_name, _p in p.items()
}
self._classes = {group: i for i, group in enumerate(self.t_groups)}
self.models_mu_c = {
group: deepcopy(self.model_mu_c)
for group in self.t_groups
}
self.models_mu_t = {
group: deepcopy(self.model_mu_t)
for group in self.t_groups
}
self.models_tau_c = {
group: deepcopy(self.model_tau_c)
for group in self.t_groups
}
self.models_tau_t = {
group: deepcopy(self.model_tau_t)
for group in self.t_groups
}
self.vars_c = {}
self.vars_t = {}
for group in self.t_groups:
mask = (treatment == group) | (treatment == self.control_name)
treatment_filt = treatment[mask]
X_filt = X[mask]
y_filt = y[mask]
w = (treatment_filt == group).astype(int)
# Train outcome models
self.models_mu_c[group].fit(X_filt[w == 0], y_filt[w == 0])
self.models_mu_t[group].fit(X_filt[w == 1], y_filt[w == 1])
# Calculate variances and treatment effects
var_c = (y_filt[w == 0] -
self.models_mu_c[group].predict(X_filt[w == 0])).var()
self.vars_c[group] = var_c
var_t = (y_filt[w == 1] -
self.models_mu_t[group].predict(X_filt[w == 1])).var()
self.vars_t[group] = var_t
# Train treatment models
d_c = self.models_mu_t[group].predict(
X_filt[w == 0]) - y_filt[w == 0]
d_t = y_filt[w == 1] - self.models_mu_c[group].predict(
X_filt[w == 1])
self.models_tau_c[group].fit(X_filt[w == 0], d_c)
self.models_tau_t[group].fit(X_filt[w == 1], d_t)
def fit(self, X, p, treatment, y, verbose=True):
"""Fit the treatment effect and outcome models of the R learner.
Args:
X (np.matrix or np.array or pd.Dataframe): a feature matrix
p (np.ndarray or pd.Series or dict): an array of propensity scores of float (0,1) in the single-treatment
case; or, a dictionary of treatment groups that map to propensity vectors of float (0,1)
treatment (np.array or pd.Series): a treatment vector
y (np.array or pd.Series): an outcome vector
"""
check_treatment_vector(treatment, self.control_name)
X, treatment, y = convert_pd_to_np(X, treatment, y)
self.t_groups = np.unique(treatment[treatment != self.control_name])
self.t_groups.sort()
check_p_conditions(p, self.t_groups)
if isinstance(p, np.ndarray):
treatment_name = self.t_groups[0]
p = {treatment_name: convert_pd_to_np(p)}
elif isinstance(p, dict):
p = {treatment_name: convert_pd_to_np(_p) for treatment_name, _p in p.items()}
self._classes = {group: i for i, group in enumerate(self.t_groups)}
self.models_tau = {group: deepcopy(self.model_tau) for group in self.t_groups}
self.vars_c = {}
self.vars_t = {}
if verbose:
logger.info('generating out-of-fold CV outcome estimates')
yhat = cross_val_predict(self.model_mu, X, y, cv=self.cv, n_jobs=-1)
for group in self.t_groups:
treatment_mask = (treatment == group) | (treatment == self.control_name)
treatment_filt = treatment[treatment_mask]
w = (treatment_filt == group).astype(int)
X_filt = X[treatment_mask]
y_filt = y[treatment_mask]
yhat_filt = yhat[treatment_mask]
p_filt = p[group][treatment_mask]
if verbose:
logger.info('training the treatment effect model for {} with R-loss'.format(group))
if self.early_stopping:
X_train_filt, X_test_filt, y_train_filt, y_test_filt, yhat_train_filt, yhat_test_filt, \
w_train, w_test, p_train_filt, p_test_filt = train_test_split(
X_filt, y_filt, yhat_filt, w, p_filt,
test_size=self.test_size, random_state=self.random_state
)
self.models_tau[group].fit(X=X_train_filt,
y=(y_train_filt - yhat_train_filt) / (w_train - p_train_filt),
sample_weight=(w_train - p_train_filt) ** 2,
eval_set=[(X_test_filt,
(y_test_filt - yhat_test_filt) / (w_test - p_test_filt))],
sample_weight_eval_set=[(w_test - p_test_filt) ** 2],
eval_metric=self.effect_learner_eval_metric,
early_stopping_rounds=self.early_stopping_rounds,
verbose=verbose)
else:
self.models_tau[group].fit(X_filt, (y_filt - yhat_filt) / (w - p_filt),
sample_weight=(w - p_filt) ** 2,
eval_metric=self.effect_learner_eval_metric)
self.vars_c[group] = (y_filt[w == 0] - yhat_filt[w == 0]).var()
self.vars_t[group] = (y_filt[w == 1] - yhat_filt[w == 1]).var()
def fit(self, X, treatment, y, p=None, seed=None):
"""Fit the inference model.
Args:
X (np.matrix or np.array or pd.Dataframe): a feature matrix
treatment (np.array or pd.Series): a treatment vector
y (np.array or pd.Series): an outcome vector
p (np.ndarray or pd.Series or dict, optional): an array of propensity scores of float (0,1) in the
single-treatment case; or, a dictionary of treatment groups that map to propensity vectors of
float (0,1); if None will run ElasticNetPropensityModel() to generate the propensity scores.
seed (int): random seed for cross-fitting
"""
X, treatment, y = convert_pd_to_np(X, treatment, y)
check_treatment_vector(treatment, self.control_name)
self.t_groups = np.unique(treatment[treatment != self.control_name])
self.t_groups.sort()
self._classes = {group: i for i, group in enumerate(self.t_groups)}
# The estimator splits the data into 3 partitions for cross-fit on the propensity score estimation,
# the outcome regression, and the treatment regression on the doubly robust estimates. The use of
# the partitions is rotated so we do not lose on the sample size.
cv = KFold(n_splits=3, shuffle=True, random_state=seed)
split_indices = [index for _, index in cv.split(y)]
self.models_mu_c = [
deepcopy(self.model_mu_c),
deepcopy(self.model_mu_c),
deepcopy(self.model_mu_c),
]
self.models_mu_t = {
group: [
deepcopy(self.model_mu_t),
deepcopy(self.model_mu_t),
deepcopy(self.model_mu_t),
]
for group in self.t_groups
}
self.models_tau = {
group: [
deepcopy(self.model_tau),
deepcopy(self.model_tau),
deepcopy(self.model_tau),
]
for group in self.t_groups
}
if p is None:
self.propensity = {
group: np.zeros(y.shape[0])
for group in self.t_groups
}
for ifold in range(3):
treatment_idx = split_indices[ifold]
outcome_idx = split_indices[(ifold + 1) % 3]
tau_idx = split_indices[(ifold + 2) % 3]
treatment_treat, treatment_out, treatment_tau = (
treatment[treatment_idx],
treatment[outcome_idx],
treatment[tau_idx],
)
y_out, y_tau = y[outcome_idx], y[tau_idx]
X_treat, X_out, X_tau = X[treatment_idx], X[outcome_idx], X[
tau_idx]
if p is None:
logger.info("Generating propensity score")
cur_p = dict()
for group in self.t_groups:
mask = (treatment_treat == group) | (treatment_treat
== self.control_name)
treatment_filt = treatment_treat[mask]
X_filt = X_treat[mask]
w_filt = (treatment_filt == group).astype(int)
w = (treatment_tau == group).astype(int)
cur_p[group], _ = compute_propensity_score(
X=X_filt,
treatment=w_filt,
X_pred=X_tau,
treatment_pred=w)
self.propensity[group][tau_idx] = cur_p[group]
else:
cur_p = dict()
if isinstance(p, (np.ndarray, pd.Series)):
cur_p = {self.t_groups[0]: convert_pd_to_np(p[tau_idx])}
else:
cur_p = {g: prop[tau_idx] for g, prop in p.items()}
check_p_conditions(cur_p, self.t_groups)
logger.info("Generate outcome regressions")
self.models_mu_c[ifold].fit(
X_out[treatment_out == self.control_name],
y_out[treatment_out == self.control_name],
)
for group in self.t_groups:
self.models_mu_t[group][ifold].fit(
X_out[treatment_out == group],
y_out[treatment_out == group])
logger.info("Fit pseudo outcomes from the DR formula")
for group in self.t_groups:
mask = (treatment_tau == group) | (treatment_tau
== self.control_name)
treatment_filt = treatment_tau[mask]
X_filt = X_tau[mask]
y_filt = y_tau[mask]
w_filt = (treatment_filt == group).astype(int)
p_filt = cur_p[group][mask]
mu_t = self.models_mu_t[group][ifold].predict(X_filt)
mu_c = self.models_mu_c[ifold].predict(X_filt)
dr = ((w_filt - p_filt) / p_filt / (1 - p_filt) *
(y_filt - mu_t * w_filt - mu_c *
(1 - w_filt)) + mu_t - mu_c)
self.models_tau[group][ifold].fit(X_filt, dr)
def fit(
self, X, assignment, treatment, y, p=None, pZ=None, seed=None, calibrate=True
):
"""Fit the inference model.
Args:
X (np.matrix or np.array or pd.Dataframe): a feature matrix
assignment (np.array or pd.Series): a (0,1)-valued assignment vector. The assignment is the
instrumental variable that does not depend on unknown confounders. The assignment status
influences treatment in a monotonic way, i.e. one can only be more likely to take the
treatment if assigned.
treatment (np.array or pd.Series): a treatment vector
y (np.array or pd.Series): an outcome vector
p (2-tuple of np.ndarray or pd.Series or dict, optional): The first (second) element corresponds to
unassigned (assigned) units. Each is an array of propensity scores of float (0,1) in the single-treatment
case; or, a dictionary of treatment groups that map to propensity vectors of float (0,1). If None will run
ElasticNetPropensityModel() to generate the propensity scores.
pZ (np.array or pd.Series, optional): an array of assignment probability of float (0,1); if None
will run ElasticNetPropensityModel() to generate the assignment probability score.
seed (int): random seed for cross-fitting
"""
X, treatment, assignment, y = convert_pd_to_np(X, treatment, assignment, y)
check_treatment_vector(treatment, self.control_name)
self.t_groups = np.unique(treatment[treatment != self.control_name])
self.t_groups.sort()
self._classes = {group: i for i, group in enumerate(self.t_groups)}
# The estimator splits the data into 3 partitions for cross-fit on the propensity score estimation,
# the outcome regression, and the treatment regression on the doubly robust estimates. The use of
# the partitions is rotated so we do not lose on the sample size. We do not cross-fit the assignment
# score estimation as the assignment process is usually simple.
cv = KFold(n_splits=3, shuffle=True, random_state=seed)
split_indices = [index for _, index in cv.split(y)]
self.models_mu_c = {
group: [
deepcopy(self.model_mu_c),
deepcopy(self.model_mu_c),
deepcopy(self.model_mu_c),
]
for group in self.t_groups
}
self.models_mu_t = {
group: [
deepcopy(self.model_mu_t),
deepcopy(self.model_mu_t),
deepcopy(self.model_mu_t),
]
for group in self.t_groups
}
self.models_tau = {
group: [
deepcopy(self.model_tau),
deepcopy(self.model_tau),
deepcopy(self.model_tau),
]
for group in self.t_groups
}
if p is None:
self.propensity_1 = {
group: np.zeros(y.shape[0]) for group in self.t_groups
} # propensity scores for those assigned
self.propensity_0 = {
group: np.zeros(y.shape[0]) for group in self.t_groups
} # propensity scores for those not assigned
if pZ is None:
self.propensity_assign, _ = compute_propensity_score(
X=X,
treatment=assignment,
X_pred=X,
treatment_pred=assignment,
calibrate_p=calibrate,
)
else:
self.propensity_assign = pZ
for ifold in range(3):
treatment_idx = split_indices[ifold]
outcome_idx = split_indices[(ifold + 1) % 3]
tau_idx = split_indices[(ifold + 2) % 3]
treatment_treat, treatment_out, treatment_tau = (
treatment[treatment_idx],
treatment[outcome_idx],
treatment[tau_idx],
)
assignment_treat, assignment_out, assignment_tau = (
assignment[treatment_idx],
assignment[outcome_idx],
assignment[tau_idx],
)
y_out, y_tau = y[outcome_idx], y[tau_idx]
X_treat, X_out, X_tau = X[treatment_idx], X[outcome_idx], X[tau_idx]
pZ_tau = self.propensity_assign[tau_idx]
if p is None:
logger.info("Generating propensity score")
cur_p_1 = dict()
cur_p_0 = dict()
for group in self.t_groups:
mask = (treatment_treat == group) | (
treatment_treat == self.control_name
)
mask_1, mask_0 = mask & (assignment_treat == 1), mask & (
assignment_treat == 0
)
cur_p_1[group], _ = compute_propensity_score(
X=X_treat[mask_1],
treatment=(treatment_treat[mask_1] == group).astype(int),
X_pred=X_tau,
treatment_pred=(treatment_tau == group).astype(int),
)
if (treatment_treat[mask_0] == group).sum() == 0:
cur_p_0[group] = np.zeros(X_tau.shape[0])
else:
cur_p_0[group], _ = compute_propensity_score(
X=X_treat[mask_0],
treatment=(treatment_treat[mask_0] == group).astype(int),
X_pred=X_tau,
treatment_pred=(treatment_tau == group).astype(int),
)
self.propensity_1[group][tau_idx] = cur_p_1[group]
self.propensity_0[group][tau_idx] = cur_p_0[group]
else:
cur_p_1 = dict()
cur_p_0 = dict()
if isinstance(p[0], (np.ndarray, pd.Series)):
cur_p_0 = {self.t_groups[0]: convert_pd_to_np(p[0][tau_idx])}
else:
cur_p_0 = {g: prop[tau_idx] for g, prop in p[0].items()}
check_p_conditions(cur_p_0, self.t_groups)
if isinstance(p[1], (np.ndarray, pd.Series)):
cur_p_1 = {self.t_groups[0]: convert_pd_to_np(p[1][tau_idx])}
else:
cur_p_1 = {g: prop[tau_idx] for g, prop in p[1].items()}
check_p_conditions(cur_p_1, self.t_groups)
logger.info("Generate outcome regressions")
for group in self.t_groups:
mask = (treatment_out == group) | (treatment_out == self.control_name)
mask_1, mask_0 = mask & (assignment_out == 1), mask & (
assignment_out == 0
)
self.models_mu_c[group][ifold].fit(X_out[mask_0], y_out[mask_0])
self.models_mu_t[group][ifold].fit(X_out[mask_1], y_out[mask_1])
logger.info("Fit pseudo outcomes from the DR formula")
for group in self.t_groups:
mask = (treatment_tau == group) | (treatment_tau == self.control_name)
treatment_filt = treatment_tau[mask]
X_filt = X_tau[mask]
y_filt = y_tau[mask]
w_filt = (treatment_filt == group).astype(int)
p_1_filt = cur_p_1[group][mask]
p_0_filt = cur_p_0[group][mask]
z_filt = assignment_tau[mask]
pZ_filt = pZ_tau[mask]
mu_t = self.models_mu_t[group][ifold].predict(X_filt)
mu_c = self.models_mu_c[group][ifold].predict(X_filt)
dr = (
z_filt * (y_filt - mu_t) / pZ_filt
- (1 - z_filt) * (y_filt - mu_c) / (1 - pZ_filt)
+ mu_t
- mu_c
)
weight = (
z_filt * (w_filt - p_1_filt) / pZ_filt
- (1 - z_filt) * (w_filt - p_0_filt) / (1 - pZ_filt)
+ p_1_filt
- p_0_filt
)
dr /= weight
self.models_tau[group][ifold].fit(X_filt, dr, sample_weight=weight**2)
def fit(self, X, treatment, y, p=None, sample_weight=None, verbose=True):
"""Fit the treatment effect and outcome models of the R learner.
Args:
X (np.matrix or np.array or pd.Dataframe): a feature matrix
treatment (np.array or pd.Series): a treatment vector
y (np.array or pd.Series): an outcome vector
p (np.ndarray or pd.Series or dict, optional): an array of propensity scores of float (0,1) in the
single-treatment case; or, a dictionary of treatment groups that map to propensity vectors of
float (0,1); if None will run ElasticNetPropensityModel() to generate the propensity scores.
sample_weight (np.array or pd.Series, optional): an array of sample weights indicating the
weight of each observation for `effect_learner`. If None, it assumes equal weight.
verbose (bool, optional): whether to output progress logs
"""
X, treatment, y = convert_pd_to_np(X, treatment, y)
check_treatment_vector(treatment, self.control_name)
if sample_weight is not None:
assert len(sample_weight) == len(
y
), "Data length must be equal for sample_weight and the input data"
sample_weight = convert_pd_to_np(sample_weight)
self.t_groups = np.unique(treatment[treatment != self.control_name])
self.t_groups.sort()
if p is None:
self._set_propensity_models(X=X, treatment=treatment, y=y)
p = self.propensity
else:
p = self._format_p(p, self.t_groups)
self._classes = {group: i for i, group in enumerate(self.t_groups)}
self.models_tau = {group: deepcopy(self.model_tau) for group in self.t_groups}
self.vars_c = {}
self.vars_t = {}
if verbose:
logger.info("generating out-of-fold CV outcome estimates")
yhat = cross_val_predict(self.model_mu, X, y, cv=self.cv, n_jobs=-1)
for group in self.t_groups:
mask = (treatment == group) | (treatment == self.control_name)
treatment_filt = treatment[mask]
X_filt = X[mask]
y_filt = y[mask]
yhat_filt = yhat[mask]
p_filt = p[group][mask]
w = (treatment_filt == group).astype(int)
weight = (w - p_filt) ** 2
diff_c = y_filt[w == 0] - yhat_filt[w == 0]
diff_t = y_filt[w == 1] - yhat_filt[w == 1]
if sample_weight is not None:
sample_weight_filt = sample_weight[mask]
sample_weight_filt_c = sample_weight_filt[w == 0]
sample_weight_filt_t = sample_weight_filt[w == 1]
self.vars_c[group] = get_weighted_variance(diff_c, sample_weight_filt_c)
self.vars_t[group] = get_weighted_variance(diff_t, sample_weight_filt_t)
weight *= sample_weight_filt # update weight
else:
self.vars_c[group] = diff_c.var()
self.vars_t[group] = diff_t.var()
if verbose:
logger.info(
"training the treatment effect model for {} with R-loss".format(
group
)
)
self.models_tau[group].fit(
X_filt, (y_filt - yhat_filt) / (w - p_filt), sample_weight=weight
)
def fit(self, X, treatment, y, p=None, sample_weight=None, verbose=True):
"""Fit the treatment effect and outcome models of the R learner.
Args:
X (np.matrix or np.array or pd.Dataframe): a feature matrix
y (np.array or pd.Series): an outcome vector
p (np.ndarray or pd.Series or dict, optional): an array of propensity scores of float (0,1) in the
single-treatment case; or, a dictionary of treatment groups that map to propensity vectors of
float (0,1); if None will run ElasticNetPropensityModel() to generate the propensity scores.
sample_weight (np.array or pd.Series, optional): an array of sample weights indicating the
weight of each observation for `effect_learner`. If None, it assumes equal weight.
verbose (bool, optional): whether to output progress logs
"""
X, treatment, y = convert_pd_to_np(X, treatment, y)
check_treatment_vector(treatment, self.control_name)
# initialize equal sample weight if it's not provided, for simplicity purpose
sample_weight = (
convert_pd_to_np(sample_weight)
if sample_weight is not None
else convert_pd_to_np(np.ones(len(y)))
)
assert len(sample_weight) == len(
y
), "Data length must be equal for sample_weight and the input data"
self.t_groups = np.unique(treatment[treatment != self.control_name])
self.t_groups.sort()
if p is None:
self._set_propensity_models(X=X, treatment=treatment, y=y)
p = self.propensity
else:
p = self._format_p(p, self.t_groups)
self._classes = {group: i for i, group in enumerate(self.t_groups)}
self.models_tau = {group: deepcopy(self.model_tau) for group in self.t_groups}
self.vars_c = {}
self.vars_t = {}
if verbose:
logger.info("generating out-of-fold CV outcome estimates")
yhat = cross_val_predict(self.model_mu, X, y, cv=self.cv, n_jobs=-1)
for group in self.t_groups:
treatment_mask = (treatment == group) | (treatment == self.control_name)
treatment_filt = treatment[treatment_mask]
w = (treatment_filt == group).astype(int)
X_filt = X[treatment_mask]
y_filt = y[treatment_mask]
yhat_filt = yhat[treatment_mask]
p_filt = p[group][treatment_mask]
sample_weight_filt = sample_weight[treatment_mask]
if verbose:
logger.info(
"training the treatment effect model for {} with R-loss".format(
group
)
)
if self.early_stopping:
(
X_train_filt,
X_test_filt,
y_train_filt,
y_test_filt,
yhat_train_filt,
yhat_test_filt,
w_train,
w_test,
p_train_filt,
p_test_filt,
sample_weight_train_filt,
sample_weight_test_filt,
) = train_test_split(
X_filt,
y_filt,
yhat_filt,
w,
p_filt,
sample_weight_filt,
test_size=self.test_size,
random_state=self.random_state,
)
weight = sample_weight_filt
self.models_tau[group].fit(
X=X_train_filt,
y=(y_train_filt - yhat_train_filt) / (w_train - p_train_filt),
sample_weight=sample_weight_train_filt
* ((w_train - p_train_filt) ** 2),
eval_set=[
(
X_test_filt,
(y_test_filt - yhat_test_filt) / (w_test - p_test_filt),
)
],
sample_weight_eval_set=[
sample_weight_test_filt * ((w_test - p_test_filt) ** 2)
],
eval_metric=self.effect_learner_eval_metric,
early_stopping_rounds=self.early_stopping_rounds,
verbose=verbose,
)
else:
self.models_tau[group].fit(
X_filt,
(y_filt - yhat_filt) / (w - p_filt),
sample_weight=sample_weight_filt * ((w - p_filt) ** 2),
eval_metric=self.effect_learner_eval_metric,
)
diff_c = y_filt[w == 0] - yhat_filt[w == 0]
diff_t = y_filt[w == 1] - yhat_filt[w == 1]
sample_weight_filt_c = sample_weight_filt[w == 0]
sample_weight_filt_t = sample_weight_filt[w == 1]
self.vars_c[group] = get_weighted_variance(diff_c, sample_weight_filt_c)
self.vars_t[group] = get_weighted_variance(diff_t, sample_weight_filt_t)
def estimate_ate(self, X, treatment, y, p, segment=None, return_ci=False):
"""Estimate the Average Treatment Effect (ATE).
Args:
X (np.matrix or np.array or pd.Dataframe): a feature matrix
treatment (np.array or pd.Series): a treatment vector
y (np.array or pd.Series): an outcome vector
p (np.ndarray or pd.Series or dict): an array of propensity scores of float (0,1) in the single-treatment
case; or, a dictionary of treatment groups that map to propensity vectors of float (0,1)
segment (np.array, optional): An optional segment vector of int. If given, the ATE and its CI will be
estimated for each segment.
return_ci (bool, optional): Whether to return confidence intervals
Returns:
(tuple): The ATE and its confidence interval (LB, UB) for each treatment, t and segment, s
"""
X, treatment, y = convert_pd_to_np(X, treatment, y)
check_treatment_vector(treatment, self.control_name)
self.t_groups = np.unique(treatment[treatment != self.control_name])
self.t_groups.sort()
check_p_conditions(p, self.t_groups)
if isinstance(p, (np.ndarray, pd.Series)):
treatment_name = self.t_groups[0]
p = {treatment_name: convert_pd_to_np(p)}
elif isinstance(p, dict):
p = {
treatment_name: convert_pd_to_np(_p)
for treatment_name, _p in p.items()
}
ate = []
ate_lb = []
ate_ub = []
for i, group in enumerate(self.t_groups):
logger.info("Estimating ATE for group {}.".format(group))
w_group = (treatment == group).astype(int)
p_group = p[group]
if self.calibrate_propensity:
logger.info("Calibrating propensity scores.")
p_group = calibrate(p_group, w_group)
yhat_c = np.zeros_like(y, dtype=float)
yhat_t = np.zeros_like(y, dtype=float)
if self.cv:
for i_fold, (i_trn,
i_val) in enumerate(self.cv.split(X, y), 1):
logger.info(
"Training an outcome model for CV #{}".format(i_fold))
self.model_tau.fit(
np.hstack((X[i_trn], w_group[i_trn].reshape(-1, 1))),
y[i_trn])
yhat_c[i_val] = self.model_tau.predict(
np.hstack((X[i_val], np.zeros((len(i_val), 1)))))
yhat_t[i_val] = self.model_tau.predict(
np.hstack((X[i_val], np.ones((len(i_val), 1)))))
else:
self.model_tau.fit(np.hstack((X, w_group.reshape(-1, 1))), y)
yhat_c = self.model_tau.predict(
np.hstack((X, np.zeros((len(y), 1)))))
yhat_t = self.model_tau.predict(
np.hstack((X, np.ones((len(y), 1)))))
if segment is None:
logger.info("Training the TMLE learner.")
_ate, se = simple_tmle(y, w_group, yhat_c, yhat_t, p_group)
_ate_lb = _ate - se * norm.ppf(1 - self.ate_alpha / 2)
_ate_ub = _ate + se * norm.ppf(1 - self.ate_alpha / 2)
else:
assert (segment.shape[0] == X.shape[0] and segment.ndim
== 1), "Segment must be the 1-d np.array of int."
segments = np.unique(segment)
_ate = []
_ate_lb = []
_ate_ub = []
for s in sorted(segments):
logger.info(
"Training the TMLE learner for segment {}.".format(s))
filt = (segment
== s) & (yhat_c < np.quantile(yhat_c, q=0.99))
_ate_s, se = simple_tmle(
y[filt],
w_group[filt],
yhat_c[filt],
yhat_t[filt],
p_group[filt],
)
_ate_lb_s = _ate_s - se * norm.ppf(1 - self.ate_alpha / 2)
_ate_ub_s = _ate_s + se * norm.ppf(1 - self.ate_alpha / 2)
_ate.append(_ate_s)
_ate_lb.append(_ate_lb_s)
_ate_ub.append(_ate_ub_s)
ate.append(_ate)
ate_lb.append(_ate_lb)
ate_ub.append(_ate_ub)
return np.array(ate), np.array(ate_lb), np.array(ate_ub)
def fit(self, X, treatment, y, p=None):
"""Fit the inference model.
Args:
X (np.matrix or np.array or pd.Dataframe): a feature matrix
treatment (np.array or pd.Series): a treatment vector
y (np.array or pd.Series): an outcome vector
p (np.ndarray or pd.Series or dict, optional): an array of propensity scores of float (0,1) in the
single-treatment case; or, a dictionary of treatment groups that map to propensity vectors of
float (0,1); if None will run ElasticNetPropensityModel() to generate the propensity scores.
"""
X, treatment, y = convert_pd_to_np(X, treatment, y)
check_treatment_vector(treatment, self.control_name)
self.t_groups = np.unique(treatment[treatment != self.control_name])
self.t_groups.sort()
if p is None:
self._set_propensity_models(X=X, treatment=treatment, y=y)
p = self.propensity
else:
p = self._format_p(p, self.t_groups)
self._classes = {group: i for i, group in enumerate(self.t_groups)}
self.models_mu_c = {
group: deepcopy(self.model_mu_c)
for group in self.t_groups
}
self.models_mu_t = {
group: deepcopy(self.model_mu_t)
for group in self.t_groups
}
self.models_tau_c = {
group: deepcopy(self.model_tau_c)
for group in self.t_groups
}
self.models_tau_t = {
group: deepcopy(self.model_tau_t)
for group in self.t_groups
}
self.vars_c = {}
self.vars_t = {}
for group in self.t_groups:
mask = (treatment == group) | (treatment == self.control_name)
treatment_filt = treatment[mask]
X_filt = X[mask]
y_filt = y[mask]
w = (treatment_filt == group).astype(int)
# Train outcome models
self.models_mu_c[group].fit(X_filt[w == 0], y_filt[w == 0])
self.models_mu_t[group].fit(X_filt[w == 1], y_filt[w == 1])
# Calculate variances and treatment effects
var_c = (y_filt[w == 0] -
self.models_mu_c[group].predict(X_filt[w == 0])).var()
self.vars_c[group] = var_c
var_t = (y_filt[w == 1] -
self.models_mu_t[group].predict(X_filt[w == 1])).var()
self.vars_t[group] = var_t
# Train treatment models
d_c = self.models_mu_t[group].predict(
X_filt[w == 0]) - y_filt[w == 0]
d_t = y_filt[w == 1] - self.models_mu_c[group].predict(
X_filt[w == 1])
self.models_tau_c[group].fit(X_filt[w == 0], d_c)
self.models_tau_t[group].fit(X_filt[w == 1], d_t)