in dowhy/causal_estimator.py [0:0]
def __init__(self, data, identified_estimand, treatment, outcome,
control_value=0, treatment_value=1,
test_significance=False, evaluate_effect_strength=False,
confidence_intervals=False,
target_units=None, effect_modifiers=None,
params=None):
"""Initializes an estimator with data and names of relevant variables.
This method is called from the constructors of its child classes.
:param data: data frame containing the data
:param identified_estimand: probability expression
representing the target identified estimand to estimate.
:param treatment: name of the treatment variable
:param outcome: name of the outcome variable
:param control_value: Value of the treatment in the control group, for effect estimation. If treatment is multi-variate, this can be a list.
:param treatment_value: Value of the treatment in the treated group, for effect estimation. If treatment is multi-variate, this can be a list.
:param test_significance: Binary flag or a string indicating whether to test significance and by which method. All estimators support test_significance="bootstrap" that estimates a p-value for the obtained estimate using the bootstrap method. Individual estimators can override this to support custom testing methods. The bootstrap method supports an optional parameter, num_null_simulations that can be specified through the params dictionary. If False, no testing is done. If True, significance of the estimate is tested using the custom method if available, otherwise by bootstrap.
:param evaluate_effect_strength: (Experimental) whether to evaluate the strength of effect
:param confidence_intervals: Binary flag or a string indicating whether the confidence intervals should be computed and which method should be used. All methods support estimation of confidence intervals using the bootstrap method by using the parameter confidence_intervals="bootstrap". The bootstrap method takes in two arguments (num_simulations and sample_size_fraction) that can be optionally specified in the params dictionary. Estimators may also override this to implement their own confidence interval method. If this parameter is False, no confidence intervals are computed. If True, confidence intervals are computed by the estimator's specific method if available, otherwise through bootstrap.
:param target_units: The units for which the treatment effect should be estimated. This can be a string for common specifications of target units (namely, "ate", "att" and "atc"). It can also be a lambda function that can be used as an index for the data (pandas DataFrame). Alternatively, it can be a new DataFrame that contains values of the effect_modifiers and effect will be estimated only for this new data.
:param effect_modifiers: Variables on which to compute separate effects, or return a heterogeneous effect function. Not all methods support this currently.
:param params: (optional) Additional method parameters
num_null_simulations: The number of simulations for testing the statistical significance of the estimator
num_simulations: The number of simulations for finding the confidence interval (and/or standard error) for a estimate
sample_size_fraction: The size of the sample for the bootstrap estimator
confidence_level: The confidence level of the confidence interval estimate
num_quantiles_to_discretize_cont_cols: The number of quantiles into which a numeric effect modifier is split, to enable estimation of conditional treatment effect over it.
:returns: an instance of the estimator class.
"""
self._data = data
self._target_estimand = identified_estimand
# Currently estimation methods only support univariate treatment and outcome
self._treatment_name = treatment
self._outcome_name = outcome[0] # assuming one-dimensional outcome
self._control_value = control_value
self._treatment_value = treatment_value
self._significance_test = test_significance
self._effect_strength_eval = evaluate_effect_strength
self._target_units = target_units
self._effect_modifier_names = effect_modifiers
self._confidence_intervals = confidence_intervals
self._bootstrap_estimates = None # for confidence intervals and std error
self._bootstrap_null_estimates = None # for significance test
self._effect_modifiers = None
self.method_params = params
# Setting the default interpret method
self.interpret_method = CausalEstimator.DEFAULT_INTERPRET_METHOD
# Unpacking the keyword arguments
if params is not None:
for key, value in params.items():
setattr(self, key, value)
self.logger = logging.getLogger(__name__)
# Setting treatment and outcome values
if self._data is not None:
self._treatment = self._data[self._treatment_name]
self._outcome = self._data[self._outcome_name]
# Now saving the effect modifiers
if self._effect_modifier_names:
# only add the observed nodes
self._effect_modifier_names = [cname
for cname in self._effect_modifier_names
if cname in self._data.columns]
if len(self._effect_modifier_names) > 0:
self._effect_modifiers = self._data[self._effect_modifier_names]
self._effect_modifiers = pd.get_dummies(self._effect_modifiers, drop_first=True)
self.logger.debug("Effect modifiers: " +
",".join(self._effect_modifier_names))
else:
self._effect_modifier_names = None
# Checking if some parameters were set, otherwise setting to default values
if not hasattr(self, 'num_null_simulations'):
self.num_null_simulations = CausalEstimator.DEFAULT_NUMBER_OF_SIMULATIONS_STAT_TEST
if not hasattr(self, 'num_simulations'):
self.num_simulations = CausalEstimator.DEFAULT_NUMBER_OF_SIMULATIONS_CI
if not hasattr(self, 'sample_size_fraction'):
self.sample_size_fraction = CausalEstimator.DEFAULT_SAMPLE_SIZE_FRACTION
if not hasattr(self, 'confidence_level'):
self.confidence_level = CausalEstimator.DEFAULT_CONFIDENCE_LEVEL
if not hasattr(self, 'num_quantiles_to_discretize_cont_cols'):
self.num_quantiles_to_discretize_cont_cols = CausalEstimator.NUM_QUANTILES_TO_DISCRETIZE_CONT_COLS
# Estimate conditional estimates by default
if not hasattr(self, 'need_conditional_estimates'):
self.need_conditional_estimates = bool(self._effect_modifier_names)