def fit_predict()

in causalml/inference/meta/xlearner.py [0:0]

• 36 lines of code
• 7 McCabe index (conditional complexity)

    def fit_predict(self, X, treatment, y, p=None, return_ci=False, n_bootstraps=1000, bootstrap_size=10000,
                    return_components=False, verbose=True):
        """Fit the treatment effect and outcome models of the R learner and predict treatment effects.

        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.
            return_ci (bool): whether to return confidence intervals
            n_bootstraps (int): number of bootstrap iterations
            bootstrap_size (int): number of samples per bootstrap
            return_components (bool, optional): whether to return outcome for treatment and control seperately
            verbose (str): whether to output progress logs
        Returns:
            (numpy.ndarray): Predictions of treatment effects. Output dim: [n_samples, n_treatment]
                If return_ci, returns CATE [n_samples, n_treatment], LB [n_samples, n_treatment],
                UB [n_samples, n_treatment]
        """
        X, treatment, y = convert_pd_to_np(X, treatment, y)
        self.fit(X, treatment, y, p)

        if p is None:
            p = self.propensity

        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()}

        te = self.predict(X, treatment=treatment, y=y, p=p, return_components=return_components)

        if not return_ci:
            return te
        else:
            t_groups_global = self.t_groups
            _classes_global = self._classes
            models_mu_c_global = deepcopy(self.models_mu_c)
            models_mu_t_global = deepcopy(self.models_mu_t)
            models_tau_c_global = deepcopy(self.models_tau_c)
            models_tau_t_global = deepcopy(self.models_tau_t)
            te_bootstraps = np.zeros(shape=(X.shape[0], self.t_groups.shape[0], n_bootstraps))

            logger.info('Bootstrap Confidence Intervals')
            for i in tqdm(range(n_bootstraps)):
                te_b = self.bootstrap(X, treatment, y, p, size=bootstrap_size)
                te_bootstraps[:, :, i] = te_b

            te_lower = np.percentile(te_bootstraps, (self.ate_alpha / 2) * 100, axis=2)
            te_upper = np.percentile(te_bootstraps, (1 - self.ate_alpha / 2) * 100, axis=2)

            # set member variables back to global (currently last bootstrapped outcome)
            self.t_groups = t_groups_global
            self._classes = _classes_global
            self.models_mu_c = deepcopy(models_mu_c_global)
            self.models_mu_t = deepcopy(models_mu_t_global)
            self.models_tau_c = deepcopy(models_tau_c_global)
            self.models_tau_t = deepcopy(models_tau_t_global)

            return (te, te_lower, te_upper)