econml.dr.DRLearner
- class econml.dr.DRLearner(*, model_propensity='auto', model_regression='auto', model_final=StatsModelsLinearRegression(), multitask_model_final=False, featurizer=None, min_propensity=1e-06, categories='auto', cv=2, mc_iters=None, mc_agg='mean', random_state=None, allow_missing=False, use_ray=False, ray_remote_func_options=None)[source]
Bases:
econml._ortho_learner._OrthoLearner
CATE estimator that uses doubly-robust correction techniques to account for covariate shift (selection bias) between the treatment arms. The estimator is a special case of an
_OrthoLearner
estimator, so it follows the two stage process, where a set of nuisance functions are estimated in the first stage in a crossfitting manner and a final stage estimates the CATE model. See the documentation of_OrthoLearner
for a description of this two stage process.In this estimator, the CATE is estimated by using the following estimating equations. If we let:
\[Y_{i, t}^{DR} = E[Y | X_i, W_i, T_i=t] + \frac{Y_i - E[Y | X_i, W_i, T_i=t]}{Pr[T_i=t | X_i, W_i]} \cdot 1\{T_i=t\}\]Then the following estimating equation holds:
\[E\left[Y_{i, t}^{DR} - Y_{i, 0}^{DR} | X_i\right] = \theta_t(X_i)\]Thus if we estimate the nuisance functions \(h(X, W, T) = E[Y | X, W, T]\) and \(p_t(X, W)=Pr[T=t | X, W]\) in the first stage, we can estimate the final stage cate for each treatment t, by running a regression, regressing \(Y_{i, t}^{DR} - Y_{i, 0}^{DR}\) on \(X_i\).
The problem of estimating the nuisance function \(p\) is a simple multi-class classification problem of predicting the label \(T\) from \(X, W\). The
DRLearner
class takes as input the parametermodel_propensity
, which is an arbitrary scikit-learn classifier, that is internally used to solve this classification problem.The second nuisance function \(h\) is a simple regression problem and the
DRLearner
class takes as input the parametermodel_regressor
, which is an arbitrary scikit-learn regressor that is internally used to solve this regression problem.The final stage is multi-task regression problem with outcomes the labels \(Y_{i, t}^{DR} - Y_{i, 0}^{DR}\) for each non-baseline treatment t. The
DRLearner
takes as input parametermodel_final
, which is any scikit-learn regressor that is internally used to solve this multi-task regresion problem. If the parametermultitask_model_final
is False, then this model is assumed to be a mono-task regressor, and separate clones of it are used to solve each regression target separately.- Parameters
model_propensity (scikit-learn classifier or ‘auto’, default ‘auto’) – Estimator for Pr[T=t | X, W]. Trained by regressing treatments on (features, controls) concatenated. Must implement fit and predict_proba methods. The fit method must be able to accept X and T, where T is a shape (n, ) array. If ‘auto’,
LogisticRegressionCV
will be chosen.model_regression (scikit-learn regressor or ‘auto’, default ‘auto’) – Estimator for E[Y | X, W, T]. Trained by regressing Y on (features, controls, one-hot-encoded treatments) concatenated. The one-hot-encoding excludes the baseline treatment. Must implement fit and predict methods. If different models per treatment arm are desired, see the
MultiModelWrapper
helper class. If ‘auto’WeightedLassoCV
/WeightedMultiTaskLassoCV
will be chosen.model_final – estimator for the final cate model. Trained on regressing the doubly robust potential outcomes on (features X).
If X is None, then the fit method of model_final should be able to handle X=None.
If featurizer is not None and X is not None, then it is trained on the outcome of featurizer.fit_transform(X).
If multitask_model_final is True, then this model must support multitasking and it is trained by regressing all doubly robust target outcomes on (featurized) features simultanteously.
The output of the predict(X) of the trained model will contain the CATEs for each treatment compared to baseline treatment (lexicographically smallest). If multitask_model_final is False, it is assumed to be a mono-task model and a separate clone of the model is trained for each outcome. Then predict(X) of the t-th clone will be the CATE of the t-th lexicographically ordered treatment compared to the baseline.
multitask_model_final (bool, default False) – Whether the model_final should be treated as a multi-task model. See description of model_final.
featurizer (transformer, optional) – Must support fit_transform and transform. Used to create composite features in the final CATE regression. It is ignored if X is None. The final CATE will be trained on the outcome of featurizer.fit_transform(X). If featurizer=None, then CATE is trained on X.
min_propensity (float, default
1e-6
) – The minimum propensity at which to clip propensity estimates to avoid dividing by zero.categories (‘auto’ or list, default ‘auto’) – The categories to use when encoding discrete treatments (or ‘auto’ to use the unique sorted values). The first category will be treated as the control treatment.
cv (int, cross-validation generator or an iterable, default 2) – Determines the cross-validation splitting strategy. Possible inputs for cv are:
None, to use the default 3-fold cross-validation,
integer, to specify the number of folds.
An iterable yielding (train, test) splits as arrays of indices.
For integer/None inputs, if the treatment is discrete
StratifiedKFold
is used, else,KFold
is used (with a random shuffle in either case).Unless an iterable is used, we call split(concat[W, X], T) to generate the splits. If all W, X are None, then we call split(ones((T.shape[0], 1)), T).
mc_iters (int, optional) – The number of times to rerun the first stage models to reduce the variance of the nuisances.
mc_agg ({‘mean’, ‘median’}, default ‘mean’) – How to aggregate the nuisance value for each sample across the mc_iters monte carlo iterations of cross-fitting.
random_state (int,
RandomState
instance or None) – If int, random_state is the seed used by the random number generator; IfRandomState
instance, random_state is the random number generator; If None, the random number generator is theRandomState
instance used bynp.random
.allow_missing (bool) – Whether to allow missing values in X, W. If True, will need to supply model_propensity, model_regression, and model_final that can handle missing values.
use_ray (bool, default False) – Whether to use Ray to parallelize the cross-fitting step. If True, Ray must be installed.
ray_remote_func_options (dict, default None) – Options to pass to the remote function when using Ray. See https://docs.ray.io/en/latest/ray-core/api/doc/ray.remote.html
Examples
A simple example with the default models:
from econml.dr import DRLearner np.random.seed(123) X = np.random.normal(size=(1000, 3)) T = np.random.binomial(2, scipy.special.expit(X[:, 0])) sigma = 0.001 y = (1 + .5*X[:, 0]) * T + X[:, 0] + np.random.normal(0, sigma, size=(1000,)) est = DRLearner() est.fit(y, T, X=X, W=None)
>>> est.const_marginal_effect(X[:2]) array([[0.520977..., 1.244073...], [0.365645..., 0.749762...]]) >>> est.effect(X[:2], T0=0, T1=1) array([0.520977..., 0.365645...]) >>> est.score_ 3.15958089... >>> est.score(y, T, X=X) 2.60965712... >>> est.model_cate(T=1).coef_ array([0.369069..., 0.016610..., 0.019072...]) >>> est.model_cate(T=2).coef_ array([ 0.768336..., 0.082106..., -0.030475...]) >>> est.cate_feature_names() ['X0', 'X1', 'X2'] >>> [mdl.coef_ for mdls in est.models_regression for mdl in mdls] [array([ 1.463..., 0.006..., -0.006..., 0.726..., 2.029...]), array([ 1.466..., -0.002..., 0..., 0.646..., 2.014...])] >>> [mdl.coef_ for mdls in est.models_propensity for mdl in mdls] [array([[-0.67903093, 0.04261741, -0.05969718], [ 0.034..., -0.013..., -0.013...], [ 0.644..., -0.028..., 0.073...]]), array([[-0.831..., 0.100..., 0.090...], [ 0.084..., 0.013..., -0.154...], [ 0.747..., -0.113..., 0.063...]])]
Beyond default models:
from sklearn.linear_model import LassoCV from sklearn.ensemble import RandomForestClassifier, RandomForestRegressor from econml.dr import DRLearner np.random.seed(123) X = np.random.normal(size=(1000, 3)) T = np.random.binomial(2, scipy.special.expit(X[:, 0])) sigma = 0.01 y = (1 + .5*X[:, 0]) * T + X[:, 0] + np.random.normal(0, sigma, size=(1000,)) est = DRLearner(model_propensity=RandomForestClassifier(n_estimators=100, min_samples_leaf=10), model_regression=RandomForestRegressor(n_estimators=100, min_samples_leaf=10), model_final=LassoCV(cv=3), featurizer=None) est.fit(y, T, X=X, W=None)
>>> est.score_ 3.7... >>> est.const_marginal_effect(X[:3]) array([[0.64..., 1.23...], [0.49..., 0.92...], [0.20..., 0.26...]]) >>> est.model_cate(T=2).coef_ array([0.72..., 0. , 0. ]) >>> est.model_cate(T=2).intercept_ 2.0... >>> est.model_cate(T=1).coef_ array([0.31..., 0.01..., 0.00...]) >>> est.model_cate(T=1).intercept_ 0.97...
- score_
The MSE in the final doubly robust potential outcome regressions, i.e.
\[\frac{1}{n_t} \sum_{t=1}^{n_t} \frac{1}{n} \sum_{i=1}^n (Y_{i, t}^{DR} - \hat{\theta}_t(X_i))^2\]where n_t is the number of treatments (excluding control).
If sample_weight is not None at fit time, then a weighted average across samples is returned.
- Type
- __init__(*, model_propensity='auto', model_regression='auto', model_final=StatsModelsLinearRegression(), multitask_model_final=False, featurizer=None, min_propensity=1e-06, categories='auto', cv=2, mc_iters=None, mc_agg='mean', random_state=None, allow_missing=False, use_ray=False, ray_remote_func_options=None)[source]
Methods
__init__
(*[, model_propensity, ...])ate
([X, T0, T1])Calculate the average treatment effect \(E_X[\tau(X, T0, T1)]\).
ate_inference
([X, T0, T1])Inference results for the quantity \(E_X[\tau(X, T0, T1)]\) produced by the model.
ate_interval
([X, T0, T1, alpha])Confidence intervals for the quantity \(E_X[\tau(X, T0, T1)]\) produced by the model.
cate_feature_names
([feature_names])Get the output feature names.
cate_output_names
([output_names])Public interface for getting output names.
cate_treatment_names
([treatment_names])Get treatment names.
const_marginal_ate
([X])Calculate the average constant marginal CATE \(E_X[\theta(X)]\).
Inference results for the quantities \(E_X[\theta(X)]\) produced by the model.
const_marginal_ate_interval
([X, alpha])Confidence intervals for the quantities \(E_X[\theta(X)]\) produced by the model.
Calculate the constant marginal CATE \(\theta(·)\).
Inference results for the quantities \(\theta(X)\) produced by the model.
const_marginal_effect_interval
([X, alpha])Confidence intervals for the quantities \(\theta(X)\) produced by the model.
effect
([X, T0, T1])Calculate the heterogeneous treatment effect \(\tau(X, T0, T1)\).
effect_inference
([X, T0, T1])Inference results for the quantities \(\tau(X, T0, T1)\) produced by the model.
effect_interval
([X, T0, T1, alpha])Confidence intervals for the quantities \(\tau(X, T0, T1)\) produced by the model.
fit
(Y, T, *[, X, W, sample_weight, ...])Estimate the counterfactual model from data, i.e. estimates function \(\theta(\cdot)\).
marginal_ate
(T[, X])Calculate the average marginal effect \(E_{T, X}[\partial\tau(T, X)]\).
marginal_ate_inference
(T[, X])Inference results for the quantities \(E_{T,X}[\partial \tau(T, X)]\) produced by the model.
marginal_ate_interval
(T[, X, alpha])Confidence intervals for the quantities \(E_{T,X}[\partial \tau(T, X)]\) produced by the model.
marginal_effect
(T[, X])Calculate the heterogeneous marginal effect \(\partial\tau(T, X)\).
marginal_effect_inference
(T[, X])Inference results for the quantities \(\partial \tau(T, X)\) produced by the model.
marginal_effect_interval
(T[, X, alpha])Confidence intervals for the quantities \(\partial \tau(T, X)\) produced by the model.
model_cate
([T])Get the fitted final CATE model.
refit_final
(*[, inference])Estimate the counterfactual model using a new final model specification but with cached first stage results.
score
(Y, T[, X, W, sample_weight])Score the fitted CATE model on a new data set.
shap_values
(X, *[, feature_names, ...])Shap value for the final stage models (const_marginal_effect)
Attributes
Get an instance of
DoWhyWrapper
to allow other functionalities from dowhy package.Get the fitted featurizer.
fitted_models_final
model_final_
models_nuisance_
Get the fitted propensity models.
Get the fitted regression models.
Get the fitted final CATE model.
Gets the score for the propensity model on out-of-sample training data
Gets the score for the regression model on out-of-sample training data
ortho_learner_model_final_
transformer
- ate(X=None, *, T0=0, T1=1)
Calculate the average treatment effect \(E_X[\tau(X, T0, T1)]\).
The effect is calculated between the two treatment points and is averaged over the population of X variables.
- Parameters
T0 ((m, d_t) matrix or vector of length m) – Base treatments for each sample
T1 ((m, d_t) matrix or vector of length m) – Target treatments for each sample
X ((m, d_x) matrix, optional) – Features for each sample
- Returns
τ – Average treatment effects on each outcome Note that when Y is a vector rather than a 2-dimensional array, the result will be a scalar
- Return type
float or (d_y,) array
- ate_inference(X=None, *, T0=0, T1=1)
Inference results for the quantity \(E_X[\tau(X, T0, T1)]\) produced by the model. Available only when
inference
is notNone
, when calling the fit method.- Parameters
X ((m, d_x) matrix, optional) – Features for each sample
T0 ((m, d_t) matrix or vector of length m, default 0) – Base treatments for each sample
T1 ((m, d_t) matrix or vector of length m, default 1) – Target treatments for each sample
- Returns
PopulationSummaryResults – The inference results instance contains prediction and prediction standard error and can on demand calculate confidence interval, z statistic and p value. It can also output a dataframe summary of these inference results.
- Return type
- ate_interval(X=None, *, T0=0, T1=1, alpha=0.05)
Confidence intervals for the quantity \(E_X[\tau(X, T0, T1)]\) produced by the model. Available only when
inference
is notNone
, when calling the fit method.- Parameters
X ((m, d_x) matrix, optional) – Features for each sample
T0 ((m, d_t) matrix or vector of length m, default 0) – Base treatments for each sample
T1 ((m, d_t) matrix or vector of length m, default 1) – Target treatments for each sample
alpha (float in [0, 1], default 0.05) – The overall level of confidence of the reported interval. The alpha/2, 1-alpha/2 confidence interval is reported.
- Returns
lower, upper – The lower and the upper bounds of the confidence interval for each quantity.
- Return type
tuple(type of
ate(X, T0, T1)
, type ofate(X, T0, T1))
)
- cate_feature_names(feature_names=None)[source]
Get the output feature names.
- Parameters
feature_names (list of str of length X.shape[1] or None) – The names of the input features. If None and X is a dataframe, it defaults to the column names from the dataframe.
- Returns
out_feature_names – The names of the output features \(\phi(X)\), i.e. the features with respect to which the final CATE model for each treatment is linear. It is the names of the features that are associated with each entry of the
coef_()
parameter. Available only when the featurizer is not None and has a method: get_feature_names(feature_names). Otherwise None is returned.- Return type
list of str or None
- cate_output_names(output_names=None)
Public interface for getting output names.
To be overriden by estimators that apply transformations the outputs.
- Parameters
output_names (list of str of length Y.shape[1] or None) – The names of the outcomes. If None and the Y passed to fit was a dataframe, it defaults to the column names from the dataframe.
- Returns
output_names – Returns output names.
- Return type
list of str
- cate_treatment_names(treatment_names=None)
Get treatment names.
If the treatment is discrete or featurized, it will return expanded treatment names.
- Parameters
treatment_names (list of str of length T.shape[1], optional) – The names of the treatments. If None and the T passed to fit was a dataframe, it defaults to the column names from the dataframe.
- Returns
out_treatment_names – Returns (possibly expanded) treatment names.
- Return type
list of str
- const_marginal_ate(X=None)[source]
Calculate the average constant marginal CATE \(E_X[\theta(X)]\).
- Parameters
X ((m, d_x) matrix, optional) – Features for each sample.
- Returns
theta – Average constant marginal CATE of each treatment on each outcome. Note that when Y or T is a vector rather than a 2-dimensional array, the corresponding singleton dimensions in the output will be collapsed (e.g. if both are vectors, then the output of this method will be a scalar)
- Return type
(d_y, d_t) matrix
- const_marginal_ate_inference(X=None)
Inference results for the quantities \(E_X[\theta(X)]\) produced by the model. Available only when
inference
is notNone
, when calling the fit method.- Parameters
X ((m, d_x) matrix, optional) – Features for each sample
- Returns
PopulationSummaryResults – The inference results instance contains prediction and prediction standard error and can on demand calculate confidence interval, z statistic and p value. It can also output a dataframe summary of these inference results.
- Return type
- const_marginal_ate_interval(X=None, *, alpha=0.05)
Confidence intervals for the quantities \(E_X[\theta(X)]\) produced by the model. Available only when
inference
is notNone
, when calling the fit method.- Parameters
X ((m, d_x) matrix, optional) – Features for each sample
alpha (float in [0, 1], default 0.05) – The overall level of confidence of the reported interval. The alpha/2, 1-alpha/2 confidence interval is reported.
- Returns
lower, upper – The lower and the upper bounds of the confidence interval for each quantity.
- Return type
tuple(type of
const_marginal_ate(X)
, type ofconst_marginal_ate(X)
)
- const_marginal_effect(X=None)[source]
Calculate the constant marginal CATE \(\theta(·)\).
The marginal effect is conditional on a vector of features on a set of m test samples X[i].
- Parameters
X ((m, d_x) matrix, optional) – Features for each sample.
- Returns
theta – Constant marginal CATE of each treatment on each outcome for each sample X[i]. Note that when Y or T is a vector rather than a 2-dimensional array, the corresponding singleton dimensions in the output will be collapsed (e.g. if both are vectors, then the output of this method will also be a vector)
- Return type
(m, d_y, d_t) matrix or (d_y, d_t) matrix if X is None
- const_marginal_effect_inference(X=None)
Inference results for the quantities \(\theta(X)\) produced by the model. Available only when
inference
is notNone
, when calling the fit method.- Parameters
X ((m, d_x) matrix, optional) – Features for each sample
- Returns
InferenceResults – The inference results instance contains prediction and prediction standard error and can on demand calculate confidence interval, z statistic and p value. It can also output a dataframe summary of these inference results.
- Return type
- const_marginal_effect_interval(X=None, *, alpha=0.05)
Confidence intervals for the quantities \(\theta(X)\) produced by the model. Available only when
inference
is notNone
, when calling the fit method.- Parameters
X ((m, d_x) matrix, optional) – Features for each sample
alpha (float in [0, 1], default 0.05) – The overall level of confidence of the reported interval. The alpha/2, 1-alpha/2 confidence interval is reported.
- Returns
lower, upper – The lower and the upper bounds of the confidence interval for each quantity.
- Return type
tuple(type of
const_marginal_effect(X)
, type ofconst_marginal_effect(X)
)
- effect(X=None, *, T0=0, T1=1)
Calculate the heterogeneous treatment effect \(\tau(X, T0, T1)\).
The effect is calculated between the two treatment points conditional on a vector of features on a set of m test samples \(\{T0_i, T1_i, X_i\}\).
- Parameters
T0 ((m, d_t) matrix or vector of length m) – Base treatments for each sample
T1 ((m, d_t) matrix or vector of length m) – Target treatments for each sample
X ((m, d_x) matrix, optional) – Features for each sample
- Returns
τ – Heterogeneous treatment effects on each outcome for each sample Note that when Y is a vector rather than a 2-dimensional array, the corresponding singleton dimension will be collapsed (so this method will return a vector)
- Return type
(m, d_y) matrix
- effect_inference(X=None, *, T0=0, T1=1)
Inference results for the quantities \(\tau(X, T0, T1)\) produced by the model. Available only when
inference
is notNone
, when calling the fit method.- Parameters
X ((m, d_x) matrix, optional) – Features for each sample
T0 ((m, d_t) matrix or vector of length m, default 0) – Base treatments for each sample
T1 ((m, d_t) matrix or vector of length m, default 1) – Target treatments for each sample
- Returns
InferenceResults – The inference results instance contains prediction and prediction standard error and can on demand calculate confidence interval, z statistic and p value. It can also output a dataframe summary of these inference results.
- Return type
- effect_interval(X=None, *, T0=0, T1=1, alpha=0.05)
Confidence intervals for the quantities \(\tau(X, T0, T1)\) produced by the model. Available only when
inference
is notNone
, when calling the fit method.- Parameters
X ((m, d_x) matrix, optional) – Features for each sample
T0 ((m, d_t) matrix or vector of length m, default 0) – Base treatments for each sample
T1 ((m, d_t) matrix or vector of length m, default 1) – Target treatments for each sample
alpha (float in [0, 1], default 0.05) – The overall level of confidence of the reported interval. The alpha/2, 1-alpha/2 confidence interval is reported.
- Returns
lower, upper – The lower and the upper bounds of the confidence interval for each quantity.
- Return type
tuple(type of
effect(X, T0, T1)
, type ofeffect(X, T0, T1))
)
- fit(Y, T, *, X=None, W=None, sample_weight=None, freq_weight=None, sample_var=None, groups=None, cache_values=False, inference='auto')[source]
Estimate the counterfactual model from data, i.e. estimates function \(\theta(\cdot)\).
- Parameters
Y ((n,) vector of length n) – Outcomes for each sample
T ((n,) vector of length n) – Treatments for each sample
X ((n, d_x) matrix, optional) – Features for each sample
W ((n, d_w) matrix, optional) – Controls for each sample
sample_weight ((n,) array_like, optional) – Individual weights for each sample. If None, it assumes equal weight.
freq_weight ((n,) array_like of int, optional) – Weight for the observation. Observation i is treated as the mean outcome of freq_weight[i] independent observations. When
sample_var
is not None, this should be provided.sample_var ((n,) nd array_like, optional) – Variance of the outcome(s) of the original freq_weight[i] observations that were used to compute the mean outcome represented by observation i.
groups ((n,) vector, optional) – All rows corresponding to the same group will be kept together during splitting. If groups is not None, the cv argument passed to this class’s initializer must support a ‘groups’ argument to its split method.
cache_values (bool, default False) – Whether to cache inputs and first stage results, which will allow refitting a different final model
inference (str,
Inference
instance, or None) – Method for performing inference. This estimator supports ‘bootstrap’ (or an instance ofBootstrapInference
).
- Returns
self
- Return type
DRLearner instance
- marginal_ate(T, X=None)
Calculate the average marginal effect \(E_{T, X}[\partial\tau(T, X)]\).
The marginal effect is calculated around a base treatment point and averaged over the population of X.
- Parameters
T ((m, d_t) matrix) – Base treatments for each sample
X ((m, d_x) matrix, optional) – Features for each sample
- Returns
grad_tau – Average marginal effects on each outcome Note that when Y or T is a vector rather than a 2-dimensional array, the corresponding singleton dimensions in the output will be collapsed (e.g. if both are vectors, then the output of this method will be a scalar)
- Return type
(d_y, d_t) array
- marginal_ate_inference(T, X=None)
Inference results for the quantities \(E_{T,X}[\partial \tau(T, X)]\) produced by the model. Available only when
inference
is notNone
, when calling the fit method.- Parameters
T ((m, d_t) matrix) – Base treatments for each sample
X ((m, d_x) matrix, optional) – Features for each sample
- Returns
PopulationSummaryResults – The inference results instance contains prediction and prediction standard error and can on demand calculate confidence interval, z statistic and p value. It can also output a dataframe summary of these inference results.
- Return type
- marginal_ate_interval(T, X=None, *, alpha=0.05)
Confidence intervals for the quantities \(E_{T,X}[\partial \tau(T, X)]\) produced by the model. Available only when
inference
is notNone
, when calling the fit method.- Parameters
T ((m, d_t) matrix) – Base treatments for each sample
X ((m, d_x) matrix, optional) – Features for each sample
alpha (float in [0, 1], default 0.05) – The overall level of confidence of the reported interval. The alpha/2, 1-alpha/2 confidence interval is reported.
- Returns
lower, upper – The lower and the upper bounds of the confidence interval for each quantity.
- Return type
tuple(type of
marginal_ate(T, X)
, type ofmarginal_ate(T, X)
)
- marginal_effect(T, X=None)
Calculate the heterogeneous marginal effect \(\partial\tau(T, X)\).
The marginal effect is calculated around a base treatment point conditional on a vector of features on a set of m test samples \(\{T_i, X_i\}\). If treatment_featurizer is None, the base treatment is ignored in this calculation and the result is equivalent to const_marginal_effect.
- Parameters
T ((m, d_t) matrix) – Base treatments for each sample
X ((m, d_x) matrix, optional) – Features for each sample
- Returns
grad_tau – Heterogeneous marginal effects on each outcome for each sample Note that when Y or T is a vector rather than a 2-dimensional array, the corresponding singleton dimensions in the output will be collapsed (e.g. if both are vectors, then the output of this method will also be a vector)
- Return type
(m, d_y, d_t) array
- marginal_effect_inference(T, X=None)
Inference results for the quantities \(\partial \tau(T, X)\) produced by the model. Available only when
inference
is notNone
, when calling the fit method.- Parameters
T ((m, d_t) matrix) – Base treatments for each sample
X ((m, d_x) matrix, optional) – Features for each sample
- Returns
InferenceResults – The inference results instance contains prediction and prediction standard error and can on demand calculate confidence interval, z statistic and p value. It can also output a dataframe summary of these inference results.
- Return type
- marginal_effect_interval(T, X=None, *, alpha=0.05)
Confidence intervals for the quantities \(\partial \tau(T, X)\) produced by the model. Available only when
inference
is notNone
, when calling the fit method.- Parameters
T ((m, d_t) matrix) – Base treatments for each sample
X ((m, d_x) matrix, optional) – Features for each sample
alpha (float in [0, 1], default 0.05) – The overall level of confidence of the reported interval. The alpha/2, 1-alpha/2 confidence interval is reported.
- Returns
lower, upper – The lower and the upper bounds of the confidence interval for each quantity.
- Return type
tuple(type of
marginal_effect(T, X)
, type ofmarginal_effect(T, X)
)
- model_cate(T=1)[source]
Get the fitted final CATE model.
- Parameters
T (alphanumeric) – The treatment with respect to which we want the fitted CATE model.
- Returns
model_cate – An instance of the model_final object that was fitted after calling fit which corresponds to the CATE model for treatment T=t, compared to baseline. Available when multitask_model_final=False.
- Return type
object of type(model_final)
- refit_final(*, inference='auto')[source]
Estimate the counterfactual model using a new final model specification but with cached first stage results.
In order for this to succeed,
fit
must have been called withcache_values=True
. This call will only refit the final model. This call we use the current setting of any parameters that change the final stage estimation. If any parameters that change how the first stage nuisance estimates has also been changed then it will have no effect. You need to call fit again to change the first stage estimation results.- Parameters
inference (inference method, optional) – The string or object that represents the inference method
- Returns
self – This instance
- Return type
- score(Y, T, X=None, W=None, sample_weight=None)[source]
Score the fitted CATE model on a new data set. Generates nuisance parameters for the new data set based on the fitted residual nuisance models created at fit time. It uses the mean prediction of the models fitted by the different crossfit folds. Then calculates the MSE of the final residual Y on residual T regression.
If model_final does not have a score method, then it raises an
AttributeError
- Parameters
Y ((n,) vector of length n) – Outcomes for each sample
T ((n,) vector of length n) – Treatments for each sample
X ((n, d_x) matrix, optional) – Features for each sample
W ((n, d_w) matrix, optional) – Controls for each sample
sample_weight ((n,) vector, optional) – Weights for each samples
- Returns
score – The MSE of the final CATE model on the new data.
- Return type
- shap_values(X, *, feature_names=None, treatment_names=None, output_names=None, background_samples=100)[source]
Shap value for the final stage models (const_marginal_effect)
- Parameters
X ((m, d_x) matrix) – Features for each sample. Should be in the same shape of fitted X in final stage.
feature_names (list of str of length X.shape[1], optional) – The names of input features.
treatment_names (list, optional) – The name of featurized treatment. In discrete treatment scenario, the name should not include the name of the baseline treatment (i.e. the control treatment, which by default is the alphabetically smaller)
output_names (list, optional) – The name of the outcome.
background_samples (int , default 100) – How many samples to use to compute the baseline effect. If None then all samples are used.
- Returns
shap_outs – A nested dictionary by using each output name (e.g. ‘Y0’, ‘Y1’, … when output_names=None) and each treatment name (e.g. ‘T0’, ‘T1’, … when treatment_names=None) as key and the shap_values explanation object as value. If the input data at fit time also contain metadata, (e.g. are pandas DataFrames), then the column metatdata for the treatments, outcomes and features are used instead of the above defaults (unless the user overrides with explicitly passing the corresponding names).
- Return type
nested dictionary of Explanation object
- property dowhy
Get an instance of
DoWhyWrapper
to allow other functionalities from dowhy package. (e.g. causal graph, refutation test, etc.)- Returns
DoWhyWrapper – An instance of
DoWhyWrapper
- Return type
instance
- property featurizer_
Get the fitted featurizer.
- Returns
featurizer – An instance of the fitted featurizer that was used to preprocess X in the final CATE model training. Available only when featurizer is not None and X is not None.
- Return type
object of type(featurizer)
- property models_propensity
Get the fitted propensity models.
- Returns
models_propensity – A nested list of instances of the model_propensity object. Number of sublist equals to number of monte carlo iterations, each element in the sublist corresponds to a crossfitting fold and is the model instance that was fitted for that training fold.
- Return type
nested list of objects of type(model_propensity)
- property models_regression
Get the fitted regression models.
- Returns
model_regression – A nested list of instances of the model_regression object. Number of sublist equals to number of monte carlo iterations, each element in the sublist corresponds to a crossfitting fold and is the model instance that was fitted for that training fold.
- Return type
nested list of objects of type(model_regression)
- property multitask_model_cate
Get the fitted final CATE model.
- Returns
multitask_model_cate – An instance of the model_final object that was fitted after calling fit which corresponds whose vector of outcomes correspond to the CATE model for each treatment, compared to baseline. Available only when multitask_model_final=True.
- Return type
object of type(model_final)
- property nuisance_scores_propensity
Gets the score for the propensity model on out-of-sample training data
- property nuisance_scores_regression
Gets the score for the regression model on out-of-sample training data