RESIT¶

class
lingam.
RESIT
(regressor, random_state=None, alpha=0.01)[source]¶ Implementation of RESIT(regression with subsequent independence test) Algorithm [1]
References
[1] Jonas Peters, Joris M Mooij, Dominik Janzing, and Bernhard Sch ̈olkopf. Causal discovery with continuous additive noise models. Journal of Machine Learning Research, 15:20092053, 2014. Notes
RESIT algorithm returns an adjacency matrix consisting of zeros or ones, rather than an adjacency matrix consisting of causal coefficients, in order to estimate nonlinear causality.

__init__
(regressor, random_state=None, alpha=0.01)[source]¶ Construct a RESIT model.
Parameters:  regressor (regressor object implementing 'fit' and 'predict' function (default=None)) – Regressor to compute residuals.
This regressor object must have
fit
method andpredict
function like scikitlearn’s model.  random_state (int, optional (default=None)) –
random_state
is the seed used by the random number generator.  alpha (float, optional (default=0.01)) – Alpha level for HSIC independence test when removing superfluous edges.
 regressor (regressor object implementing 'fit' and 'predict' function (default=None)) – Regressor to compute residuals.
This regressor object must have

adjacency_matrix_
¶ Estimated adjacency matrix.
Returns: adjacency_matrix_ – The adjacency matrix B of fitted model, where n_features is the number of features. Return type: arraylike, shape (n_features, n_features)

bootstrap
(X, n_sampling)¶ Evaluate the statistical reliability of DAG based on the bootstrapping.
Parameters:  X (arraylike, shape (n_samples, n_features)) – Training data, where
n_samples
is the number of samples andn_features
is the number of features.  n_sampling (int) – Number of bootstrapping samples.
Returns: result – Returns the result of bootstrapping.
Return type:  X (arraylike, shape (n_samples, n_features)) – Training data, where

causal_order_
¶ Estimated causal ordering.
Returns: causal_order_ – The causal order of fitted model, where n_features is the number of features. Return type: arraylike, shape (n_features)

estimate_total_effect
(X, from_index, to_index)[source]¶ Estimate total effect using causal model.
Parameters:  X (arraylike, shape (n_samples, n_features)) – Original data, where n_samples is the number of samples and n_features is the number of features.
 from_index – Index of source variable to estimate total effect.
 to_index – Index of destination variable to estimate total effect.
Returns: total_effect – Because RESIT is a nonlinear algorithm, it cannot estimate the total effect and always returns a value of zero
Return type: float

fit
(X)[source]¶ Fit the model to X.
Parameters: X (arraylike, shape (n_samples, n_features)) – Training data, where n_samples
is the number of samples andn_features
is the number of features.Returns: self – Returns the instance itself. Return type: object

get_error_independence_p_values
(X)[source]¶ Calculate the pvalue matrix of independence between error variables.
Parameters: X (arraylike, shape (n_samples, n_features)) – Original data, where n_samples is the number of samples and n_features is the number of features. Returns: independence_p_values – RESIT always returns zero Return type: arraylike, shape (n_features, n_features)
