API Reference

This page provides a detailed API reference for the conditional independence tests available in citk.

Simple CI Tests

These are classical statistical methods for conditional independence testing.

class citk.tests.FisherZ(data: ndarray, **kwargs)

Bases: CITKTest

This class is a wrapper around the fisherz test from the causal-learn library.

Parameters:: data (np.ndarray) – The dataset from which to run the test.

supported_dtypes = {'continuous'}

class citk.tests.Spearman(data: ndarray, **kwargs)

Bases: CITKTest

This class is a wrapper around the fisherz test from the causal-learn library on ranked data.

Parameters:: data (np.ndarray) – The dataset from which to run the test.

supported_dtypes = {'continuous'}

class citk.tests.ChiSq(data, **kwargs)

Bases: CITKTest

This class is a wrapper around the chisq test from the causal-learn library.

Parameters:: data (np.ndarray) – The dataset from which to run the test.

supported_dtypes = {'discrete'}

class citk.tests.GSq(data, **kwargs)

Bases: CITKTest

This class is a wrapper around the gsq test from the causal-learn library.

Parameters:: data (np.ndarray) – The dataset from which to run the test.

supported_dtypes = {'discrete'}

Regression-Based Tests

These tests use regression-based formulations for conditional independence.

class citk.tests.RegressionCI(data: ndarray, **kwargs)

Bases: _TigramiteBase

class_candidates: List[str] = ['tigramite.independence_tests.regressionCI.RegressionCI']

method_name = 'regci'

Nearest Neighbor Tests

class citk.tests.CMIknn(data: ndarray, **kwargs)

Bases: _TigramiteBase

class_candidates: List[str] = ['tigramite.independence_tests.cmiknn.CMIknn']

method_name = 'cmiknn'

class citk.tests.CMIknnMixed(data: ndarray, **kwargs)

Bases: _TigramiteBase

class_candidates: List[str] = ['tigramite.independence_tests.cmiknn.CMIknnMixed', 'tigramite.independence_tests.cmiknn_mixed.CMIknnMixed']

method_name = 'cmiknn_mixed'

class citk.tests.MCMIknn(data: ndarray, **kwargs)

Bases: CITKTest

supported_dtypes = {'continuous', 'discrete'}

Kernel Tests

class citk.tests.RCoT(data: ndarray, **kwargs)

Bases: _RCITBase

method_name = 'rcot'

rcit_func_name = 'RCoT'

class citk.tests.RCIT(data: ndarray, **kwargs)

Bases: _RCITBase

method_name = 'rcit'

rcit_func_name = 'RCIT'

Machine Learning-Based Tests

These tests leverage machine learning models to detect complex, non-linear conditional dependencies.

class citk.tests.KCI(data, **kwargs)

Bases: CITKTest

Wrapper for the Kernel Conditional Independence (KCI) test from the causal-learn library.

Parameters:

data (np.ndarray) – The dataset from which to run the test.
**kwargs (dict) – Additional keywords for the KCI test. See causal-learn documentation.

supported_dtypes = {'continuous'}

class citk.tests.RandomForest(data: ndarray, **kwargs)

Bases: CITKTest

Performs a conditional independence test using Random Forest feature importance.

Parameters:

data (np.ndarray) – The dataset from which to run the test.
n_estimators (int, optional) – The number of trees in the forest.
num_permutations (int, optional) – The number of permutations to perform for the permutation test.
random_state (int, optional) – Seed for the random number generator for reproducibility.

supported_dtypes = {'continuous', 'discrete'}

class citk.tests.DML(data: ndarray, **kwargs)

Bases: CITKTest

Double-ML based conditional independence test.

Parameters:

data (np.ndarray) – The dataset from which to run the test.
model (scikit-learn compatible regressor, optional) – The model used to predict X from Z and Y from Z. Defaults to HistGradientBoostingRegressor.
cv_folds (int, optional) – The number of folds for cross-fitting.
n_perms (int, optional) – Deprecated. Kept for backward compatibility.

supported_dtypes = {'continuous'}

class citk.tests.CRIT(data: ndarray, **kwargs)

Bases: CITKTest

Conformalized Residual Independence Test (CRIT).

Parameters:

data (np.ndarray) – The dataset from which to run the test.
alpha (float, optional) – The significance level for the conformal prediction intervals.
cv_folds (int, optional) – The number of folds for cross-fitting.
n_perms (int, optional) – Deprecated. Kept for backward compatibility.

supported_dtypes = {'continuous'}

class citk.tests.EDML(data: ndarray, **kwargs)

Bases: CITKTest

E-Value Double-ML based conditional independence test.

Parameters:

data (np.ndarray) – The dataset from which to run the test.
model (scikit-learn compatible regressor, optional) – The model used to predict X from Z and Y from Z. Defaults to HistGradientBoostingRegressor.
cv_folds (int, optional) – The number of folds for cross-fitting the residual models.
betting_folds (int, optional) – The number of folds for the e-value betting mechanism.