src.dackar.anomalies.kernel_two_sample_test
===========================================

.. py:module:: src.dackar.anomalies.kernel_two_sample_test

.. autoapi-nested-parse::

   Created on July, 2025

   @author: wangc, mandd



Attributes
----------

.. autoapisummary::

   src.dackar.anomalies.kernel_two_sample_test.logger


Functions
---------

.. autoapisummary::

   src.dackar.anomalies.kernel_two_sample_test.MMD2u
   src.dackar.anomalies.kernel_two_sample_test.MMD2b
   src.dackar.anomalies.kernel_two_sample_test.MMD2u_UCB
   src.dackar.anomalies.kernel_two_sample_test.MMD2b_UCB
   src.dackar.anomalies.kernel_two_sample_test.compute_null_distribution
   src.dackar.anomalies.kernel_two_sample_test.compute_null_distribution_given_permutations
   src.dackar.anomalies.kernel_two_sample_test.kernel_two_sample_test
   src.dackar.anomalies.kernel_two_sample_test.chebyshevTesting
   src.dackar.anomalies.kernel_two_sample_test.chebyshevTesting_precomputed_mmd


Module Contents
---------------

.. py:data:: logger

.. py:function:: MMD2u(K, m, n)

   Method designed to perform MMD^2_u unbiased statistic using U-statistics.

   :param K: np.array, 2-D matrix
   :param m: int, size of first vector
   :param n: int, size of second vector

   :returns: float, MMD^2_u unbiased statistic using U-statistics
   :rtype: val


.. py:function:: MMD2b(K, m, n)

   Method designed to perform MMD^2 biased statistics using V-statistics

   :param K: np.array, 2-D matrix
   :param m: int, size of first vector
   :param n: int, size of second vector

   :returns: float, MMD^2 biased statistics using V-statistics
   :rtype: out


.. py:function:: MMD2u_UCB(K, m, alpha=0.05)

   Method designed to calculate the uniform convergence bound for MMD2u

   :param K: np.array, 2-D matrix
   :param m: int, sample size
   :param alpha: float, acceptance value for hypothesis testing

   :returns: float, uniform convergence bound for MMD2u
   :rtype: ucb


.. py:function:: MMD2b_UCB(K, m, alpha=0.05)

   Method designed to calculate the uniform convergence bound for MMD2b

   :param K: np.array, 2-D matrix
   :param m: int, sample size
   :param alpha: float, acceptance value for hypothesis testing

   :returns: float, uniform convergence bound for MMD2b
   :rtype: ucb


.. py:function:: compute_null_distribution(K, m, n, iterations=1000, verbose=False, random_state=None, marker_interval=500)

   Method designed to calculate the bootstrap null-distribution of MMD2u.

   :param K: np.array, 2-D matrix
   :param m: int, size of first vector
   :param n: int, size of second vector
   :param iterations: int, number of bootstrap iterations
   :param verbose: bool, flag to provide calculation details
   :param random_state: np class, numpy random number generator class
   :param marker_interval: int, interval where calculation details are displayed

   :returns: np.array, null-distribution of MMD2u
   :rtype: mmd2u_null


.. py:function:: compute_null_distribution_given_permutations(K, m, n, permutation, iterations=None)

   Method designed to calculate the bootstrap null-distribution of MMD2u given predefined permutations.

   :param K: np.array, 2-D matrix
   :param m: int, size of first vector
   :param n: int, size of second vector
   :param permutation: np.array, array of permutations
   :param iterations: int, number of bootstrap iterations

   :returns: np.array, null-distribution of MMD2u given predefined permutations
   :rtype: mmd2u_null


.. py:function:: kernel_two_sample_test(X, Y, kernel_function='rbf', iterations=2000, verbose=False, random_state=None, alpha=0.05, thin=None, **kwargs)

   Method designed to calculate MMD^2_u, its null distribution and the p-value of the kernel two-sample test.

   :param X: np.array, first vector
   :param Y: np.array, second vector
   :param kernel_function: string, type of kenerl function. Valid values are: additive_chi2, chi2,
                           linear, poly, polynomial, rbf, laplacian, sigmoid, cosine
   :param iterations: int, number of iterations
   :param verbose: bool, flag to provide calculation details
   :param random_state: np class, numpy random number generator class
   :param alpha: float, acceptance value for hypothesis testing
   :param thin: int, sample size for thinning calculation
   :param \*\*kwargs: dict, dictionary of parameteres that are passed to pairwise_kernels() as kernel parameters.
                      E.g. if kernel_two_sample_test(..., kernel_function='rbf', gamma=0.1), then this will
                      result in getting the kernel through kernel_function(metric='rbf', gamma=0.1).

   :returns: float, MMD^2_u unbiased statistic using U-statistics
             mmd2u_null: np.array, null-distribution of MMD2u
             p_value: float, calculated p-value for hypothesis testing
   :rtype: mmd2u


.. py:function:: chebyshevTesting(X, Y, kernel_function='rbf', iterations=2000, verbose=False, random_state=None, alpha=0.01, **kwargs)

   Method designed to perform Chebyshev testing using Chebyshev's inequality

   :param X: np.array, first vector
   :param Y: np.array, second vector
   :param kernel_function: string, type of kernel function
   :param iterations: int, number of bootstrap iterations
   :param verbose: bool, flag to provide calculation details
   :param random_state: np class, numpy random number generator class
   :param alpha: float, acceptance value for hypothesis testing
   :param \*\*kwargs: dict, dictionary of parameteres that are passed to pairwise_kernels() as kernel parameters.

   :returns: bool, outcome of Chebyshev testing
   :rtype: accept


.. py:function:: chebyshevTesting_precomputed_mmd(mmd2u, mmd2u_null, alpha=0.01)

   Method designed to perform MMD Chebyshev testing

   :param mmd2u: float, MMD^2_u unbiased statistic using U-statistics
   :param mmd2u_null: np.array, null-distribution of MMD2u
   :param alpha: float, acceptance value for hypothesis testing

   :returns: bool, outcome of Chebyshev testing
   :rtype: accept