mim

bcselector.information_theory.j_criterion_approximations.mim(data, target_variable, candidate_variable_index, **kwargs)[source]

This estimator computes the Mutual Information Maximisation criterion.

Parameters
  • data (np.array matrix) – Matrix of data set. Columns are variables, rows are observations.

  • target_variable (int or float) – Target variable. Can not be in data!

  • candidate_variable_index (int) – Index of candidate variable in data matrix.

Returns

j_criterion_value – J_criterion approximated by the Mutual Information Maximisation.

Return type

float

mifs

bcselector.information_theory.j_criterion_approximations.mifs(data, target_variable, prev_variables_index, candidate_variable_index, **kwargs)[source]

This estimator computes the Mutual Information Feature Selection criterion.

Parameters
  • data (np.array matrix) – Matrix of data set. Columns are variables, rows are observations.

  • target_variable (int or float) – Target variable. Can not be in data!

  • prev_variables_index (list of ints, set of ints) – Indexes of previously selected variables.

  • candidate_variable_index (int) – Index of candidate variable in data matrix.

  • beta (float) – Impact of redundancy segment in MIFS approximation. Higher the beta is, higher the impact.

Returns

j_criterion_value – J_criterion approximated by the Mutual Information Feature Selection.

Return type

float

mrmr

bcselector.information_theory.j_criterion_approximations.mrmr(data, target_variable, prev_variables_index, candidate_variable_index, **kwargs)[source]

This estimator computes the Max-Relevance Min-Redundancy criterion.

Parameters
  • data (np.array matrix) – Matrix of data set. Columns are variables, rows are observations.

  • target_variable (int or float) – Target variable. Can not be in data!

  • prev_variables_index (list of ints) – Indexes of previously selected variables.

  • candidate_variable_index (int) – Index of candidate variable in data matrix.

Returns

j_criterion_value – J_criterion approximated by the Max-Relevance Min-Redundancy.

Return type

float

jmi

bcselector.information_theory.j_criterion_approximations.jmi(data, target_variable, prev_variables_index, candidate_variable_index, **kwargs)[source]

This estimator computes the Joint Mutual Information criterion.

Parameters
  • data (np.array matrix) – Matrix of data set. Columns are variables, rows are observations.

  • target_variable (int or float) – Target variable. Can not be in data!

  • prev_variables_index (list of ints) – Indexes of previously selected variables.

  • candidate_variable_index (int) – Index of candidate variable in data matrix.

Returns

j_criterion_value – J_criterion approximated by the Joint Mutual Information.

Return type

float

cife

bcselector.information_theory.j_criterion_approximations.cife(data, target_variable, prev_variables_index, candidate_variable_index, **kwargs)[source]

This estimator computes the Conditional Infomax Feature Extraction criterion.

Parameters
  • data (np.array matrix) – Matrix of data set. Columns are variables, rows are observations.

  • target_variable (int or float) – Target variable. Can not be in data!

  • prev_variables_index (list of ints) – Indexes of previously selected variables.

  • candidate_variable_index (int) – Index of candidate variable in data matrix.

  • beta (float) – Impact of redundancy segment in MIFS approximation. Higher the beta is, higher the impact.

Returns

j_criterion_value – J_criterion approximated by the Conditional Infomax Feature Extraction.

Return type

float