tedana.selection._utils

Utility functions for tedana.selection

Functions

do_svm(X_train, y_train, X_test[, svmtype])	Implements Support Vector Classification on provided data
getelbow(arr[, return_val])	Elbow using linear projection method - moderate
getelbow_cons(arr[, return_val])	Elbow using mean/variance method - conservative

do_svm(X_train, y_train, X_test, svmtype=0)

Implements Support Vector Classification on provided data

Parameters:

• X_train ((N1 x F) array_like) – Training vectors, where n_samples is the number of samples in the training dataset and n_features is the number of features.
• y_train ((N1,) array_like) – Target values (class labels in classification, real numbers in regression)
• X_test ((N2 x F) array_like) – Test vectors, where n_samples is the number of samples in the test dataset and n_features is the number of features.
• svmtype (int, optional) – Desired support vector machine type. Must be in [0, 1, 2]. Default: 0

Returns:

• y_pred ((N2,) numpy.ndarray) – Predicted class labels for samples in X_test
• clf ({sklearn.svm.SVC, sklearn.svm.LinearSVC}) – Trained sklearn model instance

getelbow(arr, return_val=False)

Elbow using linear projection method - moderate

Parameters:

• arr ((C,) array_like) – Metric (e.g., Kappa or Rho) values.
• return_val (bool, optional) – Return the value of the elbow instead of the index. Default: False

Returns:

Either the elbow index (if return_val is True) or the values at the elbow index (if return_val is False)

Return type:

int or float

getelbow_cons(arr, return_val=False)

Elbow using mean/variance method - conservative

Parameters:

• arr ((C,) array_like) – Metric (e.g., Kappa or Rho) values.
• return_val (bool, optional) – Return the value of the elbow instead of the index. Default: False

Returns:

Either the elbow index (if return_val is True) or the values at the elbow index (if return_val is False)

Return type:

int or float