Developer Guide for Intel® Data Analytics Acceleration Library 2019 Update 1

Quality Metrics for Principal Components Analysis

Given the results of the PCA algorithm, data set of eigenvalues in decreasing order, full number of principal components p and reduced number of components p r p the problem is to evaluate the explained variances radio and noise variance.

QualityMetricsId for the PCA algorithm is explainedVarianceMetrics.

For description of the default PCA quality metrics, refer to Details.