packLogo
Principal Component AnalysisStatistical tool to reduce the dimensionality of your data
AboutSecurityDocumentation
This pack allows you to apply Principal Component Analysis (PCA) to your data. PCA determines the best space of lower dimensions for our dataset. “Best” is the sense that it maximises the dispersion of its elements. PCA is incredibly useful: * calculates at once the best representation of our dataset in various forms: as a ranking (1 dimension), as a map (2 dimensions), and as a cloud (3 dimensions) and so on. * factors in any correlation existing between your variables (=columns of your table). * tells us how much of the original dataset is actually explained by each form. This pack ports a Javascript implementation of PCA written by Bitanath, kudos to them! See: https://github.com/bitanath/pca
What's in this Pack
All (2)Tables (2)
LoadingsTableWeights of the original variables in the linear combination defining each principal component, and percentage explained of your dataset for each principal component
building-block-table
Loadings
PrincipalComponentsTableCompute the principal components of your dataset and returns the coordinates of your samples within this base
building-block-table
PrincipalComponents
Docs using this Pack
DetailsRelease 2Updated 1 month ago
Docs using this Pack
Docs using this Pack
DetailsRelease 2Updated 1 month ago