PCA Reference

Comparing PCA statistics on two different datasets

📘

PCA is an advanced Monitor allowing you to monitor multidimensional correlations. If you have limited experience with PCA, we suggest involving a Data Scientist who has PCA experience when setting up this monitor

Configuration parameters

Parameter name and description Parameter values
1. Name Arbitrary String
2. Target features Multi-select of all features with numeric values
3. Number of components Integer
4. Computed metric
  • Primary component explained variance ratio
  • Explained variance effective component number ratio
  • Explained variance rms

Parameter details

See the PCA page for details on ‘Primary component explained variance’ and ‘Explained variance effective component number’

Explained variance rms

Let EVn,x denote the explained variance of the n:th principal component in dataset ‘x’. Let’s say we have two datasets ‘A’ and ‘B’, where we’ve reduced the dimension to three components in both of the datasets. Explained variance rms (root mean squared) would then be:

13411341

Ratio metrics

Calculates the ratio metrics between the two datasets:

Ratio = target metric/reference metric