PCA Pro allows you to prepare a machine learning dataset for training by performing a form of exploratory data analysis. The main use case involves a user wanting to reduce the time required to train a model without sacrificing too much model accuracy. PCA Pro will identify and plot the components in the dataset that contribute most to the variance in the data. Using the eigenvectors generated in the app you can specify the set of components that make up the transformation matrix. Using the transformation matrix you then apply it to the original dataset so that the result is a reduction in the number of training/validation features.
PCA Pro can be used in conjunction with the Machine Learning Playground (MLP) app by pasting the transformed dataset into the MLP. You can examine how the training of an ML model is improved using the transformed dataset. In addition, the datasets eigenvectors and a transformation matrix are displayed if you wish to use them outside of the app.