Mapping augmentation
The mapping method uses ML and data analysis to summarize and reduce the dimensionality of data for augmentation. It can be done via unsupervised or supervised learning. Some examples of mapping methods include eigendecomposition and PCA. PCA is a statistical procedure that transforms a set of correlated variables into uncorrelated variables called principal components.
In the DeltaPy library, there are seven mapping methods for tabular augmentation. Pluto has done a few implementations in the Python Notebook, but he will not explain the coding here. The Python wrapper function is repetitive and can easily be applied to any mapping method. The functions are as follows:
- Eigendecomposition (ED) is a form of PCA for tabular augmentation. In ED, the eigenvectors are the covariance matrix of the data, and the corresponding eigenvalues represent the amount of variance by each component. ED includes linear discriminant analysis (LDA), singular value decomposition...
