Transforming augmentation
Before digging into the tabular augmentation methods, Pluto will reiterate that he will not build a neural network model to test if the augmentation benefits the particular dataset. In addition, the pattern for writing the wrapper functions follows the previous practice: using the chosen library to do the critical augmentation step.
As the Python Notebook notes, the DeltaPy library’s dependency is the fbprofet and pystan libraries. The three libraries are in beta and may be unstable. Pluto has repeatedly tested the Python code. Once the libraries have been loaded, the code works flawlessly.
Tabular transformation is a collection of techniques that take one variable and generate a new dataset based on the transformation method. It applies to both cross-section and time series data. The DeltaPy library defines 14 functions for transformation.
These transformation techniques include the operations functions used in present information, the smoothing...
