Learning Data Mining with Python - Second Edition

The transformer API

Transformers have two key functions:

• fit(): This takes a training set of data as input and sets internal parameters
• transform(): This performs the transformation itself. This can take either the training dataset, or a new dataset of the same format

Both fit() and transform() functions should take the same data type as input, but transform() can return data of a different type while fit() always returns self.

We are going to create a trivial transformer to show the API in action. The transformer will take a NumPy array as input, and discretize it based on the mean. Any value higher than the mean (of the training data) will be given the value 1 and any value lower or equal to the mean will be given the value 0.

We did ...