SklearnDatasets

class mastml.datasets.SklearnDatasets(return_X_y=True, as_frame=False)

Bases: object

Class wrapping the sklearn.datasets funcionality for easy import of toy datasets from sklearn. Added some changes to make all datasets operate more consistently, e.g. boston housing data

Args:

return_X_y: (bool), whether to return X, y data as (X, y) tuple (should be true for easiest use in MASTML)

as_frame: (bool), whether to return X, y data as pandas dataframe objects

n_class: (int), number of classes (only applies to load_digits method)

Methods:

load_boston: Loads the Boston housing data (regression)

load_iris: Loads the flower iris data (classification)

load_diabetes: Loads the diabetes data set (regression)

load_digits: Loads the MNIST digits data set (classification)

load_linnerud: Loads the linnerud data set (regression)

load_wine: Loads the wine data set (classification)

load_breast_cancer: Loads the breast cancer data set (classification)

load_friedman: Loads the Friedman data set (regression)

Methods Summary

load_boston()
load_breast_cancer()
load_diabetes()
load_digits([n_class])
load_friedman([n_samples, n_features, noise])
load_iris()
load_linnerud()
load_wine()

Methods Documentation

load_boston()

load_breast_cancer()

load_diabetes()

load_digits(n_class=10)

load_friedman(n_samples=100, n_features=10, noise=0.0)

load_iris()

load_linnerud()

load_wine()