RandomRBF

Random Radial Basis Function generator.

Produces a radial basis function stream. A number of centroids, having a random central position, a standard deviation, a class label and weight are generated. A new sample is created by choosing one of the centroids at random, taking into account their weights, and offsetting the attributes in a random direction from the centroid's center. The offset length is drawn from a Gaussian distribution.

This process will create a normally distributed hypersphere of samples on the surrounds of each centroid.

Parameters

• seed_model ('int | None') – defaults to None

  Model's random seed to generate centroids.

• seed_sample ('int | None') – defaults to None

  Sample's random seed.

• n_classes ('int') – defaults to 2

  The number of class labels to generate.

• n_features ('int') – defaults to 10

  The number of numerical features to generate.

• n_centroids ('int') – defaults to 50

  The number of centroids to generate.

Attributes

• desc

  Return the description from the docstring.

Examples

>>> from river.datasets import synth
>>>
>>> dataset = synth.RandomRBF(seed_model=42, seed_sample=42,
...                           n_classes=4, n_features=4, n_centroids=20)
>>>
>>> for x, y in dataset.take(5):
...     print(x, y)
{0: 1.0989, 1: 0.3840, 2: 0.7759, 3: 0.6592} 2
{0: 0.2366, 1: 1.3233, 2: 0.5691, 3: 0.2083} 0
{0: 1.3540, 1: -0.3306, 2: 0.1683, 3: 0.8865} 0
{0: 0.2585, 1: -0.2217, 2: 0.4739, 3: 0.6522} 0
{0: 0.1295, 1: 0.5953, 2: 0.1774, 3: 0.6673} 1

Methods

take

Iterate over the k samples.

Parameters

• k (int)