Generate dataset blobs

Generates an artificial dataset useful for testing clustering algorithms

Definition

Output ports

X table

X

Y table

Y

Configuration

center_max (center_max)

Largest allowed coordinate for the generated centers

center_min (center_min)

Smallest allowed coordinate for the generated centers

centers (centers)

Number of clusters.

cluster_std (cluster_std)

Standard deviation of the clusters.

n_features (n_features)

The number of features for each sample.

n_samples (n_samples)

The total number of points equally divided among clusters.

shuffle (shuffle)

Shuffle datapoints (otherwise given in cluster order)

Implementation

class node_io.MakeBlobs