Simplex Data

Data in a rough simplex from "How to Use t-SNE Effectively".

Usage

simplex_data(n, noise = 0.5, color = "#003399")

Arguments

n

Number of points (and hence dimensionality) of the simplex.

noise

Degree by which to perturb the points from their original locations. A normal distribution with the specified standard deviation is applied to the non-zero coordinate.

color

Color to apply to each point.

Value

Data frame with coordinates in the X1, X2 ... Xn columns, and color in the color column.

Details

Create a dataset of the specified number of points arranged in a rough simplex, which also determines the dimensionality of the dataset. Each point has a single non-zero coordinate in a different column to all the other points.

References

http://distill.pub/2016/misread-tsne/

See also

Other distill functions: circle_data(), cube_data(), gaussian_data(), grid_data(), link_data(), long_cluster_data(), long_gaussian_data(), ortho_curve(), random_circle_cluster_data(), random_circle_data(), random_jump(), random_walk(), subset_clusters_data(), three_clusters_data(), trefoil_data(), two_clusters_data(), two_different_clusters_data(), unlink_data()

Examples

df <- simplex_data(n = 50)