File: plot_random_dataset.py

package info (click to toggle)
scikit-learn 1.4.2%2Bdfsg-8
  • links: PTS, VCS
  • area: main
  • in suites: forky, sid, trixie
  • size: 25,036 kB
  • sloc: python: 201,105; cpp: 5,790; ansic: 854; makefile: 304; sh: 56; javascript: 20
file content (60 lines) | stat: -rw-r--r-- 2,322 bytes parent folder | download
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
"""
==============================================
Plot randomly generated classification dataset
==============================================

This example plots several randomly generated classification datasets.
For easy visualization, all datasets have 2 features, plotted on the x and y
axis. The color of each point represents its class label.

The first 4 plots use the :func:`~sklearn.datasets.make_classification` with
different numbers of informative features, clusters per class and classes.
The final 2 plots use :func:`~sklearn.datasets.make_blobs` and
:func:`~sklearn.datasets.make_gaussian_quantiles`.

"""

import matplotlib.pyplot as plt

from sklearn.datasets import make_blobs, make_classification, make_gaussian_quantiles

plt.figure(figsize=(8, 8))
plt.subplots_adjust(bottom=0.05, top=0.9, left=0.05, right=0.95)

plt.subplot(321)
plt.title("One informative feature, one cluster per class", fontsize="small")
X1, Y1 = make_classification(
    n_features=2, n_redundant=0, n_informative=1, n_clusters_per_class=1
)
plt.scatter(X1[:, 0], X1[:, 1], marker="o", c=Y1, s=25, edgecolor="k")

plt.subplot(322)
plt.title("Two informative features, one cluster per class", fontsize="small")
X1, Y1 = make_classification(
    n_features=2, n_redundant=0, n_informative=2, n_clusters_per_class=1
)
plt.scatter(X1[:, 0], X1[:, 1], marker="o", c=Y1, s=25, edgecolor="k")

plt.subplot(323)
plt.title("Two informative features, two clusters per class", fontsize="small")
X2, Y2 = make_classification(n_features=2, n_redundant=0, n_informative=2)
plt.scatter(X2[:, 0], X2[:, 1], marker="o", c=Y2, s=25, edgecolor="k")

plt.subplot(324)
plt.title("Multi-class, two informative features, one cluster", fontsize="small")
X1, Y1 = make_classification(
    n_features=2, n_redundant=0, n_informative=2, n_clusters_per_class=1, n_classes=3
)
plt.scatter(X1[:, 0], X1[:, 1], marker="o", c=Y1, s=25, edgecolor="k")

plt.subplot(325)
plt.title("Three blobs", fontsize="small")
X1, Y1 = make_blobs(n_features=2, centers=3)
plt.scatter(X1[:, 0], X1[:, 1], marker="o", c=Y1, s=25, edgecolor="k")

plt.subplot(326)
plt.title("Gaussian divided into three quantiles", fontsize="small")
X1, Y1 = make_gaussian_quantiles(n_features=2, n_classes=3)
plt.scatter(X1[:, 0], X1[:, 1], marker="o", c=Y1, s=25, edgecolor="k")

plt.show()