This repository was archived by the owner on Jan 25, 2023. It is now read-only.
forked from scikit-learn/scikit-learn
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathplot_cluster_iris.py
More file actions
92 lines (72 loc) · 2.52 KB
/
plot_cluster_iris.py
File metadata and controls
92 lines (72 loc) · 2.52 KB
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
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
#!/usr/bin/python
# -*- coding: utf-8 -*-
"""
=========================================================
K-means Clustering
=========================================================
The plots display firstly what a K-means algorithm would yield
using three clusters. It is then shown what the effect of a bad
initialization is on the classification process:
By setting n_init to only 1 (default is 10), the amount of
times that the algorithm will be run with different centroid
seeds is reduced.
The next plot displays what using eight clusters would deliver
and finally the ground truth.
"""
print(__doc__)
# Code source: Gael Varoqueux
# Modified for Documentation merge by Jaques Grobler
# License: BSD 3 clause
import numpy as np
import pylab as pl
from mpl_toolkits.mplot3d import Axes3D
from sklearn.cluster import KMeans
from sklearn import datasets
np.random.seed(5)
centers = [[1, 1], [-1, -1], [1, -1]]
iris = datasets.load_iris()
X = iris.data
y = iris.target
estimators = {'k_means_iris_3': KMeans(n_clusters=3),
'k_means_iris_8': KMeans(n_clusters=8),
'k_means_iris_bad_init': KMeans(n_clusters=3, n_init=1,
init='random')}
fignum = 1
for name, est in estimators.iteritems():
fig = pl.figure(fignum, figsize=(4, 3))
pl.clf()
ax = Axes3D(fig, rect=[0, 0, .95, 1], elev=48, azim=134)
pl.cla()
est.fit(X)
labels = est.labels_
ax.scatter(X[:, 3], X[:, 0], X[:, 2], c=labels.astype(np.float))
ax.w_xaxis.set_ticklabels([])
ax.w_yaxis.set_ticklabels([])
ax.w_zaxis.set_ticklabels([])
ax.set_xlabel('Petal width')
ax.set_ylabel('Sepal length')
ax.set_zlabel('Petal length')
fignum = fignum + 1
# Plot the ground truth
fig = pl.figure(fignum, figsize=(4, 3))
pl.clf()
ax = Axes3D(fig, rect=[0, 0, .95, 1], elev=48, azim=134)
pl.cla()
for name, label in [('Setosa', 0),
('Versicolour', 1),
('Virginica', 2)]:
ax.text3D(X[y == label, 3].mean(),
X[y == label, 0].mean() + 1.5,
X[y == label, 2].mean(), name,
horizontalalignment='center',
bbox=dict(alpha=.5, edgecolor='w', facecolor='w'))
# Reorder the labels to have colors matching the cluster results
y = np.choose(y, [1, 2, 0]).astype(np.float)
ax.scatter(X[:, 3], X[:, 0], X[:, 2], c=y)
ax.w_xaxis.set_ticklabels([])
ax.w_yaxis.set_ticklabels([])
ax.w_zaxis.set_ticklabels([])
ax.set_xlabel('Petal width')
ax.set_ylabel('Sepal length')
ax.set_zlabel('Petal length')
pl.show()