File: plot_spectral_coclustering.py

package info (click to toggle)
scikit-learn 0.23.2-5
  • links: PTS, VCS
  • area: main
  • in suites: bookworm, bullseye, sid
  • size: 21,892 kB
  • sloc: python: 132,020; cpp: 5,765; javascript: 2,201; ansic: 831; makefile: 213; sh: 44
file content (58 lines) | stat: -rw-r--r-- 1,776 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
"""
==============================================
A demo of the Spectral Co-Clustering algorithm
==============================================

This example demonstrates how to generate a dataset and bicluster it
using the Spectral Co-Clustering algorithm.

The dataset is generated using the ``make_biclusters`` function, which
creates a matrix of small values and implants bicluster with large
values. The rows and columns are then shuffled and passed to the
Spectral Co-Clustering algorithm. Rearranging the shuffled matrix to
make biclusters contiguous shows how accurately the algorithm found
the biclusters.

"""
print(__doc__)

# Author: Kemal Eren <kemal@kemaleren.com>
# License: BSD 3 clause

import numpy as np
from matplotlib import pyplot as plt

from sklearn.datasets import make_biclusters
from sklearn.cluster import SpectralCoclustering
from sklearn.metrics import consensus_score

data, rows, columns = make_biclusters(
    shape=(300, 300), n_clusters=5, noise=5,
    shuffle=False, random_state=0)

plt.matshow(data, cmap=plt.cm.Blues)
plt.title("Original dataset")

# shuffle clusters
rng = np.random.RandomState(0)
row_idx = rng.permutation(data.shape[0])
col_idx = rng.permutation(data.shape[1])
data = data[row_idx][:, col_idx]

plt.matshow(data, cmap=plt.cm.Blues)
plt.title("Shuffled dataset")

model = SpectralCoclustering(n_clusters=5, random_state=0)
model.fit(data)
score = consensus_score(model.biclusters_,
                        (rows[:, row_idx], columns[:, col_idx]))

print("consensus score: {:.3f}".format(score))

fit_data = data[np.argsort(model.row_labels_)]
fit_data = fit_data[:, np.argsort(model.column_labels_)]

plt.matshow(fit_data, cmap=plt.cm.Blues)
plt.title("After biclustering; rearranged to show biclusters")

plt.show()