File: bench_plot_fastkmeans.py

package info (click to toggle)
scikit-learn 0.18-5
  • links: PTS, VCS
  • area: main
  • in suites: stretch
  • size: 71,040 kB
  • ctags: 91,142
  • sloc: python: 97,257; ansic: 8,360; cpp: 5,649; makefile: 242; sh: 238
file content (138 lines) | stat: -rw-r--r-- 4,668 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
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
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
from __future__ import print_function

from collections import defaultdict
from time import time

import numpy as np
from numpy import random as nr

from sklearn.cluster.k_means_ import KMeans, MiniBatchKMeans


def compute_bench(samples_range, features_range):

    it = 0
    results = defaultdict(lambda: [])
    chunk = 100

    max_it = len(samples_range) * len(features_range)
    for n_samples in samples_range:
        for n_features in features_range:
            it += 1
            print('==============================')
            print('Iteration %03d of %03d' % (it, max_it))
            print('==============================')
            print()
            data = nr.randint(-50, 51, (n_samples, n_features))

            print('K-Means')
            tstart = time()
            kmeans = KMeans(init='k-means++', n_clusters=10).fit(data)

            delta = time() - tstart
            print("Speed: %0.3fs" % delta)
            print("Inertia: %0.5f" % kmeans.inertia_)
            print()

            results['kmeans_speed'].append(delta)
            results['kmeans_quality'].append(kmeans.inertia_)

            print('Fast K-Means')
            # let's prepare the data in small chunks
            mbkmeans = MiniBatchKMeans(init='k-means++',
                                       n_clusters=10,
                                       batch_size=chunk)
            tstart = time()
            mbkmeans.fit(data)
            delta = time() - tstart
            print("Speed: %0.3fs" % delta)
            print("Inertia: %f" % mbkmeans.inertia_)
            print()
            print()

            results['MiniBatchKMeans Speed'].append(delta)
            results['MiniBatchKMeans Quality'].append(mbkmeans.inertia_)

    return results


def compute_bench_2(chunks):
    results = defaultdict(lambda: [])
    n_features = 50000
    means = np.array([[1, 1], [-1, -1], [1, -1], [-1, 1],
                      [0.5, 0.5], [0.75, -0.5], [-1, 0.75], [1, 0]])
    X = np.empty((0, 2))
    for i in range(8):
        X = np.r_[X, means[i] + 0.8 * np.random.randn(n_features, 2)]
    max_it = len(chunks)
    it = 0
    for chunk in chunks:
        it += 1
        print('==============================')
        print('Iteration %03d of %03d' % (it, max_it))
        print('==============================')
        print()

        print('Fast K-Means')
        tstart = time()
        mbkmeans = MiniBatchKMeans(init='k-means++',
                                   n_clusters=8,
                                   batch_size=chunk)

        mbkmeans.fit(X)
        delta = time() - tstart
        print("Speed: %0.3fs" % delta)
        print("Inertia: %0.3fs" % mbkmeans.inertia_)
        print()

        results['MiniBatchKMeans Speed'].append(delta)
        results['MiniBatchKMeans Quality'].append(mbkmeans.inertia_)

    return results


if __name__ == '__main__':
    from mpl_toolkits.mplot3d import axes3d  # register the 3d projection
    import matplotlib.pyplot as plt

    samples_range = np.linspace(50, 150, 5).astype(np.int)
    features_range = np.linspace(150, 50000, 5).astype(np.int)
    chunks = np.linspace(500, 10000, 15).astype(np.int)

    results = compute_bench(samples_range, features_range)
    results_2 = compute_bench_2(chunks)

    max_time = max([max(i) for i in [t for (label, t) in results.iteritems()
                         if "speed" in label]])
    max_inertia = max([max(i) for i in [
                        t for (label, t) in results.iteritems()
                            if "speed" not in label]])

    fig = plt.figure('scikit-learn K-Means benchmark results')
    for c, (label, timings) in zip('brcy',
                                    sorted(results.iteritems())):
        if 'speed' in label:
            ax = fig.add_subplot(2, 2, 1, projection='3d')
            ax.set_zlim3d(0.0, max_time * 1.1)
        else:
            ax = fig.add_subplot(2, 2, 2, projection='3d')
            ax.set_zlim3d(0.0, max_inertia * 1.1)

        X, Y = np.meshgrid(samples_range, features_range)
        Z = np.asarray(timings).reshape(samples_range.shape[0],
                                        features_range.shape[0])
        ax.plot_surface(X, Y, Z.T, cstride=1, rstride=1, color=c, alpha=0.5)
        ax.set_xlabel('n_samples')
        ax.set_ylabel('n_features')

    i = 0
    for c, (label, timings) in zip('br',
                                   sorted(results_2.iteritems())):
        i += 1
        ax = fig.add_subplot(2, 2, i + 2)
        y = np.asarray(timings)
        ax.plot(chunks, y, color=c, alpha=0.8)
        ax.set_xlabel('Chunks')
        ax.set_ylabel(label)

    plt.show()