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
|
# -*- coding: utf-8 -*-
"""
==============================
OT for empirical distributions
==============================
"""
import numpy as np
import matplotlib.pylab as pl
import ot
#%% parameters
n = 150 # nb bins
xs, ys = ot.datasets.get_data_classif('3gauss', n)
xt, yt = ot.datasets.get_data_classif('3gauss2', n)
a, b = ot.unif(n), ot.unif(n)
# loss matrix
M = ot.dist(xs, xt)
# M/=M.max()
#%% plot samples
pl.figure(1)
pl.subplot(2, 2, 1)
pl.scatter(xs[:, 0], xs[:, 1], c=ys, marker='+', label='Source samples')
pl.legend(loc=0)
pl.title('Source distributions')
pl.subplot(2, 2, 2)
pl.scatter(xt[:, 0], xt[:, 1], c=yt, marker='o', label='Target samples')
pl.legend(loc=0)
pl.title('target distributions')
pl.figure(2)
pl.imshow(M, interpolation='nearest')
pl.title('Cost matrix M')
#%% OT estimation
# EMD
G0 = ot.emd(a, b, M)
# sinkhorn
lambd = 1e-1
Gs = ot.sinkhorn(a, b, M, lambd)
# Group lasso regularization
reg = 1e-1
eta = 1e0
Gg = ot.da.sinkhorn_lpl1_mm(a, ys.astype(np.int), b, M, reg, eta)
#%% visu matrices
pl.figure(3)
pl.subplot(2, 3, 1)
pl.imshow(G0, interpolation='nearest')
pl.title('OT matrix ')
pl.subplot(2, 3, 2)
pl.imshow(Gs, interpolation='nearest')
pl.title('OT matrix Sinkhorn')
pl.subplot(2, 3, 3)
pl.imshow(Gg, interpolation='nearest')
pl.title('OT matrix Group lasso')
pl.subplot(2, 3, 4)
ot.plot.plot2D_samples_mat(xs, xt, G0, c=[.5, .5, 1])
pl.scatter(xs[:, 0], xs[:, 1], c=ys, marker='+', label='Source samples')
pl.scatter(xt[:, 0], xt[:, 1], c=yt, marker='o', label='Target samples')
pl.subplot(2, 3, 5)
ot.plot.plot2D_samples_mat(xs, xt, Gs, c=[.5, .5, 1])
pl.scatter(xs[:, 0], xs[:, 1], c=ys, marker='+', label='Source samples')
pl.scatter(xt[:, 0], xt[:, 1], c=yt, marker='o', label='Target samples')
pl.subplot(2, 3, 6)
ot.plot.plot2D_samples_mat(xs, xt, Gg, c=[.5, .5, 1])
pl.scatter(xs[:, 0], xs[:, 1], c=ys, marker='+', label='Source samples')
pl.scatter(xt[:, 0], xt[:, 1], c=yt, marker='o', label='Target samples')
pl.tight_layout()
#%% sample interpolation
xst0 = n * G0.dot(xt)
xsts = n * Gs.dot(xt)
xstg = n * Gg.dot(xt)
pl.figure(4, figsize=(8, 3))
pl.subplot(1, 3, 1)
pl.scatter(xt[:, 0], xt[:, 1], c=yt, marker='o',
label='Target samples', alpha=0.5)
pl.scatter(xst0[:, 0], xst0[:, 1], c=ys,
marker='+', label='Transp samples', s=30)
pl.title('Interp samples')
pl.legend(loc=0)
pl.subplot(1, 3, 2)
pl.scatter(xt[:, 0], xt[:, 1], c=yt, marker='o',
label='Target samples', alpha=0.5)
pl.scatter(xsts[:, 0], xsts[:, 1], c=ys,
marker='+', label='Transp samples', s=30)
pl.title('Interp samples Sinkhorn')
pl.subplot(1, 3, 3)
pl.scatter(xt[:, 0], xt[:, 1], c=yt, marker='o',
label='Target samples', alpha=0.5)
pl.scatter(xstg[:, 0], xstg[:, 1], c=ys,
marker='+', label='Transp samples', s=30)
pl.title('Interp samples Grouplasso')
pl.tight_layout()
pl.show()
|
