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
|
"""Private utilities."""
import warnings
import numpy as np
def logdet(a):
sign, logdet = np.linalg.slogdet(a)
if (sign < 0).any():
warnings.warn("invalid value encountered in log", RuntimeWarning)
return np.where(sign < 0, np.nan, logdet)
else:
return logdet
def split_X_lengths(X, lengths):
if lengths is None:
return [X]
else:
cs = np.cumsum(lengths)
n_samples = len(X)
if cs[-1] != n_samples:
raise ValueError(
f"lengths array {lengths} doesn't sum to {n_samples} samples")
return np.split(X, cs)[:-1]
# Copied from scikit-learn 0.19.
def _validate_covars(covars, covariance_type, n_components):
"""Do basic checks on matrix covariance sizes and values."""
from scipy import linalg
if covariance_type == 'spherical':
if len(covars) != n_components:
raise ValueError("'spherical' covars have length n_components")
elif np.any(covars <= 0):
raise ValueError("'spherical' covars must be positive")
elif covariance_type == 'tied':
if covars.shape[0] != covars.shape[1]:
raise ValueError("'tied' covars must have shape (n_dim, n_dim)")
elif (not np.allclose(covars, covars.T)
or np.any(linalg.eigvalsh(covars) <= 0)):
raise ValueError("'tied' covars must be symmetric, "
"positive-definite")
elif covariance_type == 'diag':
if len(covars.shape) != 2:
raise ValueError("'diag' covars must have shape "
"(n_components, n_dim)")
elif np.any(covars <= 0):
raise ValueError("'diag' covars must be positive")
elif covariance_type == 'full':
if len(covars.shape) != 3:
raise ValueError("'full' covars must have shape "
"(n_components, n_dim, n_dim)")
elif covars.shape[1] != covars.shape[2]:
raise ValueError("'full' covars must have shape "
"(n_components, n_dim, n_dim)")
for n, cv in enumerate(covars):
if (not np.allclose(cv, cv.T)
or np.any(linalg.eigvalsh(cv) <= 0)):
raise ValueError("component %d of 'full' covars must be "
"symmetric, positive-definite" % n)
else:
raise ValueError("covariance_type must be one of " +
"'spherical', 'tied', 'diag', 'full'")
# Copied from scikit-learn 0.19.
def distribute_covar_matrix_to_match_covariance_type(
tied_cv, covariance_type, n_components):
"""Create all the covariance matrices from a given template."""
if covariance_type == 'spherical':
cv = np.tile(tied_cv.mean() * np.ones(tied_cv.shape[1]),
(n_components, 1))
elif covariance_type == 'tied':
cv = tied_cv
elif covariance_type == 'diag':
cv = np.tile(np.diag(tied_cv), (n_components, 1))
elif covariance_type == 'full':
cv = np.tile(tied_cv, (n_components, 1, 1))
else:
raise ValueError("covariance_type must be one of " +
"'spherical', 'tied', 'diag', 'full'")
return cv
|
