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
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
|
# Author: Mathieu Blondel
# Olivier Grisel
#
# License: BSD Style.
cimport numpy as np
import numpy as np
cimport cython
cdef extern from "math.h":
double fabs(double f)
double sqrt(double f)
ctypedef np.float64_t DOUBLE
@cython.boundscheck(False)
@cython.wraparound(False)
@cython.cdivision(True)
def mean_variance_axis0(X):
"""Compute mean and variance along axis 0 on a CSR matrix
Parameters
----------
X: CSR sparse matrix, shape (n_samples, n_features)
Input data.
Returns
-------
means: float array with shape (n_features,)
Feature-wise means
variances: float array with shape (n_features,)
Feature-wise variances
"""
cdef unsigned int n_samples = X.shape[0]
cdef unsigned int n_features = X.shape[1]
cdef np.ndarray[DOUBLE, ndim=1] X_data = X.data
cdef np.ndarray[int, ndim=1] X_indices = X.indices
cdef np.ndarray[int, ndim=1] X_indptr = X.indptr
cdef unsigned int i
cdef unsigned int j
cdef unsigned int ind
cdef double diff
# means[j] contains the mean of feature j
cdef np.ndarray[DOUBLE, ndim=1] means = np.asarray(X.mean(axis=0))[0]
# variances[j] contains the variance of feature j
cdef np.ndarray[DOUBLE, ndim=1] variances = np.zeros_like(means)
# counts[j] contains the number of samples where feature j is non-zero
counts = np.zeros_like(means)
for i in xrange(n_samples):
for j in xrange(X_indptr[i], X_indptr[i + 1]):
ind = X_indices[j]
diff = X_data[j] - means[ind]
variances[ind] += diff * diff
counts[ind] += 1
nz = n_samples - counts
variances += nz * means ** 2
variances /= n_samples
return means, variances
@cython.boundscheck(False)
@cython.wraparound(False)
@cython.cdivision(True)
def inplace_csr_row_normalize_l1(X):
"""Inplace row normalize using the l1 norm"""
cdef unsigned int n_samples = X.shape[0]
cdef unsigned int n_features = X.shape[1]
cdef np.ndarray[DOUBLE, ndim=1] X_data = X.data
cdef np.ndarray[int, ndim=1] X_indices = X.indices
cdef np.ndarray[int, ndim=1] X_indptr = X.indptr
# the column indices for row i are stored in:
# indices[indptr[i]:indices[i+1]]
# and their corresponding values are stored in:
# data[indptr[i]:indptr[i+1]]
cdef unsigned int i
cdef unsigned int j
cdef double sum_
for i in xrange(n_samples):
sum_ = 0.0
for j in xrange(X_indptr[i], X_indptr[i + 1]):
sum_ += fabs(X_data[j])
if sum_ == 0.0:
# do not normalize empty rows (can happen if CSR is not pruned
# correctly)
continue
for j in xrange(X_indptr[i], X_indptr[i + 1]):
X_data[j] /= sum_
@cython.boundscheck(False)
@cython.wraparound(False)
@cython.cdivision(True)
def inplace_csr_row_normalize_l2(X):
"""Inplace row normalize using the l2 norm"""
cdef unsigned int n_samples = X.shape[0]
cdef unsigned int n_features = X.shape[1]
cdef np.ndarray[DOUBLE, ndim=1] X_data = X.data
cdef np.ndarray[int, ndim=1] X_indices = X.indices
cdef np.ndarray[int, ndim=1] X_indptr = X.indptr
cdef unsigned int i
cdef unsigned int j
cdef double sum_
for i in xrange(n_samples):
sum_ = 0.0
for j in xrange(X_indptr[i], X_indptr[i + 1]):
sum_ += (X_data[j] * X_data[j])
if sum_ == 0.0:
# do not normalize empty rows (can happen if CSR is not pruned
# correctly)
continue
sum_ = sqrt(sum_)
for j in xrange(X_indptr[i], X_indptr[i + 1]):
X_data[j] /= sum_
@cython.boundscheck(False)
@cython.wraparound(False)
@cython.cdivision(True)
def inplace_csr_column_scale(X, np.ndarray[DOUBLE, ndim=1] scale):
"""Inplace column scaling of a CSR matrix.
Scale each feature of the data matrix by multiplying with specific scale
provided by the caller assuming a (n_samples, n_features) shape.
Parameters
----------
X: CSR matrix with shape (n_samples, n_features)
Matrix to normalize using the variance of the features.
scale: float array with shape (n_features,)
Array of precomputed feature-wise values to use for scaling.
"""
cdef unsigned int n_samples = X.shape[0]
cdef unsigned int n_features = X.shape[1]
cdef np.ndarray[DOUBLE, ndim=1] X_data = X.data
cdef np.ndarray[int, ndim=1] X_indices = X.indices
cdef np.ndarray[int, ndim=1] X_indptr = X.indptr
cdef unsigned int i, j
for i in xrange(n_samples):
for j in xrange(X_indptr[i], X_indptr[i + 1]):
X_data[j] *= scale[X_indices[j]]
|
