169 lines
4.6 KiB
Cython
169 lines
4.6 KiB
Cython
# 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]]
|