forked from scikit-learn/scikit-learn
-
Notifications
You must be signed in to change notification settings - Fork 0
/
_binning.pyx
73 lines (61 loc) · 2.42 KB
/
_binning.pyx
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
# Author: Nicolas Hug
cimport cython
import numpy as np
from numpy.math cimport INFINITY
from cython.parallel import prange
from libc.math cimport isnan
from .common cimport X_DTYPE_C, X_BINNED_DTYPE_C
def _map_to_bins(const X_DTYPE_C [:, :] data,
list binning_thresholds,
const unsigned char missing_values_bin_idx,
int n_threads,
X_BINNED_DTYPE_C [::1, :] binned):
"""Bin continuous and categorical values to discrete integer-coded levels.
A given value x is mapped into bin value i iff
thresholds[i - 1] < x <= thresholds[i]
Parameters
----------
data : ndarray, shape (n_samples, n_features)
The data to bin.
binning_thresholds : list of arrays
For each feature, stores the increasing numeric values that are
used to separate the bins.
n_threads : int
Number of OpenMP threads to use.
binned : ndarray, shape (n_samples, n_features)
Output array, must be fortran aligned.
"""
cdef:
int feature_idx
for feature_idx in range(data.shape[1]):
_map_col_to_bins(data[:, feature_idx],
binning_thresholds[feature_idx],
missing_values_bin_idx,
n_threads,
binned[:, feature_idx])
cdef void _map_col_to_bins(const X_DTYPE_C [:] data,
const X_DTYPE_C [:] binning_thresholds,
const unsigned char missing_values_bin_idx,
int n_threads,
X_BINNED_DTYPE_C [:] binned):
"""Binary search to find the bin index for each value in the data."""
cdef:
int i
int left
int right
int middle
for i in prange(data.shape[0], schedule='static', nogil=True,
num_threads=n_threads):
if isnan(data[i]):
binned[i] = missing_values_bin_idx
else:
# for known values, use binary search
left, right = 0, binning_thresholds.shape[0]
while left < right:
# equal to (right + left - 1) // 2 but avoids overflow
middle = left + (right - left - 1) // 2
if data[i] <= binning_thresholds[middle]:
right = middle
else:
left = middle + 1
binned[i] = left