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
|
"""Utilities that are required by gplearn.
Most of these functions are slightly modified versions of some key utility
functions from scikit-learn that gplearn depends upon. They reside here in
order to maintain compatibility across different versions of scikit-learn.
"""
import importlib.metadata
import numbers
import numpy as np
from joblib import cpu_count
from packaging.version import Version
def _sklearn_version_ge(min_version):
"""Check whether we have at least min_version of scikit-learn."""
sklearn_version = importlib.metadata.version("scikit-learn")
return Version(sklearn_version) >= Version(min_version)
def check_random_state(seed):
"""Turn seed into a np.random.RandomState instance
Parameters
----------
seed : None | int | instance of RandomState
If seed is None, return the RandomState singleton used by np.random.
If seed is an int, return a new RandomState instance seeded with seed.
If seed is already a RandomState instance, return it.
Otherwise raise ValueError.
"""
if seed is None or seed is np.random:
return np.random.mtrand._rand
if isinstance(seed, (numbers.Integral, np.integer)):
return np.random.RandomState(seed)
if isinstance(seed, np.random.RandomState):
return seed
raise ValueError('%r cannot be used to seed a numpy.random.RandomState'
' instance' % seed)
def _get_n_jobs(n_jobs):
"""Get number of jobs for the computation.
This function reimplements the logic of joblib to determine the actual
number of jobs depending on the cpu count. If -1 all CPUs are used.
If 1 is given, no parallel computing code is used at all, which is useful
for debugging. For n_jobs below -1, (n_cpus + 1 + n_jobs) are used.
Thus for n_jobs = -2, all CPUs but one are used.
Parameters
----------
n_jobs : int
Number of jobs stated in joblib convention.
Returns
-------
n_jobs : int
The actual number of jobs as positive integer.
"""
if n_jobs < 0:
return max(cpu_count() + 1 + n_jobs, 1)
elif n_jobs == 0:
raise ValueError('Parameter n_jobs == 0 has no meaning.')
else:
return n_jobs
def _partition_estimators(n_estimators, n_jobs):
"""Private function used to partition estimators between jobs."""
# Compute the number of jobs
n_jobs = min(_get_n_jobs(n_jobs), n_estimators)
# Partition estimators between jobs
n_estimators_per_job = (n_estimators // n_jobs) * np.ones(n_jobs,
dtype=int)
n_estimators_per_job[:n_estimators % n_jobs] += 1
starts = np.cumsum(n_estimators_per_job)
return n_jobs, n_estimators_per_job.tolist(), [0] + starts.tolist()
|
