|
1
|
|
|
# encoding=utf8 |
|
2
|
|
|
import logging |
|
3
|
|
|
|
|
4
|
|
|
import numpy as np |
|
5
|
|
|
|
|
6
|
|
|
from NiaPy.algorithms.algorithm import Algorithm |
|
7
|
|
|
|
|
8
|
|
|
logging.basicConfig() |
|
9
|
|
|
logger = logging.getLogger('NiaPy.algorithms.other') |
|
10
|
|
|
logger.setLevel('INFO') |
|
11
|
|
|
|
|
12
|
|
|
__all__ = ['RandomSearch'] |
|
13
|
|
|
|
|
14
|
|
|
class RandomSearch(Algorithm): |
|
15
|
|
|
r"""Implementation of a simple Random Algorithm. |
|
16
|
|
|
|
|
17
|
|
|
Algorithm: |
|
18
|
|
|
Random Search |
|
19
|
|
|
|
|
20
|
|
|
Date: |
|
21
|
|
|
11.10.2020 |
|
22
|
|
|
|
|
23
|
|
|
Authors: |
|
24
|
|
|
Iztok Fister Jr., Grega Vrbančič |
|
25
|
|
|
|
|
26
|
|
|
License: |
|
27
|
|
|
MIT |
|
28
|
|
|
|
|
29
|
|
|
Reference URL: https://en.wikipedia.org/wiki/Random_search |
|
30
|
|
|
|
|
31
|
|
|
Attributes: |
|
32
|
|
|
Name (List[str]): List of strings representing algorithm name. |
|
33
|
|
|
|
|
34
|
|
|
See Also: |
|
35
|
|
|
* :class:`NiaPy.algorithms.Algorithm` |
|
36
|
|
|
""" |
|
37
|
|
|
Name = ['RandomSearch', 'RS'] |
|
38
|
|
|
|
|
39
|
|
|
@staticmethod |
|
40
|
|
|
def algorithmInfo(): |
|
41
|
|
|
r"""Get basic information of algorithm. |
|
42
|
|
|
|
|
43
|
|
|
Returns: |
|
44
|
|
|
str: Basic information of algorithm. |
|
45
|
|
|
|
|
46
|
|
|
See Also: |
|
47
|
|
|
* :func:`NiaPy.algorithms.Algorithm.algorithmInfo` |
|
48
|
|
|
""" |
|
49
|
|
|
return r"""None""" |
|
50
|
|
|
|
|
51
|
|
|
def setParameters(self): |
|
52
|
|
|
r"""Set the algorithm parameters/arguments. |
|
53
|
|
|
|
|
54
|
|
|
Arguments: |
|
55
|
|
|
See Also |
|
56
|
|
|
* :func:`NiaPy.algorithms.Algorithm.setParameters` |
|
57
|
|
|
""" |
|
58
|
|
|
|
|
59
|
|
|
Algorithm.setParameters(self, NP=1) |
|
60
|
|
|
|
|
61
|
|
|
def getParameters(self): |
|
62
|
|
|
r"""Get algorithms parametes values. |
|
63
|
|
|
|
|
64
|
|
|
Returns: |
|
65
|
|
|
Dict[str, Any]: |
|
66
|
|
|
See Also |
|
67
|
|
|
* :func:`NiaPy.algorithms.Algorithm.getParameters` |
|
68
|
|
|
""" |
|
69
|
|
|
d = Algorithm.getParameters(self) |
|
70
|
|
|
return d |
|
71
|
|
|
|
|
72
|
|
|
def initPopulation(self, task): |
|
73
|
|
|
r"""Initialize the starting population. |
|
74
|
|
|
|
|
75
|
|
|
Args: |
|
76
|
|
|
task (Task): Optimization task. |
|
77
|
|
|
Returns: |
|
78
|
|
|
Tuple[numpy.ndarray, float, dict]: |
|
79
|
|
|
1. Initial solution |
|
80
|
|
|
2. Initial solutions fitness/objective value |
|
81
|
|
|
3. Additional arguments |
|
82
|
|
|
""" |
|
83
|
|
|
total_candidates = 0 |
|
84
|
|
|
if task.nGEN or task.nFES: |
|
85
|
|
|
total_candidates = task.nGEN if task.nGEN else task.nFES |
|
86
|
|
|
self.candidates = [] |
|
87
|
|
|
for i in range(total_candidates): |
|
88
|
|
|
while True: |
|
89
|
|
|
x = task.Lower + task.bcRange() * self.rand(task.D) |
|
90
|
|
|
if not np.any([np.all(a == x) for a in self.candidates]): |
|
91
|
|
|
self.candidates.append(x) |
|
92
|
|
|
break |
|
93
|
|
|
|
|
94
|
|
|
xfit = task.eval(self.candidates[0]) |
|
95
|
|
|
return x, xfit, {} |
|
|
|
|
|
|
96
|
|
|
|
|
97
|
|
|
def runIteration(self, task, x, xfit, xb, fxb, **dparams): |
|
98
|
|
|
r"""Core function of the algorithm. |
|
99
|
|
|
|
|
100
|
|
|
Args: |
|
101
|
|
|
task (Task): |
|
102
|
|
|
x (numpy.ndarray): |
|
103
|
|
|
xfit (float): |
|
104
|
|
|
xb (numpy.ndarray): |
|
105
|
|
|
fxb (float): |
|
106
|
|
|
**dparams (dict): Additional arguments. |
|
107
|
|
|
|
|
108
|
|
|
Returns: |
|
109
|
|
|
Tuple[numpy.ndarray, float, numpy.ndarray, float, dict]: |
|
110
|
|
|
1. New solution |
|
111
|
|
|
2. New solutions fitness/objective value |
|
112
|
|
|
3. New global best solution |
|
113
|
|
|
4. New global best solutions fitness/objective value |
|
114
|
|
|
5. Additional arguments |
|
115
|
|
|
""" |
|
116
|
|
|
current_candidate = task.Evals if task.Evals else task.Iters |
|
117
|
|
|
x = self.candidates[current_candidate] |
|
118
|
|
|
xfit = task.eval(x) |
|
119
|
|
|
xb, fxb = self.getBest(x, xfit, xb, fxb) |
|
120
|
|
|
return x, xfit, xb, fxb, {} |
|
121
|
|
|
|
NiaOrg /
NiaPy
Loading history...