gradient_free_optimizers.optimizers.local.hill_climbing_optimizer.HillClimbingOptimizer._move_climb() - Code Metrics - Inspection of "simpler move_random function + new attributes" - SimonBlanke/Gradient-Free-Optimizers - Measure and Improve Code Quality continuously with Scrutinizer

Passed

Push — master ( d39371...69bf6f )

by Simon

created 2020-08-19 18:43 UTC

HillClimbingOptimizer._move_climb() A

↳ Parent: gradient_free_optimizers.optimizers.local.hill_climbing_optimizer

Complexity

Conditions

Size

Total Lines	10
Code Lines	8

Duplication

Lines	0
Ratio	0 %

Importance

Changes

Metric	Value
cc	1
eloc	8
nop	3
dl	0
loc	10
rs	10
c	0
b	0
f	0

# Author: Simon Blanke
# Email: [email protected]
# License: MIT License

import numpy as np

from ..base_optimizer import BaseOptimizer
from ...search import Search

from numpy.random import normal, laplace, logistic, gumbel

dist_dict = {
    "normal": normal,
    "laplace": laplace,
    "logistic": logistic,
    "gumbel": gumbel,
}


class HillClimbingOptimizer(BaseOptimizer, Search):
    def __init__(
        self, search_space, epsilon=0.05, distribution="normal", n_neighbours=1,
    ):
        super().__init__(search_space)
        self.epsilon = epsilon
        self.distribution = dist_dict[distribution]
        self.n_neighbours = n_neighbours

    def _move_climb(self, pos, epsilon_mod=1):
        sigma = self.space_dim * self.epsilon * epsilon_mod
        pos_normal = self.distribution(pos, sigma, pos.shape)
        pos_new_int = np.rint(pos_normal)

        n_zeros = [0] * len(self.space_dim)
        pos = np.clip(pos_new_int, n_zeros, self.space_dim)

        self.pos_new = pos.astype(int)
        return self.pos_new

    def iterate(self):
        return self._move_climb(self.pos_current)



1			# Author: Simon Blanke
2			# Email: [email protected]
3			# License: MIT License
4
5			import numpy as np
6
7			from ..base_optimizer import BaseOptimizer
8			from ...search import Search
9
10			from numpy.random import normal, laplace, logistic, gumbel
11
12			dist_dict = {
13			"normal": normal,
14			"laplace": laplace,
15			"logistic": logistic,
16			"gumbel": gumbel,
17			}
18
19
20			class HillClimbingOptimizer(BaseOptimizer, Search):
21			def __init__(
22			self, search_space, epsilon=0.05, distribution="normal", n_neighbours=1,
23			):
24			super().__init__(search_space)
25			self.epsilon = epsilon
26			self.distribution = dist_dict[distribution]
27			self.n_neighbours = n_neighbours
28
29			def _move_climb(self, pos, epsilon_mod=1):
30			sigma = self.space_dim * self.epsilon * epsilon_mod
31			pos_normal = self.distribution(pos, sigma, pos.shape)
32			pos_new_int = np.rint(pos_normal)
33
34			n_zeros = [0] * len(self.space_dim)
35			pos = np.clip(pos_new_int, n_zeros, self.space_dim)
36
37			self.pos_new = pos.astype(int)
38			return self.pos_new
39
40			def iterate(self):
41			return self._move_climb(self.pos_current)
42
43

SimonBlanke / Gradient-Free-Optimizers

Push — master ( d39371...69bf6f )

HillClimbingOptimizer._move_climb() A

Complexity

Size

Duplication

Importance

Duplication Side-by-Side

Filter issues like