genetic_algorithm.basic_string

Simple multithreaded algorithm to show how the 4 phases of a genetic algorithm works (Evaluation, Selection, Crossover and Mutation) https://en.wikipedia.org/wiki/Genetic_algorithm Author: D4rkia

Attributes

MUTATION_PROBABILITY
N_POPULATION
N_SELECTED
target_str

Functions

basic(→ tuple[int, int, str])	Verify that the target contains no genes besides the ones inside genes variable.
crossover(→ tuple[str, str])	Slice and combine two strings at a random point.
evaluate(→ tuple[str, float])	Evaluate how similar the item is with the target by just
mutate(→ str)	Mutate a random gene of a child with another one from the list.
select(→ list[str])	Select the second parent and generate new population

Module Contents

genetic_algorithm.basic_string.basic(target: str, genes: list[str], debug: bool = True) → tuple[int, int, str]

Verify that the target contains no genes besides the ones inside genes variable.

>>> from string import ascii_lowercase
>>> basic("doctest", ascii_lowercase, debug=False)[2]
'doctest'
>>> genes = list(ascii_lowercase)
>>> genes.remove("e")
>>> basic("test", genes)
Traceback (most recent call last):
    ...
ValueError: ['e'] is not in genes list, evolution cannot converge
>>> genes.remove("s")
>>> basic("test", genes)
Traceback (most recent call last):
    ...
ValueError: ['e', 's'] is not in genes list, evolution cannot converge
>>> genes.remove("t")
>>> basic("test", genes)
Traceback (most recent call last):
    ...
ValueError: ['e', 's', 't'] is not in genes list, evolution cannot converge

genetic_algorithm.basic_string.crossover(parent_1: str, parent_2: str) → tuple[str, str]

Slice and combine two strings at a random point. >>> random.seed(42) >>> crossover(“123456”, “abcdef”) (‘12345f’, ‘abcde6’)

genetic_algorithm.basic_string.evaluate(item: str, main_target: str) → tuple[str, float]

Evaluate how similar the item is with the target by just counting each char in the right position >>> evaluate(“Helxo Worlx”, “Hello World”) (‘Helxo Worlx’, 9.0)

genetic_algorithm.basic_string.mutate(child: str, genes: list[str]) → str

Mutate a random gene of a child with another one from the list. >>> random.seed(123) >>> mutate(“123456”, list(“ABCDEF”)) ‘12345A’

genetic_algorithm.basic_string.select(parent_1: tuple[str, float], population_score: list[tuple[str, float]], genes: list[str]) → list[str]

Select the second parent and generate new population

>>> random.seed(42)
>>> parent_1 = ("123456", 8.0)
>>> population_score = [("abcdef", 4.0), ("ghijkl", 5.0), ("mnopqr", 7.0)]
>>> genes = list("ABCDEF")
>>> child_n = int(min(parent_1[1] + 1, 10))
>>> population = []
>>> for _ in range(child_n):
...     parent_2 = population_score[random.randrange(len(population_score))][0]
...     child_1, child_2 = crossover(parent_1[0], parent_2)
...     population.extend((mutate(child_1, genes), mutate(child_2, genes)))
>>> len(population) == (int(parent_1[1]) + 1) * 2
True

genetic_algorithm.basic_string.MUTATION_PROBABILITY = 0.4

genetic_algorithm.basic_string.N_POPULATION = 200

genetic_algorithm.basic_string.N_SELECTED = 50

genetic_algorithm.basic_string.target_str = 'This is a genetic algorithm to evaluate, combine, evolve, and mutate a string!'