I'm currently creating a genetic algorithm and am trying to only get certain values from the ASCII table so the runtime of the algorithm can be a bit faster. In the code below I get the values between 9-127 but I only need the values 9-10, and 32-127 from the ASCII table and I'm not sure on how to exactly only get those specific values. Code below is done in python.
import numpy as np
TARGET_PHRASE = """The smartest and fastest Pixel yet.
Google Tensor: Our first custom-built processor.
The first processor designed by Google and made for Pixel, Tensor makes the new Pixel phones our most powerful yet.
The most advanced Pixel Camera ever.
Capture brilliant color and vivid detail with Pixels best-in-class computational photography and new pro-level lenses.""" # target DNA
POP_SIZE = 4000 # population size
CROSS_RATE = 0.8 # mating probability (DNA crossover)
MUTATION_RATE = 0.00001 # mutation probability
N_GENERATIONS = 100000
DNA_SIZE = len(TARGET_PHRASE)
TARGET_ASCII = np.fromstring(TARGET_PHRASE, dtype=np.uint8) # convert string to number
ASCII_BOUND = [9, 127]
class GA(object):
def __init__(self, DNA_size, DNA_bound, cross_rate, mutation_rate, pop_size):
self.DNA_size = DNA_size
DNA_bound[1] += 1
self.DNA_bound = DNA_bound
self.cross_rate = cross_rate
self.mutate_rate = mutation_rate
self.pop_size = pop_size
self.pop = np.random.randint(*DNA_bound, size=(pop_size, DNA_size)).astype(np.int8) # int8 for convert to ASCII
def translateDNA(self, DNA): # convert to readable string
return DNA.tostring().decode('ascii')
def get_fitness(self): # count how many character matches
match_count = (self.pop == TARGET_ASCII).sum(axis=1)
return match_count
def select(self):
fitness = self.get_fitness() # add a small amount to avoid all zero fitness
idx = np.random.choice(np.arange(self.pop_size), size=self.pop_size, replace=True, p=fitness/fitness.sum())
return self.pop[idx]
def crossover(self, parent, pop):
if np.random.rand() < self.cross_rate:
i_ = np.random.randint(0, self.pop_size, size=1) # select another individual from pop
cross_points = np.random.randint(0, 2, self.DNA_size).astype(np.bool) # choose crossover points
parent[cross_points] = pop[i_, cross_points] # mating and produce one child
return parent
def mutate(self, child):
for point in range(self.DNA_size):
if np.random.rand() < self.mutate_rate:
child[point] = np.random.randint(*self.DNA_bound) # choose a random ASCII index
return child
def evolve(self):
pop = self.select()
pop_copy = pop.copy()
for parent in pop: # for every parent
child = self.crossover(parent, pop_copy)
child = self.mutate(child)
parent[:] = child
self.pop = pop
if __name__ == '__main__':
ga = GA(DNA_size=DNA_SIZE, DNA_bound=ASCII_BOUND, cross_rate=CROSS_RATE,
mutation_rate=MUTATION_RATE, pop_size=POP_SIZE)
for generation in range(N_GENERATIONS):
fitness = ga.get_fitness()
best_DNA = ga.pop[np.argmax(fitness)]
best_phrase = ga.translateDNA(best_DNA)
print('Gen', generation, ': ', best_phrase)
if best_phrase == TARGET_PHRASE:
break
ga.evolve()
You need a customed method to generate random samples in range 9-10, and 32-127, like
def my_rand(pop_size, DNA_size):
bold1=[9,10]
bold2=list(range(32,127))
bold=bold1+bold2
pop = np.random.choice(bold,(pop_size,DNA_size)).astype(np.int8)
return pop
then call this method to replace the line 29, like
delete -- self.pop = np.random.randint(*DNA_bound, size=(pop_size, DNA_size)).astype(np.int8) # int8 for convert to ASCII
call ---self.pop = my_rand(pop_size, DNA_size)