def guess_password(password_hash: int, num_chars: int,
hash_func: Callable[[str], int]) -> str:
"""Attempt to find the string whose hash matches the given hash via a genetic algorithm.
:param password_hash: The hash for the original password
:param num_chars: How many characters to put in the generated passwords
:param hash_func: The function to be used for hashing; it should take in a string and output its hash
:return: The optimal result produced by the genetic algorithm
"""
def gen_passwords():
"""Generate a list of random passwords."""
population = []
for i in range(500):
char_list = []
for j in range(num_chars):
char_list.append(get_pass_char())
population.append(Password(char_list, password_hash, hash_func))
return population
# Uncomment the lines in main.py if you want to uncomment these
#def time_out():
#print("TIMEOUT ERROR: too much time has passed since beginning the reconstruction. This may have occurred "
#"because you entered an improper password length.")
#input("Press any key to exit.")
#_thread.interrupt_main()
#tmr = Timer(30.0, time_out)
#tmr.start()
best_pass = genetic_algorithm.run(gen_passwords,
lambda best: best.get_fitness() < 1, 0.7,
0.04, 0.6)
#tmr.cancel()
return str(best_pass)
def run(parameters):
global idx
idx += 1
try:
res = ga.run(parameters)
except:
print('An error occuered with ', parameters)
errored_params_pool.append(parameters)
return {}
print('run', idx, parameters, ' - ', res['run_time'])
return res
mutation_probability = 0.1
mutation_rate = 0.1
# algorithm settings
max_iter = 300
k = 10
stop_thrs = 10
mutation_level = 0.2
run_num = 3
run = 1
individual_size = 120
# In[3]:
parameters = [
run, population_size, k,\
fitness_function, crossover_type, crossover_probability, \
elitism_ratio, max_parent_allowance, \
mutation_probability, mutation_rate, max_iter, individual_size,\
stop_thrs, mutation_level \
]
# In[4]:
ga.run(parameters)
# In[ ]:
from genetic_algorithm import run
if __name__ == "__main__":
run()
# Problem Definition
problem = structure()
problem.costfunc = sphere
problem.nvar = 5
problem.varmin = -10
problem.varmax = 10
# GA Parameters
params = structure()
params.maxit = 100
params.npop = 20
params.pc = 1
params.gamma = 0.1
params.mu = 0.2 # como temos 5 genes (nvar), sempre vamos alterar 1 na mutacao
params.sigma = 0.1
# Run GA
out = genetic_algorithm.run(problem, params)
# Results
# plt.plot(out.bestcost)
plt.semilogy(out.bestcost)
plt.xlim(0, params.maxit)
plt.xlabel('Iterations')
plt.ylabel('Best Cost')
plt.title('Genetic Algorithm (GA)')
plt.grid(True)
plt.show()