def run_param_search(problem, output_dir):
rhc = mlrose.RHCRunner(problem=problem,
experiment_name="RHC",
output_directory=output_dir,
seed=42,
iteration_list=2**np.arange(15),
max_attempts=1000,
restart_list=[10])
rhc_run_stats, rhc_run_curves = rhc.run()
sa = mlrose.SARunner(problem=problem,
experiment_name="SA",
output_directory=output_dir,
seed=42,
iteration_list=2**np.arange(20),
max_attempts=1000,
temperature_list=[100, 250, 500],
decay_list=[mlrose.ExpDecay, mlrose.GeomDecay])
sa_run_stats, sa_run_curves = sa.run()
ga = mlrose.GARunner(problem=problem,
experiment_name="GA",
output_directory=output_dir,
seed=42,
iteration_list=2**np.arange(13),
max_attempts=1000,
population_sizes=[100, 200, 300],
mutation_rates=[0.1, 0.2, 0.3])
ga_run_stats, ga_run_curves = ga.run()
mimic = mlrose.MIMICRunner(problem=problem,
experiment_name="MIMIC",
output_directory=output_dir,
seed=42,
iteration_list=2**np.arange(13),
population_sizes=[100, 200, 300],
max_attempts=500,
keep_percent_list=[0.1, 0.2, 0.3],
use_fast_mimic=True)
mimic_run_stats, mimic_run_curves = mimic.run()
experiment_name=expName,
output_directory=OUTPUT_DIRECTORY,
seed=RANDOM_STATE,
iteration_list=iList,
population_sizes=[100, 200, 300, 400, 500],
mutation_rates=[0.3, 0.4, 0.5, 0.6, 0.7],
verbose=False)
experiments.append(ga)
# s,c = ga.run()
# results.append([s,c])
# MIMIC
if not os.path.isfile(os.path.join(sys.path[0],'Output', expName, f'mimic__{expName}__curves_df.csv')):
mc = mlr.MIMICRunner(problem=problem,
experiment_name=expName,
output_directory=OUTPUT_DIRECTORY,
seed=RANDOM_STATE,
iteration_list=iList,
population_sizes=[50, 125, 200, 275, 350],
keep_percent_list=[0.25, 0.5, 0.75],
verbose=False)
experiments.append(mc)
# s,c = mc.run()
# results.append([s,c])
# experiments is 6 * 3 * 4 = 72 experiments long....
print(len(experiments))
print(np.array([[exp.dynamic_runner_name() + exp._experiment_name for exp in experiments]]).T)
if input('Continue... >') == 'y':
pass
else:
quit()
print('Running all experiments...')
max_attempts=max_attempts,
max_iters=max_iters,
random_state=random_state,
pop_size=pop_size,
mutation_prob=mutation_prob,
curve=True)
print("Genetic Alg - Total Function Evaluations:", eval_count)
plot_fitness_iteration('fitness_iteration_ga_queens.png',gen_curve,
"Queens - Genetic Alg: mutation_prob: {}, pop_size: {}".format(mutation_prob, pop_size))
# MIMIC
mim = mlrh.MIMICRunner(problem=prob,
experiment_name=experiment_name,
output_directory=output_directory,
seed=random_state,
population_sizes=[50, 100, 200],
keep_percent_list=[0.1, 0.25, 0.5, 0.75],
iteration_list=[50],
use_fast_mimic=True)
mim_stats, mim_curve = mim.run()
columns = ['Time', 'Fitness', 'Population Size', 'Keep Percent']
df=pd.read_csv("./queen/queen_prob/mimic__queen_prob__run_stats_df.csv")
print(df[columns].sort_values(by=['Fitness'], ascending=False))
max_attempts = 10
max_iters = 25
keep_pct=0.25
pop_size = 200
eval_count = 0
best_state, best_fitness, mimic_curve = mlrh.mimic(prob,
lengths_experiment = [2**x for x in range(10)]
for length in lengths_experiment:
problem = mlrose.DiscreteOpt(length=length,
fitness_fn=fitness,
maximize=True,
max_val=2)
output_dir2 = os.path.join(
this_dir, problem_name + '_MIMIC_length', str(length)
) #r"C:\Users\AREHAN2\Documents\omscs\CS7641\randomized_optimization\4peaks_GA_length\\" + str(length)
mimic = mlrose.MIMICRunner(problem=problem,
experiment_name="MIMIC",
output_directory=output_dir2,
seed=42,
iteration_list=2**np.arange(13),
population_sizes=[300],
max_attempts=500,
keep_percent_list=[0.2],
use_fast_mimic=True)
mimic_run_stats, mimic_run_curves = mimic.run()
#===================================================================================================
# STEP6: PLOT PERFORMANCE FROM STEP#4 AND STEP#5
#===================================================================================================
fig, ax = plt.subplots(1, 3, figsize=(17, 4))
param_search.plot_best_models(ga_best, sa_best, rhc_best, mimic_best, ax,
problem_name)
#plt.show()
max_iteartions_needed = []