def main():
entity = Entity()
initialize(entity)
print 'Press the Enter key to terminate this time tracking ...'
while True:
enter = raw_input()
if enter == '':
set_stop_time(entity)
break
display_summary(entity)
util.write_results_to_file(entity)
def predict(self, photo_ids, data):
predictions = self.predict_bulk(data)
accuracy = util.compute_test_accuracy(
labels=data[:, -1], predictions=predictions,
)
if self.output_filename is not None:
util.write_results_to_file(
photo_ids=photo_ids,
predictions=predictions,
filepath=self.output_filename,
)
print("Accuracy on test set = %f" % accuracy)
return predictions
def main():
c, d, m = read_problem_file("../data/problem/" + PROBLEM)
population = Population(customers=c,
depots=d,
max_vehicles=m,
size=POPULATION_SIZE,
p_crossover=CROSSOVER_PROBABILITY,
p_intra=INTRA_DEPOT_PROBABILITY,
p_inter=INTER_DEPOT_PROBABILITY,
elites=ELITES)
try:
for generation in range(0, GENERATIONS):
population.evolve()
print("generation:", generation)
population.print_summary()
except KeyboardInterrupt:
print("\nAborting")
finally:
print(population.print_summary())
write_results_to_file(
population.best,
PROBLEM + "-" + str(int(population.best.calculate_distance()[0])))
y_pheno, m, _, estimated_h2 = stepwise.warped_stepwise(Y, X, K, covariates=covar,
max_covariates=options.max_covariates, num_restarts=options.random_restarts,
qv_cutoff=options.qv_cutoff,
pv_cutoff=options.pv_cutoff)
pv, h2 = fastlmm.assoc_scan(y_pheno.copy(), X, covariates=covar, K=K)
if options.out_dir is None:
results_file_name = options.phenotype_file.replace('.txt', '')
results_file_name += "_warpedlmm_results.txt"
else:
results_file_name = options.out_dir + "/warpedlmm_results.txt"
util.write_results_to_file(snp_data, pv, results_file_name)
if options.normal:
pv_base, h2_base = fastlmm.assoc_scan(Y.copy(), X, covariates=covar, K=K)
util.write_results_to_file(snp_data, pv_base, results_file_name.replace('warpedlmm', 'fastlmm'))
if options.save:
if options.out_dir is None:
pheno_file_name = options.phenotype_file.replace('.txt', '')
pheno_file_name += "_warpedlmm_pheno.txt"
trafo_file_name = options.phenotype_file.replace('.txt', '')
trafo_file_name += "_warpedlmm_transformation.png"
else:
pheno_file_name = options.out_dir + "/warpedlmm_pheno.txt"
trafo_file_name = options.out_dir + "/warpedlmm_transformation.png"
K,
covariates=covar,
max_covariates=options.max_covariates,
num_restarts=options.random_restarts,
qv_cutoff=options.qv_cutoff,
pv_cutoff=options.pv_cutoff)
pv, h2 = fastlmm.assoc_scan(y_pheno.copy(), X, covariates=covar, K=K)
if options.out_dir is None:
results_file_name = options.phenotype_file.replace('.txt', '')
results_file_name += "_warpedlmm_results.txt"
else:
results_file_name = options.out_dir + "/warpedlmm_results.txt"
util.write_results_to_file(snp_data, pv, results_file_name)
if options.normal:
pv_base, h2_base = fastlmm.assoc_scan(Y.copy(),
X,
covariates=covar,
K=K)
util.write_results_to_file(
snp_data, pv_base,
results_file_name.replace('warpedlmm', 'fastlmm'))
if options.save:
if options.out_dir is None:
pheno_file_name = options.phenotype_file.replace('.txt', '')
pheno_file_name += "_warpedlmm_pheno.txt"
trafo_file_name = options.phenotype_file.replace('.txt', '')
