def run_automl(input_dir, output_dir, data_name, time_budget, running_on_codalab):
print('input_dir = "%s"' % input_dir)
print('output_dir = "%s"' % output_dir)
print('data_name = "%s"' % data_name)
print('time_budget = %s' % time_budget)
try:
# automl.data_doubling_rf(input_dir, output_dir, data_name, time_budget, 20)
# automl.cv_growing_rf(input_dir, output_dir, data_name, time_budget)
# automl.cv_growing_rf_gbm(input_dir, output_dir, data_name, time_budget)
# automl.competition_example(input_dir, output_dir, data_name, time_budget)
# automl.competition_example_only_rf(input_dir, output_dir, data_name, time_budget)
# automl.freeze_thaw_cv_rf(input_dir, output_dir, data_name, time_budget)
# automl.freeze_thaw_cv_rf_gbm(input_dir, output_dir, data_name, time_budget, compute_quantum=10)
# automl.automl_phase_0(input_dir, output_dir, data_name, time_budget)
# mgr = managers.FixedLearnersFreezeThawManager(input_dir=input_dir, output_dir=output_dir,
# basename=data_name, time_budget=time_budget,
# compute_quantum=None, plot=not running_on_codalab, min_mem=4,
# n_folds=5)
exp = dict()
exp = experiment.exp_param_defaults(exp)
mgr = managers.FixedLearnersStackingManager(input_dir=input_dir, output_dir=output_dir,
basename=data_name, time_budget=time_budget,
compute_quantum=None, plot=not running_on_codalab,
n_folds=5,
overhead_memory=constants.OVERHEAD,
cgroup_soft_limit=constants.CGROUP_SOFT_LIMIT,
cgroup_hard_limit=constants.CGROUP_HARD_LIMIT,
exp=exp)
mgr.communicate()
except:
traceback.print_exc()
def timing_triple_cloud():
execfile('picloud_venture_credentials.py')
exp_params = experiment.exp_param_defaults({})
exp_params['intermediate_iter'] = 1
exp_params['max_initial_run_time'] = 30
exp_params['max_burn_time'] = 30
exp_params['max_sample_time'] = 30
exp_params['n_samples'] = 25
print experiment.exp_params_to_str(exp_params)
data = scipy.io.loadmat("../data/irm_synth/irm_synth_20.mat", squeeze_me=True)
observed = list(zip(data['train_i'].flat, data['train_j'].flat, data['train_v'].flat))
missing = list(zip(data['test_i'].flat, data['test_j'].flat, data['test_v'].flat))
data = {'observations' : observed, 'missing' : missing}
model = models.product_IRM
model_params = {'D' : 1, 'alpha' : 1, 'symmetric' : True}
# Timing run
print 'Timing'
job_id = cloud.call(experiment.network_cv_timing_run, data, model, exp_params, model_params, _max_runtime=5, _env=cloud_environment)
time_per_mh_iter = cloud.result(job_id)['time_per_mh_iter']
# Live run
print 'Live'
exp_params['intermediate_iter'] = max(1, int(round(0.9 * exp_params['max_sample_time'] / (exp_params['n_samples'] * time_per_mh_iter))))
job_id = cloud.call(experiment.network_cv_single_run, data, model, exp_params, model_params, _max_runtime=5, _env=cloud_environment)
cloud.join(job_id)
print cloud.result(job_id)
def timing_run_local():
exp_params = experiment.exp_param_defaults({})
exp_params['intermediate_iter'] = 1
exp_params['max_initial_run_time'] = 30
print experiment.exp_params_to_str(exp_params)
data = scipy.io.loadmat("../data/irm_synth/irm_synth_20.mat", squeeze_me=True)
observed = list(zip(data['train_i'].flat, data['train_j'].flat, data['train_v'].flat))
missing = list(zip(data['test_i'].flat, data['test_j'].flat, data['test_v'].flat))
data = {'observations' : observed, 'missing' : missing}
model = models.product_IRM
model_params = {'D' : 1, 'alpha' : 1, 'symmetric' : True}
print experiment.network_cv_timing_run(data, model, exp_params, model_params)
def fold(unused=None):
execfile('picloud_venture_credentials.py')
data_file = '../data/irm_synth/irm_synth_20.mat'
data_dir = '../data/irm_synth/'
model = models.product_IRM
model_params = {'D' : 1, 'alpha' : 1, 'symmetric' : True}
exp_params = experiment.exp_param_defaults({})
exp_params['intermediate_iter'] = 1
exp_params['max_initial_run_time'] = 20
exp_params['max_burn_time'] = 10
exp_params['max_sample_time'] = 20
exp_params['n_samples'] = 25
exp_params['n_restarts'] = 3
print experiment.exp_params_to_str(exp_params)
print experiment.network_cv_fold(data_file, data_dir, model, exp_params, model_params)
def timing_run_cloud():
execfile('picloud_venture_credentials.py')
exp_params = experiment.exp_param_defaults({})
exp_params['intermediate_iter'] = 1
exp_params['max_initial_run_time'] = 30
print experiment.exp_params_to_str(exp_params)
data = scipy.io.loadmat("../data/irm_synth/irm_synth_20.mat", squeeze_me=True)
observed = list(zip(data['train_i'].flat, data['train_j'].flat, data['train_v'].flat))
missing = list(zip(data['test_i'].flat, data['test_j'].flat, data['test_v'].flat))
data = {'observations' : observed, 'missing' : missing}
model = models.product_IRM
model_params = {'D' : 1, 'alpha' : 1, 'symmetric' : True}
job_id = cloud.call(experiment.network_cv_timing_run, data, model, exp_params, model_params, _max_runtime=5, _env=cloud_environment)
cloud.join(job_id)
print cloud.result(job_id)
def run_automl(input_dir, output_dir, data_name, time_budget,
running_on_codalab):
print('input_dir = "%s"' % input_dir)
print('output_dir = "%s"' % output_dir)
print('data_name = "%s"' % data_name)
print('time_budget = %s' % time_budget)
try:
# automl.data_doubling_rf(input_dir, output_dir, data_name, time_budget, 20)
# automl.cv_growing_rf(input_dir, output_dir, data_name, time_budget)
# automl.cv_growing_rf_gbm(input_dir, output_dir, data_name, time_budget)
# automl.competition_example(input_dir, output_dir, data_name, time_budget)
# automl.competition_example_only_rf(input_dir, output_dir, data_name, time_budget)
# automl.freeze_thaw_cv_rf(input_dir, output_dir, data_name, time_budget)
# automl.freeze_thaw_cv_rf_gbm(input_dir, output_dir, data_name, time_budget, compute_quantum=10)
# automl.automl_phase_0(input_dir, output_dir, data_name, time_budget)
# mgr = managers.FixedLearnersFreezeThawManager(input_dir=input_dir, output_dir=output_dir,
# basename=data_name, time_budget=time_budget,
# compute_quantum=None, plot=not running_on_codalab, min_mem=4,
# n_folds=5)
exp = dict()
exp = experiment.exp_param_defaults(exp)
mgr = managers.FixedLearnersStackingManager(
input_dir=input_dir,
output_dir=output_dir,
basename=data_name,
time_budget=time_budget,
compute_quantum=None,
plot=not running_on_codalab,
n_folds=5,
overhead_memory=constants.OVERHEAD,
cgroup_soft_limit=constants.CGROUP_SOFT_LIMIT,
cgroup_hard_limit=constants.CGROUP_HARD_LIMIT,
exp=exp)
mgr.communicate()
except:
traceback.print_exc()
def timing_triple_local():
exp_params = experiment.exp_param_defaults({})
exp_params['intermediate_iter'] = 1
exp_params['max_initial_run_time'] = 30
exp_params['max_burn_time'] = 30
exp_params['max_sample_time'] = 30
exp_params['n_samples'] = 25
print experiment.exp_params_to_str(exp_params)
data = scipy.io.loadmat("../data/irm_synth/irm_synth_20.mat", squeeze_me=True)
observed = list(zip(data['train_i'].flat, data['train_j'].flat, data['train_v'].flat))
missing = list(zip(data['test_i'].flat, data['test_j'].flat, data['test_v'].flat))
data = {'observations' : observed, 'missing' : missing}
model = models.product_IRM
model_params = {'D' : 1, 'alpha' : 1, 'symmetric' : True}
# Timing run
time_per_mh_iter = experiment.network_cv_timing_run(data, model, exp_params, model_params)['time_per_mh_iter']
# Live run
exp_params['intermediate_iter'] = max(1, int(round(0.9 * exp_params['max_sample_time'] / (exp_params['n_samples'] * time_per_mh_iter))))
print experiment.network_cv_single_run(data, model, exp_params, model_params)
