def get_pyfanova_obj(self, improvement_over='DEFAULT', check_scenario_files = True, heap_size=8192):
try:
import pyfanova.fanova
self.merged_dir = os.path.join(self.output_dir,"merged_run")
# delete existing merged run folder
if os.path.exists(self.merged_dir):
import shutil
shutil.rmtree(self.merged_dir)
from pysmac.utils.state_merge import state_merge
print(os.path.join(self.scenario_output_dir, 'state-run*'))
print(glob.glob(os.path.join(self.scenario_output_dir, 'state-run*')))
state_merge(glob.glob(os.path.join(self.scenario_output_dir, 'state-run*')),
self.merged_dir, check_scenario_files = check_scenario_files)
return(pyfanova.fanova.Fanova(self.merged_dir, improvement_over=improvement_over,heap_size=heap_size))
except ImportError:
raise
raise NotImplementedError('To use this feature, please install the pyfanova package.')
except:
print('Something went during the initialization of the FANOVA.')
raise
def smac_to_fanova(state_run_directory, destination_dir):
'''
Takes the state-run files, merges them and prepares the configuration space for fANOVA.
outputs: fANOVA object
state_run_directory: str
path to the directory of the pysmac_output/out/scenario file
destination_dir: str
path to the directory in which the merged states should be stored
'''
state_run_list =[]
files = glob(state_run_directory + "/*")
for file in files:
if file.startswith(state_run_directory + "/state-run"):
state_run_list.append(file)
state_merge.state_merge(state_run_list, destination_dir)
merged_files = glob(destination_dir + '/*')
for file in merged_files:
if file.startswith(destination_dir + '/runs_and_results'):
response_file = file
if file.startswith(destination_dir + '/paramstrings'):
paramstrings = file
param_dict = output_reader.read_paramstrings_file(paramstrings)
num_line = str(param_dict[0]).replace("'", "")
num_line = str(num_line).replace("}", "")
# messy way to get the parameter names wrt order
f_params = []
for line in str(num_line).split(" "):
line = str(line).replace(",", "")
line = line.replace('{', '')
if ':' in line:
parameter = line.replace(':', '')
f_params.append(parameter)
# get configspace
with open(destination_dir + '/param.pcs') as fh:
cs = pcs_new.read(fh.readlines(), debug=True)
X = []
hps = cs.get_hyperparameters()
for p in param_dict:
c = CS.Configuration(cs, fix_types(p, cs), allow_inactive_with_values=True)
X.append([])
for hp in hps:
if hasattr(hp, 'choices'):
value = hp.choices.index(c[hp.name])
else:
value = c[hp.name]
X[-1].append(value)
X = np.array(X)
Y = data_extractor(response_file, X.shape[0])
return fanova.fANOVA(X = X, Y = Y, config_space= cs)
def run_ISMAC(source_dir, function_file, working_dir, python_executable='python3',
verbosity='ERROR', seed=None,
exploration_time_budget=np.float('inf'),
per_partition_time=60,
init_rand_exploration_evaluations=20,
init_default_evaluations=5,
exploration_evaluations=20,
insts_for_PEI=5,
max_num_partitions=4,
min_partition_size=4,
tae_str='old', # options 'aclib', 'old'
save_rounds=False,
regularize=False,
modus='SMAC', # other choice 'ROAR'
only_use_known_configs=False,
budget_strat="equal" # other choice 'inc' for increasing
):
state_run_directory = os.path.join(source_dir, 'out/scenario')
merge_dir = os.path.join(working_dir, "scenario")
state_run_list = glob.glob(state_run_directory + "/state-run*")
state_merge.state_merge(state_run_list, merge_dir)
# copy necessary files
with open(merge_dir + '/scenario.txt', "r") as inputfile:
with open(working_dir + '/piac_scenario.txt', "w") as outputfile:
for line in inputfile:
header, rest = line.split(" ", 1)
if not header in ['output-dir', 'algo-exec', 'algo-exec-dir', 'run-obj']:
outputfile.write(line)
if header == 'run-obj':
outputfile.write(" ".join([header, rest.lower()]))
outputfile.write('algo-exec-dir = %s \n' %(working_dir))
outputfile.write('algo-exec = %s %s' %(python_executable, function_file))
scenario_file = working_dir + '/piac_scenario.txt'
#shutil.copyfile(source_dir+'/features.dat', working_dir+'/features.dat')
if seed is None:
seed = np.random.seed()
model = kraken(scen_file=scenario_file, per_partition_time=per_partition_time,
working_dir=working_dir, verbosity=verbosity, seed=seed,
exploration_time_budget=exploration_time_budget,
init_rand_exploration_evaluations=init_rand_exploration_evaluations,
init_default_evaluations=init_default_evaluations,
exploration_evaluations=exploration_evaluations, insts_for_PEI=insts_for_PEI,
max_num_partitions=max_num_partitions, tae_str=tae_str, save_rounds=save_rounds,
min_partition_size=min_partition_size, regularize=regularize, modus=modus,
only_known_configs=only_use_known_configs, budget_strat=budget_strat)
return(model)
def get_pyfanova_obj(self,
improvement_over='DEFAULT',
check_scenario_files=True,
heap_size=8192):
try:
import pyfanova.fanova
self.merged_dir = os.path.join(self.output_dir, "merged_run")
# delete existing merged run folder
if os.path.exists(self.merged_dir):
import shutil
shutil.rmtree(self.merged_dir)
from pysmac.utils.state_merge import state_merge
print(os.path.join(self.scenario_output_dir, 'state-run*'))
print(
glob.glob(os.path.join(self.scenario_output_dir,
'state-run*')))
state_merge(glob.glob(
os.path.join(self.scenario_output_dir, 'state-run*')),
self.merged_dir,
check_scenario_files=check_scenario_files)
return (pyfanova.fanova.Fanova(self.merged_dir,
improvement_over=improvement_over,
heap_size=heap_size))
except ImportError:
raise
raise NotImplementedError(
'To use this feature, please install the pyfanova package.')
except:
print('Something went during the initialization of the FANOVA.')
raise
def smac_to_fanova(state_run_directory, destination_dir):
'''
Takes the state-run files, merges them and prepares the configuration space for fANOVA.
outputs: fANOVA object
state_run_directory: str
path to the directory of the pysmac_output/out/scenario file
destination_dir: str
path to the directory in which the merged states should be stored
'''
state_run_list = []
files = glob(state_run_directory + "/*")
for file in files:
if file.startswith(state_run_directory + "/state-run"):
state_run_list.append(file)
state_merge.state_merge(state_run_list, destination_dir)
merged_files = glob(destination_dir + '/*')
for file in merged_files:
if file.startswith(destination_dir + '/runs_and_results'):
response_file = file
if file.startswith(destination_dir + '/paramstrings'):
paramstrings = file
param_dict = output_reader.read_paramstrings_file(paramstrings)
num_line = str(param_dict[0]).replace("'", "")
num_line = str(num_line).replace("}", "")
# messy way to get the parameter names wrt order
f_params = []
for line in str(num_line).split(" "):
line = str(line).replace(",", "")
line = line.replace('{', '')
if ':' in line:
parameter = line.replace(':', '')
f_params.append(parameter)
# get configspace
with open(destination_dir + '/param.pcs') as fh:
cs = pcs_new.read(fh.readlines(), debug=True)
X = []
hps = cs.get_hyperparameters()
for p in param_dict:
c = CS.Configuration(cs,
fix_types(p, cs),
allow_inactive_with_values=True)
X.append([])
for hp in hps:
if hasattr(hp, 'choices'):
value = hp.choices.index(c[hp.name])
else:
value = c[hp.name]
X[-1].append(value)
X = np.array(X)
Y = data_extractor(response_file, X.shape[0])
return fanova.fANOVA(X=X, Y=Y, config_space=cs)
def run_ISMAC(
source_dir,
function_file,
working_dir,
python_executable='python3',
verbosity='ERROR',
seed=None,
exploration_time_budget=np.float('inf'),
per_partition_time=60,
init_rand_exploration_evaluations=20,
init_default_evaluations=5,
exploration_evaluations=20,
insts_for_PEI=5,
max_num_partitions=4,
min_partition_size=4,
tae_str='old', # options 'aclib', 'old'
save_rounds=False,
regularize=False,
modus='SMAC', # other choice 'ROAR'
only_use_known_configs=False,
budget_strat="equal" # other choice 'inc' for increasing
):
state_run_directory = os.path.join(source_dir, 'out/scenario')
merge_dir = os.path.join(working_dir, "scenario")
state_run_list = glob.glob(state_run_directory + "/state-run*")
state_merge.state_merge(state_run_list, merge_dir)
# copy necessary files
with open(merge_dir + '/scenario.txt', "r") as inputfile:
with open(working_dir + '/piac_scenario.txt', "w") as outputfile:
for line in inputfile:
header, rest = line.split(" ", 1)
if not header in [
'output-dir', 'algo-exec', 'algo-exec-dir', 'run-obj'
]:
outputfile.write(line)
if header == 'run-obj':
outputfile.write(" ".join([header, rest.lower()]))
outputfile.write('algo-exec-dir = %s \n' % (working_dir))
outputfile.write('algo-exec = %s %s' %
(python_executable, function_file))
scenario_file = working_dir + '/piac_scenario.txt'
#shutil.copyfile(source_dir+'/features.dat', working_dir+'/features.dat')
if seed is None:
seed = np.random.seed()
model = kraken(
scen_file=scenario_file,
per_partition_time=per_partition_time,
working_dir=working_dir,
verbosity=verbosity,
seed=seed,
exploration_time_budget=exploration_time_budget,
init_rand_exploration_evaluations=init_rand_exploration_evaluations,
init_default_evaluations=init_default_evaluations,
exploration_evaluations=exploration_evaluations,
insts_for_PEI=insts_for_PEI,
max_num_partitions=max_num_partitions,
tae_str=tae_str,
save_rounds=save_rounds,
min_partition_size=min_partition_size,
regularize=regularize,
modus=modus,
only_known_configs=only_use_known_configs,
budget_strat=budget_strat)
return (model)
def smac_to_fanova(state_run_directory, destination_dir):
'''
Takes the state-run files, merges them and prepares the configuration space for fANOVA.
outputs: fANOVA object
state_run_directory: str
path to the directory of the pysmac_output/out/scenario file
destination_dir: str
path to the directory in which the merged states should be stored
'''
state_run_list =[]
files = glob(state_run_directory + "/*")
for file in files:
if file.startswith(state_run_directory + "/state-run"):
state_run_list.append(file)
state_merge.state_merge(state_run_list, destination_dir)
merged_files = glob(destination_dir + '/*')
for file in merged_files:
if file.startswith(destination_dir + '/runs_and_results'):
response_file = file
if file.startswith(destination_dir + '/paramstrings'):
paramstrings = file
param_dict = output_reader.read_paramstrings_file(paramstrings)
num_line = str(param_dict[0]).replace("'", "")
num_line = str(num_line).replace("}", "")
# messy way to get the parameter names wrt order
f_params = []
for line in str(num_line).split(" "):
line = str(line).replace(",", "")
line = line.replace('{', '')
if ':' in line:
parameter = line.replace(':', '')
f_params.append(parameter)
# getting features
all_nums = []
for dict_row in param_dict:
num_line = str(dict_row).replace("'", "")
num_line = str(num_line).replace("}", "")
nums = []
for line in str(num_line).split(" "):
line = str(line).replace(",", "")
if line.isdigit():
nums.append(np.int(line))
elif line.replace(".", "", 1).isdigit():
nums.append(np.float(line))
elif '-' in line:
new_line = line.replace("-","")
if new_line.isdigit():
nums.append(np.int(line))
elif new_line.replace(".", "", 1).isdigit():
nums.append(np.float(line))
all_nums.append(nums)
x = np.array(all_nums)
length = len(x)
Y = data_extractor(response_file, length)
fh = open(destination_dir + '/param.pcs')
orig_pcs = fh.readlines()
cs = pcs_new.read(orig_pcs, debug=True)
X = np.zeros((x.shape))
for i in range(x.shape[1]):
idx = cs.get_idx_by_hyperparameter_name(f_params[i])
X[:, idx] = x[:, i]
# create an instance of fanova with data for the random forest and the configSpace
return fanova.fANOVA(X = X, Y = Y, config_space= cs)