def dev__run_simulations():
test_case = test_case_MgO
assert os.path.isfile(config_fn)
assert os.path.isfile(data_in_fn)
o = PyposmatFileSampler(config_fn=test_case['config_fn'],
data_in_fn=test_case['data_in_fn'])
o.run_simulations(i_iteration=test_case['i_iteration'])
def test__configure_task_manager():
o_sampler = PyposmatFileSampler(
config_fn=config_fn,
data_in_fn=datafile_in_fn,
data_out_fn=datafile_out_fn)
o_sampler.create_base_directories()
o_sampler.read_configuration_file()
o_sampler.configure_qoi_manager(use_fitting_qois=False,use_testing_qois=True)
o_sampler.configure_task_manager()
from pypospack.task import TaskManager
assert type(o_sampler.task_manager) is TaskManager
def dev__configure_qoi_manager():
config_fn = test_case_MgO['config_fn']
data_in_fn = test_case_MgO['data_in_fn']
o = PyposmatFileSampler(config_fn=config_fn, data_in_fn=data_in_fn)
qois = [k for k in o.configuration.qois]
print('qoi_names:', qois)
o.configure_qoi_manager()
print('o.configuration.qoi_names:', o.configuration.qoi_names)
s = str(type(o.qoi_manager))
print("type(o.qoi_manager):{}".format(s))
s = str(type((o.qoi_manager.tasks)))
print('type(o.qoi_manager.tasks:{}'.format(s))
def test____init__():
o_sampler = PyposmatFileSampler(
config_fn=config_fn,
data_in_fn=datafile_in_fn,
data_out_fn=datafile_out_fn)
assert o_sampler.reference_potentials == reference_potentials
def initialize_sampler(self,
config_fn,
results_fn,
mpi_rank=None,
mpi_size=None,
o_log=None):
""" initialize the sampling object
This method initializes the `mc_sampler` attribute with a sampler.
Note:
This breakout is part of a larger effort within PYPOSPACK, to have
more object-oriented approach for parametric sampling. The goal
eventually is to implement an instance of PyposmatBaseSampler, and
allow users of this software library to be able to extend this
software by simply extending the base class.
Args:
config_fn(str): path to the configuration file
results_fn(str): path to the results file
mpi_rank(int,optional): the MPI rank of executing this method
mpi_size(int,optional): the size of the MPI execution group
o_log(PyposmatLogFile,str,optional): the log file. If a string is
passed, then the sampling class will initialize a separate log
file with the string of path created. If a log file object is
passed, then sampling object will use that instance of the
object to log information. By defaut, it will pass the
attribute, `o_log`.
"""
assert type(config_fn) is str
assert type(results_fn) is str
assert type(mpi_rank) in [type(None), int]
assert type(mpi_size) in [type(None), int]
assert type(o_log) in [type(None), PyposmatLogFile, str]
# check to see if the paths provided are absolute paths
assert os.path.isabs(config_fn)
assert os.path.isabs(results_fn)
if mpi_rank is None: mpi_rank = self.mpi_rank
if mpi_size is None: mpi_size = self.mpi_size
self.mc_sampler = PyposmatMonteCarloSampler(filename_in=config_fn,
filename_out=results_fn,
mpi_rank=mpi_rank,
mpi_size=mpi_size,
o_log=o_log)
self.mc_sampler.create_base_directories()
self.mc_sampler.read_configuration_file()
# we have to be able to find the structure directory
self.mc_sampler.configuration.structures[
'structure_directory'] = self.structure_directory
self.mc_sampler.configure_qoi_manager()
self.mc_sampler.configure_task_manager()
self.mc_sampler.configure_pyposmat_datafile_out()
self.mc_sampler.configure_pyposmat_badparameters_file()
self.log_more_iteration_information()
def test____init__():
config_fn = test_case_MgO['config_fn']
data_in_fn = test_case_MgO['data_in_fn']
assert os.path.isfile(config_fn)
assert os.path.isfile(data_in_fn)
o = PyposmatFileSampler(config_fn=config_fn, data_in_fn=data_in_fn)
assert isinstance(o.configuration, PyposmatConfigurationFile)
assert isinstance(o.datafile_in, PyposmatDataFile)
assert isinstance(o.datafile_out, PyposmatDataFile)
def dev____init__():
config_fn = test_case_MgO['config_fn']
data_in_fn = test_case_MgO['data_in_fn']
assert os.path.isfile(config_fn)
assert os.path.isfile(data_in_fn)
o = PyposmatFileSampler(config_fn=config_fn, data_in_fn=data_in_fn)
s = []
s.append("type(o.configuration)={}".format(type(o.configuration)))
s.append("type(o.datafile_in)={}".format(type(o.datafile_in)))
s.append("type(o.datafile_out={}".format(type(o.datafile_out)))
print("\n".join(s))
def test__configure_qoi_manager():
test_case = test_case_MgO
o = PyposmatFileSampler(config_fn=test_case['config_fn'],
data_in_fn=test_case['data_in_fn'],
fullauto=False)
o.read_configuration_file(filename=test_case['config_fn'])
o.configure_qoi_manager()
assert isinstance(o.configuration, PyposmatConfigurationFile)
assert isinstance(o.qoi_manager, QoiManager)
def setup__configure_qoi_manager():
config_directory = "./data"
config_fn = os.path.join(config_directory,'pyposmat.config.in')
data_directory = "../../data/MgO_pareto_data"
datafile_in_fn = os.path.join(data_directory,'culled_005.out')
output_directory = "./"
datafile_out_fn = os.path.join(output_directory,'qoiplus_005.out')
o_sampler = PyposmatFileSampler(
config_fn=config_fn,
data_in_fn=datafile_in_fn,
data_out_fn=datafile_out_fn)
o_sampler.create_base_directories()
o_sampler.read_configuration_file()
class PyposmatIterativeSampler(object):
""" Iterative Sampler which wraps multiple simulation algorithms.
This class wraps multiple simulation algorithms so that they can be run in an iterative manner.
Since this class has so many configuration options, the attributes of this class is set
by a YAML based configuration file. The class PyposmatConfigurationFile aids in the creation
and reading of these options. These attributes are public and be set programmatically within
a script.
Notes:
config_fn = 'data/pyposmat.config.in'
engine = PyposmatIterativeSampler(configuration_filename=config_fn)
engine.read_configuration_file()
engine.run_all()
Args:
configuration_filename(str): the filename of the YAML configuration file
is_restart(bool,optional): When set to True, this argument controls the restart behavior
of this class. By default, is set to False
is_auto(bool,optional): When set to True, this agument will automatically configure the
class. By default this is set to False, mostly because this software is currently in
development, and this necessary to to write integration testing
log_fn(str,optional): This the filename path where to set logging, by default it is set
as `pyposmat.log` contained in the configurable data directory
log_to_stdout(bool,optional): When set to True, all log messages will be directed to
standard out as well as the log file
Attributes:
mpi_comm(MPI.Intracomm)
mpi_rank(int)
mpi_size(int)
mpi_nprocs(int)
i_iteration(int)
n_iterations(int)
rv_seed(int)
rv_seeds(np.ndarray)
configuration_filename = configuration(filename)
configuration(PyposmatConfigurationFile)
mc_sampler(PyposmatMonteCarloSampler)
root_directory(str)
data_directory(str)
is_restart(bool)
start_iteration=0
"""
parameter_sampling_types = [
'parametric', 'kde', 'from_file', 'kde_w_clusters'
]
def __init__(self,
configuration_filename,
is_restart=False,
is_auto=False,
log_fn=None,
log_to_stdout=True):
# formats should not contain a trailing end line chracter
self.SECTION_HEADER_FORMAT = "\n".join([80 * '=', "{:^80}", 80 * "="])
self.RANK_DIR_FORMAT = 'rank_{}'
self.mpi_comm = None
self.mpi_rank = None
self.mpi_size = None
self.mpi_nprocs = None
self.i_iteration = None
self.rv_seed = None
self.rv_seeds = None
self.configuration_filename = configuration_filename
self.configuration = None
self.mc_sampler = None
self.root_directory = os.getcwd()
self.data_directory = 'data'
self.is_restart = is_restart
self.start_iteration = 0
self.log_fn = log_fn
self.log_to_stdout = log_to_stdout
self.o_log = None
self.initialize_logger(log_fn=log_fn, log_to_stdout=log_to_stdout)
if self.is_restart:
self.delete_mpi_rank_directories()
@property
def structure_directory(self):
if self.configuration is None:
return None
else:
d = self.configuration.structures['structure_directory']
if not os.path.isabs(d):
d = os.path.join(self.root_directory, d)
return d
@property
def n_iterations(self):
if self.configuration is None:
return None
else:
return self.configuration.n_iterations
@property
def qoi_names(self):
if self.configuration is None:
return None
else:
return self.configuration.qoi_names
@property
def error_names(self):
if self.configuration is None:
return None
else:
return self.configuration.error_names
def delete_mpi_rank_directories(self):
if self.mpi_rank == 0:
self.log('Deleting previous rank directories')
mpi_rank_directories = [
d for d in os.listdir(self.root_directory)
if d.startswith('rank_')
]
for d in mpi_rank_directories:
try:
shutil.rmtree(os.path.join(self.root_directory, d))
except:
raise
MPI.COMM_WORLD.Barrier()
def determine_last_iteration_completed(self):
for i in range(self.n_iterations):
results_fn = os.path.join(self.data_directory,
'pyposmat.results.{}.out'.format(i))
kde_fn = os.path.join(self.data_directory,
'pyposmat.kde.{}.out'.format(i + 1))
if os.path.isfile(results_fn) and os.path.isfile(kde_fn):
if self.mpi_rank == 0:
self.log('iteration {}: is complete'.format(i))
self.start_iteration = i + 1
else:
self.start_iteration = i
break
MPI.COMM_WORLD.Barrier()
return self.start_iteration
def run_all(self):
"""runs all iterations
This method runs all iterations
"""
self.setup_mpi_environment()
self.initialize_data_directory()
self.start_iteration = 0
if self.is_restart:
self.determine_last_iteration_completed()
if self.mpi_rank == 0:
self.log("starting at simulation: {}".format(self.start_iteration))
MPI.COMM_WORLD.Barrier()
for i in range(self.start_iteration, self.n_iterations):
self.i_iteration = i
# log iteration information
self.log_iteration_information(i_iteration=i)
self.run_simulations(i)
MPI.COMM_WORLD.Barrier()
if self.mpi_rank == 0:
self.log("ALL SIMULATIONS COMPLETE FOR ALL RANKS")
self.log("MERGING FILES")
self.merge_data_files(i)
self.merge_error_files(i)
MPI.COMM_WORLD.Barrier()
if self.mpi_rank == 0:
self.log("ANALYZE RESULTS")
self.analyze_results(i)
MPI.COMM_WORLD.Barrier()
if self.mpi_rank == 0:
self.log(80 * '-')
self.log('JOBCOMPLETE')
def initialize_sampler(self,
config_fn,
results_fn,
mpi_rank=None,
mpi_size=None,
o_log=None):
""" initialize the sampling object
This method initializes the `mc_sampler` attribute with a sampler.
Note:
This breakout is part of a larger effort within PYPOSPACK, to have
more object-oriented approach for parametric sampling. The goal
eventually is to implement an instance of PyposmatBaseSampler, and
allow users of this software library to be able to extend this
software by simply extending the base class.
Args:
config_fn(str): path to the configuration file
results_fn(str): path to the results file
mpi_rank(int,optional): the MPI rank of executing this method
mpi_size(int,optional): the size of the MPI execution group
o_log(PyposmatLogFile,str,optional): the log file. If a string is
passed, then the sampling class will initialize a separate log
file with the string of path created. If a log file object is
passed, then sampling object will use that instance of the
object to log information. By defaut, it will pass the
attribute, `o_log`.
"""
assert type(config_fn) is str
assert type(results_fn) is str
assert type(mpi_rank) in [type(None), int]
assert type(mpi_size) in [type(None), int]
assert type(o_log) in [type(None), PyposmatLogFile, str]
# check to see if the paths provided are absolute paths
assert os.path.isabs(config_fn)
assert os.path.isabs(results_fn)
if mpi_rank is None: mpi_rank = self.mpi_rank
if mpi_size is None: mpi_size = self.mpi_size
self.mc_sampler = PyposmatMonteCarloSampler(filename_in=config_fn,
filename_out=results_fn,
mpi_rank=mpi_rank,
mpi_size=mpi_size,
o_log=o_log)
self.mc_sampler.create_base_directories()
self.mc_sampler.read_configuration_file()
# we have to be able to find the structure directory
self.mc_sampler.configuration.structures[
'structure_directory'] = self.structure_directory
self.mc_sampler.configure_qoi_manager()
self.mc_sampler.configure_task_manager()
self.mc_sampler.configure_pyposmat_datafile_out()
self.mc_sampler.configure_pyposmat_badparameters_file()
self.log_more_iteration_information()
def initialize_file_sampler(self,
config_fn,
results_fn,
i_iteration=0,
mpi_rank=None,
mpi_size=None,
o_log=None):
""" initialize the sampling object
This method initializes the `mc_sampler` attribute with a sampler.
Note:
This breakout is part of a larger effort within PYPOSPACK, to have
more object-oriented approach for parametric sampling. The goal
eventually is to implement an instance of PyposmatBaseSampler, and
allow users of this software library to be able to extend this
software by simply extending the base class.
Args:
config_fn(str): path to the configuration file
results_fn(str): path to the results file
i_iteration(int,optional): the iteration to sample the file from,
by default this is set to zero.
mpi_rank(int,optional): the MPI rank of executing this method
mpi_size(int,optional): the size of the MPI execution group
o_log(PyposmatLogFile,str,optional): the log file. If a string is
passed, then the sampling class will initialize a separate log
file with the string of path created. If a log file object is
passed, then sampling object will use that instance of the
object to log information. By defaut, it will pass the
attribute, `o_log`.
"""
assert type(config_fn) is str
assert type(results_fn) is str
assert type(mpi_rank) in [type(None), int]
assert type(mpi_size) in [type(None), int]
assert type(o_log) in [type(None), PyposmatLogFile, str]
# check to see if the paths provided are absolute paths
assert os.path.isabs(config_fn)
assert os.path.isabs(results_fn)
if mpi_rank is None: mpi_rank = self.mpi_rank
if mpi_size is None: mpi_size = self.mpi_size
# get the absolute path of the datafile we are sampling from
data_in_fn = None
if os.path.isabs(
self.configuration.sampling_type[i_iteration]['file']):
data_in_fn = self.configuration.sampling_type[i_iteration]['file']
else:
data_in_fn = os.path.join(
self.root_directory,
self.configuration.sampling_type[i_iteration]['file'])
data_out_fn = results_fn
self.mc_sampler = PyposmatFileSampler(config_fn=config_fn,
data_in_fn=data_in_fn,
data_out_fn=data_out_fn,
mpi_rank=mpi_rank,
mpi_size=mpi_size,
o_log=o_log,
fullauto=False)
self.mc_sampler.create_base_directories()
self.mc_sampler.read_configuration_file()
# we have to be able to find the structure directory
self.mc_sampler.configuration.structures[
'structure_directory'] = self.structure_directory
self.mc_sampler.configure_qoi_manager()
self.mc_sampler.configure_task_manager()
self.mc_sampler.configure_datafile_out()
self.mc_sampler.configure_pyposmat_badparameters_file()
self.log_more_iteration_information()
def initialize_rank_directory(self):
""" create the rank directory
This method defines the rank directory as an absolute path and stores it in
the attribute `rank_directory`. If a current directory exists there, then
it is deleted with alll it's contents and then recreated.
"""
rank_directory = os.path.join(
self.root_directory, self.RANK_DIR_FORMAT.format(self.mpi_rank))
# find the directory, delete it and it's constants and then recreates ot
if os.path.isdir(rank_directory):
shutil.rmtree(rank_directory)
os.mkdir(rank_directory)
self.rank_directory = rank_directory
def run_simulations(self, i_iteration):
""" run simulation for a single iteration
Each rank is given a different execution context so that the disk IO
don't conflict
"""
self.initialize_rank_directory()
config_filename = self.configuration_filename
results_filename = os.path.join(self.rank_directory,
'pyposmat.results.out')
bad_parameters_filename = os.path.join(self.rank_directory,
'pyposmat.badparameters.out')
# change execution context for this rank
os.chdir(self.rank_directory)
# set random seed
self.determine_rv_seeds()
self.log_random_seeds(i_iteration=i_iteration)
sampling_type = self.configuration.sampling_type[i_iteration]['type']
if self.mpi_rank == 0:
self.log("sampling_type={}".format(sampling_type))
MPI.COMM_WORLD.Barrier()
# <----- parameter sampling type ---------------------------------------
if sampling_type == 'parametric':
self.initialize_sampler(config_fn=config_filename,
results_fn=results_filename,
mpi_rank=self.mpi_rank,
mpi_size=self.mpi_size,
o_log=self.o_log)
self.run_parametric_sampling(i_iteration=i_iteration)
# <----- kde sampling sampling type ---------------------------------------
elif sampling_type == 'kde':
self.initialize_sampler(config_fn=config_filename,
results_fn=results_filename,
mpi_rank=self.mpi_rank,
mpi_size=self.mpi_size,
o_log=self.o_log)
self.run_kde_sampling(i_iteration=i_iteration)
# <----- sampling from a file type ---------------------------------------
# get parameters from file
elif sampling_type == 'from_file':
self.initialize_file_sampler(config_fn=config_filename,
results_fn=results_filename,
mpi_rank=self.mpi_rank,
mpi_size=self.mpi_size,
o_log=self.o_log)
self.run_file_sampling(i_iteration=i_iteration)
# <----- kde with clusters sampling type ---------------------------------------
elif sampling_type == 'kde_w_clusters':
cluster_fn = "pyposmat.cluster.{}.out".format(i_iteration)
pyposmat_datafile_in = os.path.join(self.root_directory,
self.data_directory,
cluster_fn)
_config_filename = os.path.join(self.root_directory,
self.configuration_filename)
# determine number of sims for this rank
_mc_n_samples = _mc_config['n_samples_per_cluster']
_n_samples_per_rank = int(_mc_n_samples / self.mpi_size)
if _mc_n_samples % self.mpi_size > self.mpi_rank:
_n_samples_per_rank += 1
# initialize sampling object
o = PyposmatClusterSampler(o_logger=self.log,
mpi_rank=self.mpi_rank,
mpi_comm=self.mpi_comm,
mpi_size=self.mpi_size)
o.create_base_directories()
o.read_configuration_file(filename=_config_filename)
# check to see if clustered data file exists
if self.mpi_rank == 0:
if not os.path.isfile(pyposmat_datafile_in):
kde_fn = "pyposmat.kde.{}.out".format(i_iteration)
kde_fn = os.path.join(self.root_directory,
self.data_directory, kde_fn)
o.write_cluster_file(filename=kde_fn,
i_iteration=i_iteration)
MPI.COMM_WORLD.Barrier()
o.configure_pyposmat_datafile_in(filename=pyposmat_datafile_in)
# fix relative path to structure databae folder
_structure_dir = o.configuration.structures['structure_directory']
o.configuration.structures['structure_directory'] = \
os.path.join('..',_structure_dir)
# finish the rest of the initialization
o.configure_qoi_manager()
o.configure_task_manager()
o.configure_pyposmat_datafile_out()
MPI.COMM_WORLD.Barrier()
# run simulations
o.run_simulations(i_iteration=i_iteration,
n_samples=_mc_n_samples,
filename=pyposmat_datafile_in)
MPI.COMM_WORLD.Barrier()
else:
error_dict = OrderedDict([('i_iteration', i_iteration),
('sampling_type', sampling_type)])
m = "unknown parameter sampling type: {}".format(sampling_type)
m += "the valid sampling types are: {}".format(",".join(
self.parameter_sampling_types))
raise PyposmatSamplingTypeError(m, error_dict)
# return to root directory
os.chdir(self.root_directory)
def initialize_data_directory(self, data_directory=None):
""" determine the absolute path of the data directory and create it
This method sets the `data_directory` attribute of the class and creates
the `data directory` if the data directory already exists.
Args:
data_directory(str):the path of the data directory, the path can be
expressed in either a relative path, or an absolute path
Returns:
(str) the absolute path of the data directory
Raises:
OSError: if the directory is not able to be created
"""
assert type(data_directory) in [type(None), str]
assert type(self.data_directory) in [type(None), str]
# determine the data directory path
if data_directory is None:
if self.data_directory is None:
self.data_directory = os.path.join(self.root_directory, 'data')
else:
if os.path.isabs(self.data_directory):
self.data_directory = data_directory
else:
self.data_directory = os.path.join(self.root_directory,
self.data_directory)
elif os.path.isabs(data_directory):
# absolute path
self.data_directory = data_directory
else:
# create a absolute path from the relative path
self.data_directory = os.path.join(self.root_directory,
data_directory)
self.data_directory = os.path.abspath(self.data_directory)
# create data directory
if self.mpi_rank == 0:
try:
os.mkdir(self.data_directory)
self.log('created the data directory.')
self.log('\tdata_directory;{}'.format(self.data_directory))
except FileExistsError as e:
self.log(
'attempted to create data directory, directory already exists.'
)
self.log('\tdata_directory:{}'.format(self.data_directory))
except OSError as e:
self.log(
'attempted to create data directory, cannot create directory.'
)
self.log('\tdata_directory:{}'.format(self.data_directory))
MPI.COMM_WORLD.Barrier()
def run_parametric_sampling(self, i_iteration):
""" run parametric sampling
Args:
i_iteration(int): what iteration of the sampling is happening
"""
assert type(i_iteration) is int
assert type(self.mc_sampler) is PyposmatMonteCarloSampler
self.mc_sampler.run_simulations(
i_iteration=i_iteration,
n_samples=self.determine_number_of_samples_per_rank(
i_iteration=i_iteration))
def run_kde_sampling(self, i_iteration):
""" run kde sampling
Args:
i_iteration(int): what iteration of the sampling is happening
"""
is_debug = False
assert type(i_iteration) is int
assert type(self.mc_sampler) is PyposmatMonteCarloSampler
kde_filename = os.path.join(self.data_directory,
'pyposmat.kde.{}.out'.format(i_iteration))
n_samples_per_rank = self.determine_number_of_samples_per_rank(
i_iteration=i_iteration)
if is_debug:
print('cwd:{}'.format(os.getcwd()))
print('mpi_rank:{},kde_filename:{}'.format(self.mpi_rank,
kde_filename))
print('n_samples_per_rank:{}'.format(n_samples_per_rank))
self.mc_sampler.run_simulations(i_iteration=i_iteration,
n_samples=n_samples_per_rank,
filename=kde_filename)
def run_file_sampling(self, i_iteration):
""" run file sampling
Args:
i_iteration(int): the iteration which to sampling for
"""
assert type(i_iteration) is int
assert type(self.mc_sampler) is PyposmatFileSampler
if 'file' in self.configuration.sampling_type[i_iteration]:
filename = os.path.join(
self.root_directory,
self.configuration.sampling_type[i_iteration]['file'])
else:
if os.path.isabs(self.data_directory):
filename = os.path.join(
self.data_directory,
'pyposmat.kde.{}.out'.format(i_iteration))
else:
filename = os.path, join(
self.root_directory, self.data_directory,
'pyposmat.kde.{}.out'.format(i_iteration))
if self.mpi_rank == 0:
self.log(80 * '-')
self.log('{:^80}'.format('file sampling'))
self.log(80 * '-')
self.log('filename_in:{}'.format(filename))
MPI.COMM_WORLD.Barrier()
self.mc_sampler.run_simulations(
i_iteration=i_iteration,
n_samples=self.determine_number_of_samples_per_rank(
i_iteration=i_iteration),
filename=filename)
def determine_number_of_samples_per_rank(self,
i_iteration,
N_samples=None):
""" determine the number of samples per rank
The total number of samples needs to be broken up between the ranks, but roughly
divided the work evenly.
Args:
i_iteration(int): which iteration we are in the simulation
N_samples(int,optional): the total number of samples we are using for
this iteration. If a number is provided, it will override
the number of simulations specified in the configuration file.
Returns:
(int): the number of samples for this rank
"""
assert type(i_iteration) is int
assert type(N_samples) in [type(None), int]
assert type(self.configuration) is PyposmatConfigurationFile
if N_samples is None:
N_samples = self.configuration.sampling_type[i_iteration][
'n_samples']
N_samples_per_rank = int(N_samples / self.mpi_size)
if N_samples % self.mpi_size > self.mpi_rank:
N_samples_per_rank += 1
return N_samples_per_rank
def initialize_logger(self, log_fn=None, log_to_stdout=None):
"""initialize log object
Args:
log_fn(str,optional)
"""
assert type(log_fn) in [type(None), str]
assert type(log_to_stdout) in [type(None), bool]
if log_fn is None:
self.log_fn = os.path.join(self.root_directory,
self.data_directory, 'pyposmat.log')
else:
self.log_fn = log_fn
self.o_log = PyposmatLogFile(filename=self.log_fn)
self.log_to_stdout = log_to_stdout
def setup_mpi_environment(self):
self.mpi_comm = MPI.COMM_WORLD
self.mpi_rank = self.mpi_comm.Get_rank()
self.mpi_size = self.mpi_comm.Get_size()
self.mpi_procname = MPI.Get_processor_name()
self.log_mpi_environment()
# random seed management
def determine_rv_seeds(self, seed=None, i_iteration=None):
""" set the random variable seed across simulations
Args:
seed(int,optional)=a seed to determine the rest of the seeds for
different ranks and iterations.
"""
RAND_INT_LOW = 0
RAND_INT_HIGH = 2147483647
assert type(seed) in [type(None), int]
assert type(i_iteration) in [type(None), int]
if type(i_iteration) is type(None):
i_iteration = self.i_iteration
# set the seed attribute
if type(seed) is int:
self.rv_seed == seed
# set the seed attribute, if the seed attribute is none
if self.rv_seed is None:
self.rv_seed = np.random.randint(low=RAND_INT_LOW,
high=RAND_INT_HIGH)
# if the rv_seed was determined in the script, then all ranks will
# have the same rv_seed attribute
np.random.seed(self.rv_seed)
# each rank, will need it's own seed. So we sample from the freshly
# generated random number generator, which is identical across ranks
self.rv_seeds = np.random.randint(low=0,
high=2147483647,
size=(int(self.mpi_size),
self.n_iterations))
# now restart the seed for this rank
np.random.seed(self.rv_seeds[self.mpi_rank, i_iteration])
# logging methods
def log(self, s):
if self.log_to_stdout:
print(s)
if self.o_log is not None:
self.o_log.write(s)
def log_iteration_information(self, i_iteration):
"""log iteration information
Args:
i_iteration_id(int):the iteration number
Returns:
(str) the log string
"""
if self.mpi_rank == 0:
s = self.SECTION_HEADER_FORMAT.format(
'Begin Iteration {}/{}'.format(i_iteration + 1,
self.n_iterations))
self.log(s)
MPI.COMM_WORLD.Barrier()
#if self.mpi_rank == 0:
# return "\n".join(s)
def log_more_iteration_information(self):
#TODO: this logging needs to go into a separate logging method. -EJR
if self.mpi_rank == 0:
self.mc_sampler.print_structure_database()
self.mc_sampler.print_sampling_configuration()
if self.mpi_rank == 0 and self.i_iteration == 0:
self.mc_sampler.print_initial_parameter_distribution()
if self.mpi_rank == 0:
self.log(80 * '-')
MPI.COMM_WORLD.Barrier()
def log_mpi_environment(self):
if self.mpi_rank == 0:
m = [
self.SECTION_HEADER_FORMAT.format(
'MPI communication information')
]
m += ['mpi_size={}'.format(self.mpi_size)]
MPI.COMM_WORLD.Barrier()
def log_random_seeds(self, i_iteration):
if self.mpi_rank == 0:
self.log(80 * '-')
self.log('{:^80}'.format('GENERATED RANDOM SEEDS'))
self.log(80 * '-')
self.log('global_seed:{}'.format(str(self.rv_seed)))
self.log('seeds_for_this_iteration:')
self.log('{:^8} {:^8}'.format('rank', 'seed'))
self.log('{} {}'.format(8 * '-', 8 * '-'))
MPI.COMM_WORLD.Barrier()
for i_rank in range(self.mpi_size):
if self.mpi_rank == i_rank:
self.log('{:^8} {:>10}'.format(
i_rank, self.rv_seeds[i_rank, i_iteration]))
MPI.COMM_WORLD.Barrier()
def get_results_dict(self):
rd = OrderedDict()
rd['mpi'] = OrderedDict()
rd['mpi']['size'] = self.mpi_size
def analyze_data_directories(self, data_dir=None):
_d = data_dir
i = 0
contents = []
if not os.path.exists(_d): return i, contents
if not os.path.isdir(_d): return i, contents
while True:
kde_fn = os.path.join(_d, "pyposmat.kde.{}.out".format(i))
if os.path.exists(kde_fn):
contents.append(kde_fn)
else:
if i > 0:
contents.append(results_fn)
break
results_fn = os.path.join(_d, "pyposmat.results.{}.out".format(i))
if os.path.exists(results_fn): pass
else: break
i = i + 1
return i, contents
def analyze_rank_directories(self, root_dir=None):
i = 0
contents = []
if root_dir is None:
_d = self.root_directory
else:
_d = root_directory
while True:
rank_dir = os.path.join(_d, "rank_{}".format(i))
if not os.path.exists(rank_dir):
break
if not os.path.isdir(rank_dir):
break
rank_fn = os.path.join("rank_{}".format(i), "pyposmat.results.out")
if not os.path.exists(os.path.join(_d, rank_fn)):
break
if not os.path.isfile(os.path.join(_d, rank_fn)):
break
else:
contents.append(rank_fn)
i = i + 1
return i, contents
def find_initial_parameters_file(self):
if 'file' in self.configuration.sampling_type[0]:
_init_fn = os.path.join(
self.root_directory,
self.configuration.sampling_type[0]['file'])
if os.path.exists(_init_fn):
if os.path.isfile(_init_fn):
return _init_fn
else:
return None
def merge_data_files(self,
i_iteration,
last_datafile_fn=None,
new_datafile_fn=None):
""" merge the pyposmat data files
Args:
i_iteration(int): the current iteration which just finished
last_datafile_fn(str,optional): the filename of the last dataset in the data directory.
new_datafile_fn(str,optional): where to output the file results
"""
if last_datafile_fn is None:
last_datafile_fn = os.path.join(
self.data_directory, 'pyposmat.kde.{}.out'.format(i_iteration))
if new_datafile_fn is None:
new_datafile_fn = os.path.join(
self.data_directory,
'pyposmat.results.{}.out'.format(i_iteration))
data_dir = self.data_directory
rank_dirs = [
v for v in os.listdir(self.root_directory) if v.startswith('rank_')
]
filenames = [
os.path.join(self.root_directory, v, 'pyposmat.results.out')
for v in rank_dirs
]
data = None
for i, v in enumerate(filenames):
data_new = None
if i == 0:
data = PyposmatDataFile()
data.read(filename=v)
else:
data_new = PyposmatDataFile()
data_new.read(filename=v)
data.df = pd.concat([data.df, data_new.df])
nrows = len(data.df)
if self.configuration.sampling_type[i_iteration][
'type'] == 'from_file':
pass
else:
sim_id_fmt = '{:0>2}_{:0>6}'
sim_id_str = [
sim_id_fmt.format(i_iteration, i) for i in range(nrows)
]
data.df['sim_id'] = [
sim_id_fmt.format(i_iteration, i) for i in range(nrows)
]
if self.configuration.sampling_type[i_iteration][
'type'] == "from_file":
data_new = PyposmatDataFile()
data_new.read(filename=filenames[0])
data_new.df = data.df
data_new.write(filename=new_datafile_fn)
else:
self.log("merging with candidates from previous simulations")
self.log("\tfilename:{}".format(last_datafile_fn))
data_old = PyposmatDataFile()
try:
data_old.read(filename=last_datafile_fn)
data_old.df = pd.concat([data_old.df, data.df])
data_old.write(filename=new_datafile_fn)
except FileNotFoundError as e:
if i_iteration == 0:
data.write(filename=new_datafile_fn)
else:
raise
def merge_error_files(self, i_iteration):
""" merge the pyposmat data files
Args:
i_iteration(int): the current iteration which just finished
last_datafile_fn(str,optional): the filename of the last dataset in the data directory.
new_datafile_fn(str,optional): where to output the file results
"""
badparameters_fn = os.path.join(self.data_directory,
'pyposmat.badparameters.out')
data_dir = self.data_directory
rank_dirs = [
v for v in os.listdir(self.root_directory) if v.startswith('rank_')
]
filenames = [
os.path.join(self.root_directory, v, 'pyposmat.badparameters.out')
for v in rank_dirs
]
# consolidate rank directories
badparameters_new = None
badparameters_next = None
for i, v in enumerate(filenames):
if badparameters_new is None:
try:
badparameters_new = PyposmatBadParametersFile(
o_config=self.configuration)
badparameters_new.read(filename=v)
except FileNotFoundError as e:
self.log("no bad parameters file at {}".format(v))
else:
try:
badparameters_next = PyposmatBadParametersFile(
o_config=self.configuration)
badparameters_next.read(filename=v)
badparameters_new.df = pd.concat(
[badparameters_new.df, badparameters_next.df])
except FileNotFoundError as e:
self.log("no bad parameters file as {}".format(v))
# determine the sim_id for bad parameters of the sim_id
if badparameters_new.df is None:
# no previous bad paramters found
# TODO: need to implement something here to deal with bad parameters
pass
else:
nrows = len(badparameters_new.df)
sim_id_fmt = '{:0>2}_{:0>6}'
sim_id_str = [
sim_id_fmt.format(i_iteration, i) for i in range(nrows)
]
badparameters_new.df['sim_id'] = sim_id_str
if self.configuration.sampling_type[i_iteration][
'type'] == "from_file":
badparameters_new.write(filename=badparameters_fn)
else:
self.log(
"merging with bad candidates from previous simulations")
self.log("\tfilename:{}".format(badparameters_fn))
badparameters = PyposmatBadParametersFile(
o_config=self.configuration)
try:
badparameters.read(filename=badparameters_fn)
badparameters.df = pd.concat(
[badparameters.df, badparameters_new.df])
badparameters.write(filename=badparameters_fn)
except FileNotFoundError as e:
if i_iteration == 0:
badparameters_new.write(filename=badparameters_fn)
else:
raise
def analyze_results(self,
i_iteration,
data_fn=None,
config_fn=None,
kde_fn=None,
analysis_fn=None):
""" analyze the results of the simulation
this method analyzes the results of the simulation, and does post simulation
tasks, such as filtering by qoi performance, pareto optimization, etc.
Args:
data_fn(str): the path of the data file. By default this is set to none
where the the file will be determine by i_iteration and internal
attributes
config_fn(str): the path of the data file. By default this is set to none
where the the file will be determine by i_iteration and internal
attributes
kde_fn(str): the path of the data file. By default this is set to none
where the the file will be determine by i_iteration and internal
attributes
"""
if data_fn is None:
data_fn = os.path.join(\
self.root_directory,
self.data_directory,
'pyposmat.results.{}.out'.format(i_iteration))
if config_fn is None:
config_fn = os.path.join(\
self.root_directory,
self.configuration_filename)
if kde_fn is None:
kde_fn = os.path.join(\
self.root_directory,
self.data_directory,
'pyposmat.kde.{}.out'.format(i_iteration+1))
if analysis_fn is None:
analysis_fn = os.path.join(self.root_directory,
self.data_directory,
'pyposmat.analysis.out')
data_analyzer = PyposmatDataAnalyzer()
data_analyzer.initialize_configuration(config_fn=config_fn)
data_analyzer.analyze_results_data(i_iteration, filename=data_fn)
assert isinstance(data_analyzer.results_statistics, OrderedDict)
if os.path.isfile(analysis_fn):
data_analyzer.read_analysis_file(filename=analysis_fn)
self.log(
data_analyzer.str__results_descriptive_statistics(
statistics=data_analyzer.results_statistics))
self.log(data_analyzer.str__qoi_filtering_summary())
data_analyzer.write_kde_file(filename=kde_fn)
data_analyzer.analyze_kde_data(i_iteration, filename=kde_fn)
assert isinstance(data_analyzer.kde_statistics, OrderedDict)
self.log(
data_analyzer.str__kde_descriptive_statistics(
statistics=data_analyzer.kde_statistics))
data_analyzer.update_analysis(i_iteration)
data_analyzer.write_analysis_file(filename=analysis_fn)
def read_configuration_file(self, filename=None):
assert type(filename) in [type(None), str]
assert type(self.configuration_filename) in [type(None), str]
if filename is not None:
self.configuration_filename = filename
if not os.path.isabs(self.configuration_filename):
self.configuration_filename = os.path.abspath(
self.configuration_filename)
self.configuration = PyposmatConfigurationFile()
self.configuration.read(filename=self.configuration_filename)
if self.mpi_rank == 0:
self._write_parameter_names()
self._write_qoi_names()
self._write_error_names()
def _write_parameter_names(self, parameter_names=None):
if parameter_names is None: _parameter_names = self.parameter_names
else: _parameter_names = parameter_names
s = [80 * '-']
s += ['{:^80}'.format('PARAMETER_NAMES')]
s += [80 * '-']
s += [p for p in _parameter_names]
self.log("\n".join(s))
def _write_qoi_names(self, qoi_names=None):
if qoi_names is None: _qoi_names = self.qoi_names
else: _qoi_names = qoi_names
s = [80 * '-']
s += ['{:^80}'.format('QOI_NAMES')]
s += [80 * '-']
s += [p for p in _qoi_names]
self.log("\n".join(s))
def _write_error_names(self, error_names=None):
if error_names is None: _error_names = self.error_names
else: _error_names = error_names
s = [80 * '-']
s += ['{:^80}'.format('ERROR_NAMES')]
s += [80 * '-']
s += [p for p in _error_names]
self.log("\n".join(s))
def test____init__():
o_sampler = PyposmatFileSampler(
config_fn=config_fn,
data_in_fn=datafile_in_fn,
data_out_fn=datafile_out_fn)
assert o_sampler.reference_potentials == reference_potentials
def reference_potential_names_to_string(o_sampler):
s = 80*'-'+"\n"
s += "{:^80}\n".format('CHECK REFERENCE POTENTIALS')
s += 80*'-'+"\n"
for v in o_sampler.reference_potentials:
s += "{}.{}\n".format(
v,
v in o_sampler.reference_potentials)
return s
if __name__ == "__main__":
print ("config_directory:{}".format(config_directory))
print ("data_directory:{}".format(data_directory))
print ("output_directory:{}".format(output_directory))
o_sampler = PyposmatFileSampler(
config_fn=config_fn,
data_in_fn=datafile_in_fn,
data_out_fn=datafile_out_fn)
print(reference_potential_names_to_string(o_sampler=o_sampler))
def test__subselect_by_dmetric():
o_sampler = PyposmatFileSampler(
config_fn=config_fn,
data_in_fn=datafile_in_fn,
data_out_fn=datafile_out_fn
)
o_sampler.create_base_directories()
o_sampler.read_configuration_file()
o_sampler.configure_qoi_manager(use_fitting_qois=False,use_testing_qois=True)
o_sampler.configure_task_manager()
o_sampler.configure_datafile_out()
o_sampler.subselect_by_dmetric(nsmallest=n_smallest)
import pandas as pd
assert type(o_sampler.subselect_df) is pd.DataFrame
config_directory = "./data"
config_fn = os.path.join(config_directory,'pyposmat.config.in')
data_directory = "../../data/MgO_pareto_data"
datafile_in_fn = os.path.join(data_directory,'culled_005.out')
output_directory = "./"
datafile_out_fn = os.path.join(output_directory,'qoiplus_005.out')
from pypospack.pyposmat.data import PyposmatConfigurationFile
o_config=PyposmatConfigurationFile()
o_config.read(filename=config_fn)
o_sampler = PyposmatFileSampler(
config_fn=config_fn,
data_in_fn=datafile_in_fn,
data_out_fn=datafile_out_fn
)
check_reference_potentials(o_sampler=o_sampler)
o_sampler.create_base_directories()
o_sampler.read_configuration_file()
# Determine which QOIS you want to calculate
# calculate only the fitting qois
#o_sampler.configure_qoi_manager(use_fitting_qois=True,use_testing_qois=False)
# Calculate only the testing qois
o_sampler.configure_qoi_manager(use_fitting_qois=False,use_testing_qois=True)
# Calculate all qois
#o_sampler.configure_qoi_manager(use_fitting_qois=True,use_testing_qois=True)