def get_best_parameterization(config_fn,data_fn,metric_name='d_metric',o_config=None,o_data=None):
_analyzer = PyposmatDataAnalyzer()
_analyzer.read_configuration_file(filename=config_fn)
_analyzer.read_data_file(filename=data_fn)
# calculate the scoring metric
if metric_name is 'd_metric':
_df = _analyzer.calculate_d_metric(df=_analyzer.datafile.df)
else:
s = "The metric name {} is unsupported"
s = s.format(metric_name)
raise PyposmatUnsupportedPotentialScoringMetric(s)
_data = PyposmatDataFile()
_data.read(filename=data_fn)
_data.df = _df
_data.subselect_by_score(score_name='d_metric',n=1)
_free_parameter_names = _analyzer.configuration.free_parameter_names
_parameter_best_dict = OrderedDict()
for pn in _free_parameter_names:
_parameter_best_dict[pn] = _data.sub_parameter_df.iloc[0][pn]
return _parameter_best_dict
def get_parameter_variance(
config_fn,data_fn,
metric_name='d_metric',
n=100,
o_config=None,
o_data=None):
"""
Args:
config_fn (str):
data_fn (str):
metric_name (str): (default:d_metric)
n (int): the number of best metric values
o_config (pypospack.config.data.PyposmatConfigurationFile)
o_data (pypospack.config.data.PyposmatDataFile)
Returns:
collections.OrderedDict
Raises:
PyposmatUnknownPotentialScoringMetric
"""
_analyzer = PyposmatDataAnalyzer()
_analyzer.read_configuration_file(filename=config_fn)
_analyzer.read_data_file(filename=data_fn)
# calculate the scoring metric
if metric_name is 'd_metric':
_df = _analyzer.calculate_d_metric(df=_analyzer.datafile.df)
else:
s = "The metric name {} is unsupported"
s = s.format(metric_name)
raise PyposmatUnsupportedPotentialScoringMetric(s)
_data = PyposmatDataFile()
_data.read(filename=data_fn)
_data.df = _df
_data.subselect_by_score(score_name='d_metric',n=n)
_param_std_df = _data.sub_parameter_df.std(axis=0)
_parameter_std_dict = OrderedDict()
for pn in _analyzer.parameter_names:
_parameter_std_dict[pn] =_param_std_df.to_dict()[pn]
return _parameter_std_dict
if __name__ == "__main__":
import os
import pypospack.utils
_pypospack_root = pypospack.utils.get_pypospack_root_directory()
_data_in_directory = os.path.join(
_pypospack_root, 'examples',
'Ni__eam__born_exp_fs__sensitivityanalysis',
'data__from_pareto_optimization')
_pyposmat_data_fn = os.path.join(_data_in_directory, 'pyposmat.kde.6.out')
_pyposmat_config_fn = os.path.join(_data_in_directory,
'pyposmat.config.in')
analyzer = PyposmatDataAnalyzer()
analyzer.read_configuration_file(filename=_pyposmat_config_fn)
analyzer.read_data_file(filename=_pyposmat_data_fn)
df = analyzer.calculate_d_metric(df=analyzer.datafile.df)
data = PyposmatDataFile()
data.read(filename=_pyposmat_data_fn)
data.df = df
data.subselect_by_score(score_name="d_metric", n=100)
# print(data.sub_df)
param_stdev_df = data.sub_parameter_df.std(axis=0)
param_mean_df = data.sub_parameter_df.mean(axis=0)
print("parameter standard deviations:\n{}".format(param_stdev_df))
print("parameter means:\n{}".format(param_mean_df))
data.subselect_by_score(score_name="d_metric", n=1)
print("best parameterization by d_metric:\n{}".format(
data.sub_parameter_df))