def load_dataset(name, data_home=None, download_if_missing=True):
"""
Loads a dataframe containing the dataset specified with the 'name' field.
Dataset file is stored/loaded from data_home if specified, otherwise at
the MATMINER_DATA environment variable if set or at matminer/datasets
by default.
Args:
name (str): keyword specifying what dataset to load, run
matminer.datasets.get_available_datasets() for options
data_home (str): path to folder to look for dataset file
download_if_missing (bool): whether to download the dataset if is not
found on disk
Returns: (pd.DataFrame,
tuple -> (pd.DataFrame, pd.DataFrame) if return_lumo = True)
"""
global _dataset_dict
if _dataset_dict is None:
_dataset_dict = _load_dataset_dict()
if name not in _dataset_dict:
error_string = "Unrecognized dataset name: {}. \n" \
"Use matminer.datasets.get_available_datasets() " \
"to see a list of currently available " \
"datasets".format(name)
# Very simple attempt to match unrecognized keyword to existing
# dataset names in an attempt to give the user immediate feedback
possible_matches = [
x for x in _dataset_dict.keys() if name.lower() in x.lower()
]
if possible_matches:
error_string += "\nCould you have been looking for these similar " \
"matches?:\n{}".format(possible_matches)
raise ValueError(error_string)
dataset_metadata = _dataset_dict[name]
data_path = os.path.join(_get_data_home(data_home),
name + "." + dataset_metadata['file_type'])
_validate_dataset(data_path, dataset_metadata['url'],
dataset_metadata['hash'], download_if_missing)
df = load_dataframe_from_json(data_path)
return df
def load_dataset(name, data_home=None, download_if_missing=True):
"""
Loads a dataframe containing the dataset specified with the 'name' field.
Dataset file is stored/loaded from data_home if specified, otherwise at
the MATMINER_DATA environment variable if set or at matminer/datasets
by default.
Args:
name (str): keyword specifying what dataset to load, run
matminer.datasets.get_available_datasets() for options
data_home (str): path to folder to look for dataset file
download_if_missing (bool): whether to download the dataset if is not
found on disk
Returns: (pd.DataFrame,
tuple -> (pd.DataFrame, pd.DataFrame) if return_lumo = True)
"""
global _dataset_dict
if _dataset_dict is None:
_dataset_dict = _load_dataset_dict()
if name not in _dataset_dict:
error_string = "Unrecognized dataset name: {}. \n" \
"Use matminer.datasets.get_available_datasets() " \
"to see a list of currently available " \
"datasets".format(name)
# Very simple attempt to match unrecognized keyword to existing
# dataset names in an attempt to give the user immediate feedback
possible_matches = [
x for x in _dataset_dict.keys() if name.lower() in x.lower()
]
if possible_matches:
error_string += "\nCould you have been looking for these similar " \
"matches?:\n{}".format(possible_matches)
raise ValueError(error_string)
dataset_metadata = _dataset_dict[name]
data_path = os.path.join(_get_data_home(data_home),
name + "." + dataset_metadata['file_type'])
_validate_dataset(data_path, dataset_metadata['url'],
dataset_metadata['hash'], download_if_missing)
df = load_dataframe_from_json(data_path)
return df
def load_dataset(name,
data_home=None,
download_if_missing=True,
include_metadata=False):
"""
Loads a dataframe containing the dataset specified with the 'name' field.
Dataset file is stored/loaded from data_home if specified, otherwise at
the MATMINER_DATA environment variable if set or at matminer/datasets
by default.
Args:
name (str): keyword specifying what dataset to load, run
matminer.datasets.available_datasets() for options
data_home (str): path to folder to look for dataset file
download_if_missing (bool): whether to download the dataset if is not
found on disk
include_metadata (bool): optional argument for some datasets with
metadata fields
Returns: (pd.DataFrame)
"""
dataset_dict = _load_dataset_dict()
if name not in dataset_dict:
error_string = "Unrecognized dataset name: {}. \n" \
"Use matminer.datasets.available_datasets() " \
"to see a list of currently available " \
"datasets".format(name)
# Very simple attempt to match unrecognized keyword to existing
# dataset names in an attempt to give the user immediate feedback
possible_matches = [
x for x in dataset_dict.keys() if name.lower() in x.lower()
]
if possible_matches:
error_string += "\nCould you have been looking for these similar " \
"matches?:\n{}".format(possible_matches)
raise ValueError(error_string)
dataset_metadata = dataset_dict[name]
data_path = os.path.join(_get_data_home(data_home),
name + "." + dataset_metadata['file_type'])
_validate_dataset(data_path, dataset_metadata['url'],
dataset_metadata['hash'], download_if_missing)
df = load_dataframe_from_json(data_path)
if not include_metadata:
if name == "elastic_tensor_2015":
df = df.drop(['cif', 'kpoint_density', 'poscar'], axis=1)
elif name in {"piezoelectric_tensor", "dielectric_constant"}:
df = df.drop(['cif', 'meta', 'poscar'], axis=1)
return df
def test_get_data_home(self):
home = _get_data_home()
self.assertEqual(home, self.dataset_dir)
specified_home = _get_data_home('/some/specified/path')
self.assertEqual(specified_home, '/some/specified/path')
def test_get_data_home(self):
home = _get_data_home()
self.assertEqual(home, self.dataset_dir)
specified_home = _get_data_home('/some/specified/path')
self.assertEqual(specified_home, '/some/specified/path')