def test_load_precomputed_dataset():
"""Tries to load and unpack the dataset on figshare.
Warning: Requires ~10 GB of memory.
NB: This test will not redownload the dataset if it is already present.
"""
from modnet.ext_data import load_ext_dataset
from pathlib import Path
path = load_ext_dataset("MP_2018.6", "MODData")
assert path == Path(__file__).parent.parent.joinpath(
"data") / "MP_2018.6.zip"
assert path.is_file()
# Replace the path with some garbage file and make sure a RuntimeError is raised
# when the dataset is loaded, as the hash will no longer match
path.unlink()
path.touch()
try:
with pytest.raises(
RuntimeError,
match="Precomputed MODData did not match expected MD5 from"):
path = load_ext_dataset("MP_2018.6", "MODData")
finally:
path.unlink(missing_ok=True)
def test_load_datasets():
with pytest.raises(ValueError):
load_ext_dataset("abcd", "MODData")
with pytest.raises(ValueError):
load_ext_dataset("MP_2018.6_CROSS_NMI", "MODData")
path = load_ext_dataset("MP_2018.6_CROSS_NMI", "cross_nmi")
df = pandas.read_pickle(path)
assert df.shape == (1304, 1304)
np.testing.assert_array_equal(df.columns, df.index.values)
def load_precomputed(cls, dataset_name: str):
""" Load a `MODData` object from a pre-computed dataset.
Note:
Datasets may require significant (~10 GB) amounts of memory
to load.
Arguments:
dataset: the name of the precomputed dataset to load.
Currently available: 'MP_2018.6'.
Returns:
MODData: the precomputed dataset.
"""
from modnet.ext_data import load_ext_dataset
model_path = load_ext_dataset(dataset_name, "MODData")
return cls.load(str(model_path))
def feature_selection(
self,
n: int = 1500,
cross_nmi: Optional[pd.DataFrame] = None,
use_precomputed_cross_nmi: bool = False,
n_jobs: int = None,
):
"""Compute the mutual information between features and targets,
then apply relevance-redundancy rankings to choose the top `n`
features.
Sets the `self.optimal_features` attribute to a list of feature
names.
Args:
n: number of desired features.
cross_nmi: specify the cross NMI between features as a
dataframe.
use_precomputed_cross_nmi: Whether or not to use the cross NMI
that was computed on Materials Project features, instead of
precomputing.
n_jobs: max. number of processes to use when calculating cross NMI.
"""
if getattr(self, "df_featurized", None) is None:
raise RuntimeError(
"Mutual information feature selection requiresd featurized data, please call `.featurize()`"
)
if getattr(self, "df_targets", None) is None:
raise RuntimeError(
"Mutual information feature selection requires target properties"
)
ranked_lists = []
optimal_features_by_target = {}
if cross_nmi is not None:
self.cross_nmi = cross_nmi
elif getattr(self, "cross_nmi", None) is None:
self.cross_nmi = None
# Loading mutual information between features
if use_precomputed_cross_nmi:
LOG.info("Loading cross NMI from 'Features_cross' file.")
from modnet.ext_data import load_ext_dataset
cnmi_path = load_ext_dataset("MP_2018.6_CROSS_NMI", "cross_nmi")
self.cross_nmi = pd.read_pickle(cnmi_path)
precomputed_cols = set(self.cross_nmi.columns)
featurized_cols = set(self.df_featurized.columns)
if len(precomputed_cols | featurized_cols) > len(precomputed_cols):
LOG.warning(
"Feature mismatch between precomputed `Features_cross` and `df_featurized`. "
f"Missing columns: {featurized_cols - precomputed_cols}")
if self.cross_nmi is None:
df = self.df_featurized.copy()
self.cross_nmi, self.feature_entropy = get_cross_nmi(
df, return_entropy=True, n_jobs=n_jobs)
if self.cross_nmi.isna().sum().sum() > 0:
raise RuntimeError(
"Cross NMI (`moddata.cross_nmi`) contains NaN values, consider setting them to zero."
)
for i, name in enumerate(self.names):
LOG.info(
f"Starting target {i + 1}/{len(self.names)}: {self.names[i]} ..."
)
# Computing mutual information with target
LOG.info(
"Computing mutual information between features and target...")
if getattr(self, "num_classes",
None) and self.num_classes[name] >= 2:
task_type = "classification"
else:
task_type = "regression"
self.target_nmi = nmi_target(self.df_featurized,
self.df_targets[[name]],
task_type)[name]
LOG.info("Computing optimal features...")
optimal_features_by_target[name] = get_features_dyn(
n, self.cross_nmi, self.target_nmi)
ranked_lists.append(optimal_features_by_target[name])
LOG.info("Done with target {}/{}: {}.".format(
i + 1, len(self.names), name))
LOG.info("Merging all features...")
self.optimal_features = merge_ranked(ranked_lists)
self.optimal_features_by_target = optimal_features_by_target
LOG.info("Done.")
