def featurize_site(self, df):
"""Applies the preset site featurizers to the input dataframe,
renames some fields and cleans the output dataframe.
"""
aliases = {
"GeneralizedRadialDistributionFunction": "GeneralizedRDF",
"AGNIFingerprints": "AGNIFingerPrint",
"BondOrientationalParameter": "BondOrientationParameter",
"GaussianSymmFunc": "ChemEnvSiteFingerprint|GaussianSymmFunc",
}
df = super().featurize_site(df, aliases=aliases)
df = df.loc[:, (df != 0).any(axis=0)]
return clean_df(df)
def featurize_structure(self, df):
"""Applies the preset structural featurizers to the input dataframe,
renames some fields and cleans the output dataframe.
"""
df = super().featurize_structure(df)
dist = df["RadialDistributionFunction|radial distribution function"].iloc[0][
"distances"
][:50]
for i, d in enumerate(dist):
_rdf_key = "RadialDistributionFunction|radial distribution function|d_{:.2f}".format(
d
)
df[_rdf_key] = df[
"RadialDistributionFunction|radial distribution function"
].apply(lambda x: x["distribution"][i])
df = df.drop("RadialDistributionFunction|radial distribution function", axis=1)
_crystal_system = {
"cubic": 1,
"tetragonal": 2,
"orthorombic": 3,
"hexagonal": 4,
"trigonal": 5,
"monoclinic": 6,
"triclinic": 7,
}
def _int_map(x):
if x == np.nan:
return 0
elif x:
return 1
else:
return 0
df["GlobalSymmetryFeatures|crystal_system"] = df[
"GlobalSymmetryFeatures|crystal_system"
].map(_crystal_system)
df["GlobalSymmetryFeatures|is_centrosymmetric"] = df[
"GlobalSymmetryFeatures|is_centrosymmetric"
].map(_int_map)
return clean_df(df)
def featurize_bandstructure(self, df):
"""Applies the preset band structure featurizers to the input dataframe,
renames some fields and cleans the output dataframe.
"""
df = super().featurize_bandstructure(df)
def _int_map(x):
if str(x) == "False":
return 0
elif str(x) == "True":
return 1
df["BandFeaturizer|is_gap_direct"] = df[
"BandFeaturizer|is_gap_direct"].map(_int_map)
df = df.drop(["bandstructure"], axis=1)
return clean_df(df)
def featurize_composition(self, df):
"""Applies the preset composition featurizers to the input dataframe,
renames some fields and cleans the output dataframe.
"""
df = super().featurize_composition(df)
_orbitals = {"s": 1, "p": 2, "d": 3, "f": 4}
df["AtomicOrbitals|HOMO_character"] = df[
"AtomicOrbitals|HOMO_character"].map(_orbitals)
df["AtomicOrbitals|LUMO_character"] = df[
"AtomicOrbitals|LUMO_character"].map(_orbitals)
df["AtomicOrbitals|HOMO_element"] = df[
"AtomicOrbitals|HOMO_element"].apply(
lambda x: -1 if not isinstance(x, str) else Element(x).Z)
df["AtomicOrbitals|LUMO_element"] = df[
"AtomicOrbitals|LUMO_element"].apply(
lambda x: -1 if not isinstance(x, str) else Element(x).Z)
return clean_df(df)
def featurize_dos(self, df):
"""Applies the presetdos featurizers to the input dataframe,
renames some fields and cleans the output dataframe.
"""
df = super().featurize_dos(df)
hotencodeColumns = [
"DOSFeaturizer|vbm_specie_1", "DOSFeaturizer|cbm_specie_1"
]
one_hot = pd.get_dummies(df[hotencodeColumns])
df = df.drop(hotencodeColumns, axis=1).join(one_hot)
_orbitals = {"s": 1, "p": 2, "d": 3, "f": 4}
df["DOSFeaturizer|vbm_character_1"] = df[
"DOSFeaturizer|vbm_character_1"].map(_orbitals)
df["DOSFeaturizer|cbm_character_1"] = df[
"DOSFeaturizer|cbm_character_1"].map(_orbitals)
# Splitting one feature into several floating features
# e.g. number;number;number into three columns
splitColumns = [
"DOSFeaturizer|cbm_location_1", "DOSFeaturizer|vbm_location_1"
]
for column in splitColumns:
try:
newColumns = df[column].str.split(";", n=2, expand=True)
for i in range(0, 3):
df[column + "_" + str(i)] = np.array(newColumns[i]).astype(
np.float)
except:
continue
df = df.drop(splitColumns, axis=1)
df = df.drop(["dos"], axis=1)
return clean_df(df)