def featurize_structure(df: pd.DataFrame) -> pd.DataFrame:
""" Decorate input `pandas.DataFrame` of structures with structural
features from matminer.
Currently applies the set of all matminer structure features.
Args:
df (pandas.DataFrame): the input dataframe with `"structure"`
column containing `pymatgen.Structure` objects.
Returns:
pandas.DataFrame: the decorated DataFrame.
"""
logging.info("Applying structure featurizers...")
df = df.copy()
structure_features = [
DensityFeatures(),
GlobalSymmetryFeatures(),
RadialDistributionFunction(),
CoulombMatrix(),
PartialRadialDistributionFunction(),
SineCoulombMatrix(),
EwaldEnergy(),
BondFractions(),
StructuralHeterogeneity(),
MaximumPackingEfficiency(),
ChemicalOrdering(),
XRDPowderPattern(),
BagofBonds()
]
featurizer = MultipleFeaturizer([feature.fit(df["structure"]) for feature in structure_features])
df = featurizer.featurize_dataframe(df, "structure", multiindex=True, ignore_errors=True)
df.columns = df.columns.map('|'.join).str.strip('|')
dist = df["RadialDistributionFunction|radial distribution function"][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
}
df["GlobalSymmetryFeatures|crystal_system"] = df["GlobalSymmetryFeatures|crystal_system"].map(_crystal_system)
df["GlobalSymmetryFeatures|is_centrosymmetric"] = df["GlobalSymmetryFeatures|is_centrosymmetric"].map(int)
return clean_df(df)
def test_bob(self):
# Test a single fit and featurization
scm = SineCoulombMatrix(flatten=False)
bob = BagofBonds(coulomb_matrix=scm, token=' - ')
bob.fit([self.ni3al])
truth1 = [
235.74041833262768, 1486.4464890775491, 1486.4464890775491,
1486.4464890775491, 38.69353092306119, 38.69353092306119,
38.69353092306119, 38.69353092306119, 38.69353092306119,
38.69353092306119, 83.33991275736257, 83.33991275736257,
83.33991275736257, 83.33991275736257, 83.33991275736257,
83.33991275736257
]
truth1_labels = [
'Al site #0', 'Ni site #0', 'Ni site #1', 'Ni site #2',
'Al - Ni bond #0', 'Al - Ni bond #1', 'Al - Ni bond #2',
'Al - Ni bond #3', 'Al - Ni bond #4', 'Al - Ni bond #5',
'Ni - Ni bond #0', 'Ni - Ni bond #1', 'Ni - Ni bond #2',
'Ni - Ni bond #3', 'Ni - Ni bond #4', 'Ni - Ni bond #5'
]
self.assertAlmostEqual(bob.featurize(self.ni3al), truth1)
self.assertEqual(bob.feature_labels(), truth1_labels)
# Test padding from fitting and dataframe featurization
bob.coulomb_matrix = CoulombMatrix(flatten=False)
bob.fit([self.ni3al, self.cscl, self.diamond_no_oxi])
df = pd.DataFrame({'structures': [self.cscl]})
df = bob.featurize_dataframe(df, 'structures')
self.assertEqual(len(df.columns.values), 25)
self.assertAlmostEqual(df['Cs site #0'][0], 7513.468312122532)
self.assertAlmostEqual(df['Al site #0'][0], 0.0)
self.assertAlmostEqual(df['Cs - Cl bond #1'][0], 135.74726437398044)
self.assertAlmostEqual(df['Al - Ni bond #0'][0], 0.0)
# Test error handling for bad fits or null fits
bob = BagofBonds(CoulombMatrix(flatten=False))
self.assertRaises(NotFittedError, bob.featurize, self.nacl)
bob.fit([self.ni3al, self.diamond])
self.assertRaises(ValueError, bob.featurize, self.nacl)\
def test_bob(self):
# Test a single fit and featurization
bob = BagofBonds(coulomb_matrix=SineCoulombMatrix(), token=' - ')
bob.fit([self.ni3al])
truth1 = [235.74041833262768, 1486.4464890775491, 1486.4464890775491,
1486.4464890775491, 38.69353092306119, 38.69353092306119,
38.69353092306119, 38.69353092306119, 38.69353092306119,
38.69353092306119, 83.33991275736257, 83.33991275736257,
83.33991275736257, 83.33991275736257, 83.33991275736257,
83.33991275736257]
truth1_labels = ['Al site #0', 'Ni site #0', 'Ni site #1', 'Ni site #2',
'Al - Ni bond #0', 'Al - Ni bond #1',
'Al - Ni bond #2', 'Al - Ni bond #3',
'Al - Ni bond #4', 'Al - Ni bond #5',
'Ni - Ni bond #0', 'Ni - Ni bond #1',
'Ni - Ni bond #2', 'Ni - Ni bond #3',
'Ni - Ni bond #4', 'Ni - Ni bond #5']
self.assertAlmostEqual(bob.featurize(self.ni3al), truth1)
self.assertEqual(bob.feature_labels(), truth1_labels)
# Test padding from fitting and dataframe featurization
bob.coulomb_matrix = CoulombMatrix()
bob.fit([self.ni3al, self.cscl, self.diamond_no_oxi])
df = pd.DataFrame({'structures': [self.cscl]})
df = bob.featurize_dataframe(df, 'structures')
self.assertEqual(len(df.columns.values), 25)
self.assertAlmostEqual(df['Cs site #0'][0], 7513.468312122532)
self.assertAlmostEqual(df['Al site #0'][0], 0.0)
self.assertAlmostEqual(df['Cs - Cl bond #1'][0], 135.74726437398044)
self.assertAlmostEqual(df['Al - Ni bond #0'][0], 0.0)
# Test error handling for bad fits or null fits
bob = BagofBonds()
self.assertRaises(NotFittedError, bob.featurize, self.nacl)
bob.fit([self.ni3al, self.diamond])
self.assertRaises(ValueError, bob.featurize, self.nacl)\