def test_op_site_fingerprint(self):
opsf = OPSiteFingerprint()
l = opsf.feature_labels()
t = ["sgl_bd CN_1", "bent180 CN_2", "bent45 CN_2", "bent90 CN_2", \
"bent135 CN_2", "tri_plan CN_3", "tet CN_3", "T CN_3", \
"sq_plan CN_4", "sq CN_4", "tet CN_4", "see_saw CN_4", \
"tri_pyr CN_4", "pent_plan CN_5", "sq_pyr CN_5", \
"tri_bipyr CN_5", "oct CN_6", "pent_pyr CN_6", "hex_pyr CN_7", \
"pent_bipyr CN_7", "bcc CN_8", "hex_bipyr CN_8", \
"q2 CN_9", "q4 CN_9", "q6 CN_9", \
"q2 CN_10", "q4 CN_10", "q6 CN_10",
"q2 CN_11", "q4 CN_11", "q6 CN_11", \
"cuboct CN_12", "q2 CN_12", "q4 CN_12", "q6 CN_12"]
for i in range(len(l)):
self.assertEqual(l[i], t[i])
ops = opsf.featurize(self.sc, 0)
self.assertEqual(len(ops), 35)
self.assertAlmostEqual(int(1000 * ops[opsf.feature_labels().index(
'oct CN_6')]), 999)
ops = opsf.featurize(self.cscl, 0)
self.assertAlmostEqual(int(1000 * ops[opsf.feature_labels().index(
'bcc CN_8')] + 0.5), 895)
opsf = OPSiteFingerprint(dist_exp=0)
ops = opsf.featurize(self.cscl, 0)
self.assertAlmostEqual(int(1000 * ops[opsf.feature_labels().index(
'bcc CN_8')] + 0.5), 955)
def get_tet_bcc_motif(structure, idx):
"""
Convenience class-method from Nils Zimmermann.
Used to distinguish coordination environment in half-Heuslers.
Args:
structure (pymatgen Structure): the target structure to evaluate
idx (index): the site index in the structure
Returns:
(str) that describes site coordination enviornment
'bcc'
'tet'
'unrecognized'
"""
op_site_fp = OPSiteFingerprint()
fp = op_site_fp.featurize(structure, idx)
labels = op_site_fp.feature_labels()
i_tet = labels.index('tet CN_4')
i_bcc = labels.index('bcc CN_8')
if fp[i_bcc] > 0.5:
return 'bcc'
elif fp[i_tet] > 0.5:
return 'tet'
else:
return 'unrecognized'
def test_op_site_fingerprint(self):
opsf = OPSiteFingerprint()
l = opsf.feature_labels()
t = ['sgl_bd CN_1', 'L-shaped CN_2', 'water-like CN_2', \
'bent 120 degrees CN_2', 'bent 150 degrees CN_2', \
'linear CN_2', 'trigonal planar CN_3', \
'trigonal non-coplanar CN_3', 'T-shaped CN_3', \
'square co-planar CN_4', 'tetrahedral CN_4', \
'rectangular see-saw-like CN_4', 'see-saw-like CN_4', \
'trigonal pyramidal CN_4', 'pentagonal planar CN_5', \
'square pyramidal CN_5', 'trigonal bipyramidal CN_5', \
'hexagonal planar CN_6', 'octahedral CN_6', \
'pentagonal pyramidal CN_6', 'hexagonal pyramidal CN_7', \
'pentagonal bipyramidal CN_7', 'body-centered cubic CN_8', \
'hexagonal bipyramidal CN_8', 'q2 CN_9', 'q4 CN_9', 'q6 CN_9', \
'q2 CN_10', 'q4 CN_10', 'q6 CN_10', \
'q2 CN_11', 'q4 CN_11', 'q6 CN_11', \
'cuboctahedral CN_12', 'q2 CN_12', 'q4 CN_12', 'q6 CN_12']
for i in range(len(l)):
self.assertEqual(l[i], t[i])
ops = opsf.featurize(self.sc, 0)
self.assertEqual(len(ops), 37)
self.assertAlmostEqual(
ops[opsf.feature_labels().index('octahedral CN_6')],
0.9995,
places=7)
ops = opsf.featurize(self.cscl, 0)
self.assertAlmostEqual(
ops[opsf.feature_labels().index('body-centered cubic CN_8')],
0.8955,
places=7)
opsf = OPSiteFingerprint(dist_exp=0)
ops = opsf.featurize(self.cscl, 0)
self.assertAlmostEqual(
ops[opsf.feature_labels().index('body-centered cubic CN_8')],
0.9555,
places=7)
# The following test aims at ensuring the copying of the OP dictionaries work.
opsfp = OPSiteFingerprint()
cnnfp = CrystalNNFingerprint.from_preset('ops')
self.assertEqual(
len([1 for l in opsfp.feature_labels() if l.split()[0] == 'wt']),
0)
def test_op_site_fingerprint(self):
opsf = OPSiteFingerprint()
l = opsf.feature_labels()
t = ['sgl_bd CN_1', 'L-shaped CN_2', 'water-like CN_2', \
'bent 120 degrees CN_2', 'bent 150 degrees CN_2', \
'linear CN_2', 'trigonal planar CN_3', \
'trigonal non-coplanar CN_3', 'T-shaped CN_3', \
'square co-planar CN_4', 'tetrahedral CN_4', \
'rectangular see-saw-like CN_4', 'see-saw-like CN_4', \
'trigonal pyramidal CN_4', 'pentagonal planar CN_5', \
'square pyramidal CN_5', 'trigonal bipyramidal CN_5', \
'hexagonal planar CN_6', 'octahedral CN_6', \
'pentagonal pyramidal CN_6', 'hexagonal pyramidal CN_7', \
'pentagonal bipyramidal CN_7', 'body-centered cubic CN_8', \
'hexagonal bipyramidal CN_8', 'q2 CN_9', 'q4 CN_9', 'q6 CN_9', \
'q2 CN_10', 'q4 CN_10', 'q6 CN_10', \
'q2 CN_11', 'q4 CN_11', 'q6 CN_11', \
'cuboctahedral CN_12', 'q2 CN_12', 'q4 CN_12', 'q6 CN_12']
for i in range(len(l)):
self.assertEqual(l[i], t[i])
ops = opsf.featurize(self.sc, 0)
self.assertEqual(len(ops), 37)
self.assertAlmostEqual(
ops[opsf.feature_labels().index('octahedral CN_6')],
0.9995,
places=7)
ops = opsf.featurize(self.cscl, 0)
self.assertAlmostEqual(
ops[opsf.feature_labels().index('body-centered cubic CN_8')],
0.8955,
places=7)
opsf = OPSiteFingerprint(dist_exp=0)
ops = opsf.featurize(self.cscl, 0)
self.assertAlmostEqual(
ops[opsf.feature_labels().index('body-centered cubic CN_8')],
0.9555,
places=7)
def test_op_site_fingerprint(self):
opsf = OPSiteFingerprint()
l = opsf.feature_labels()
t = ['sgl_bd CN_1', 'L-shaped CN_2', 'water-like CN_2', \
'bent 120 degrees CN_2', 'bent 150 degrees CN_2', \
'linear CN_2', 'trigonal planar CN_3', \
'trigonal non-coplanar CN_3', 'T-shaped CN_3', \
'square co-planar CN_4', 'tetrahedral CN_4', \
'rectangular see-saw-like CN_4', 'see-saw-like CN_4', \
'trigonal pyramidal CN_4', 'pentagonal planar CN_5', \
'square pyramidal CN_5', 'trigonal bipyramidal CN_5', \
'hexagonal planar CN_6', 'octahedral CN_6', \
'pentagonal pyramidal CN_6', 'hexagonal pyramidal CN_7', \
'pentagonal bipyramidal CN_7', 'body-centered cubic CN_8', \
'hexagonal bipyramidal CN_8', 'q2 CN_9', 'q4 CN_9', 'q6 CN_9', \
'q2 CN_10', 'q4 CN_10', 'q6 CN_10', \
'q2 CN_11', 'q4 CN_11', 'q6 CN_11', \
'cuboctahedral CN_12', 'q2 CN_12', 'q4 CN_12', 'q6 CN_12']
for i in range(len(l)):
self.assertEqual(l[i], t[i])
ops = opsf.featurize(self.sc, 0)
self.assertEqual(len(ops), 37)
self.assertAlmostEqual(ops[opsf.feature_labels().index(
'octahedral CN_6')], 0.9995, places=7)
ops = opsf.featurize(self.cscl, 0)
self.assertAlmostEqual(ops[opsf.feature_labels().index(
'body-centered cubic CN_8')], 0.8955, places=7)
opsf = OPSiteFingerprint(dist_exp=0)
ops = opsf.featurize(self.cscl, 0)
self.assertAlmostEqual(ops[opsf.feature_labels().index(
'body-centered cubic CN_8')], 0.9555, places=7)
# The following test aims at ensuring the copying of the OP dictionaries work.
opsfp = OPSiteFingerprint()
cnnfp = CrystalNNFingerprint.from_preset('ops')
self.assertEqual(len([1 for l in opsfp.feature_labels() if l.split()[0] == 'wt']), 0)
class OPStructureFingerprint(BaseFeaturizer):
"""
Calculates all order parameters (OPs) for all sites in a crystal
structure.
Args:
op_site_fp (OPSiteFingerprint): defines the types of order
parameters to be calculated.
stats ([str]): list of weighted statistics to compute for each feature.
If stats is None, for each order parameter, a list is returned that
contains the calculated parameter for each site in the structure.
*Note for nth mode, stat must be 'n*_mode'; e.g. stat='2nd_mode'
min_oxi (int): minimum site oxidation state for inclusion (e.g.,
zero means metals/cations only)
max_oxi (int): maximum site oxidation state for inclusion
"""
def __init__(self, op_site_fp=None, stats=('mean', 'std_dev', 'minimum',
'maximum'), min_oxi=None,
max_oxi=None):
self.op_site_fp = OPSiteFingerprint() if op_site_fp is None \
else op_site_fp
self._labels = self.op_site_fp.feature_labels()
self.stats = tuple([stats]) if type(stats) == str else stats
if self.stats and '_mode' in ''.join(self.stats):
nmodes = 0
for stat in self.stats:
if '_mode' in stat and int(stat[0]) > nmodes:
nmodes = int(stat[0])
self.nmodes = nmodes
self.min_oxi = min_oxi
self.max_oxi = max_oxi
def featurize(self, s):
"""
Calculate all sites' local structure order parameters (LSOPs).
Args:
s: Pymatgen Structure object.
Returns:
opvals: (2D array of floats) LSOP values of all sites'
(1st dimension) order parameters (2nd dimension). 46 order
parameters are computed per site: q_cn (coordination
number), q_lin, 35 x q_bent (starting with a target angle
of 5 degrees and, increasing by 5 degrees, until 175 degrees),
q_tet, q_oct, q_bcc, q_2, q_4, q_6, q_reg_tri, q_sq, q_sq_pyr.
"""
opvals = [[] for t in self._labels]
for i, site in enumerate(s.sites):
if (self.min_oxi is None or site.specie.oxi_state >= self.min_oxi) \
and (self.max_oxi is None or site.specie.oxi_state >= self.max_oxi):
opvalstmp = self.op_site_fp.featurize(s, i)
for j, opval in enumerate(opvalstmp):
if opval is None:
opvals[j].append(0.0)
else:
opvals[j].append(opval)
if self.stats:
opstats = []
for op in opvals:
if '_mode' in ''.join(self.stats):
modes = self.n_numerical_modes(op, self.nmodes, 0.01)
for stat in self.stats:
if '_mode' in stat:
opstats.append(modes[int(stat[0])-1])
else:
opstats.append(PropertyStats().calc_stat(op, stat))
return opstats
else:
return opvals
def feature_labels(self):
if self.stats:
labels = []
for attr in self._labels:
for stat in self.stats:
labels.append('%s %s' % (stat, attr))
return labels
else:
return self._labels
def citations(self):
return ('@article{zimmermann_jain_2017, title={Applications of order'
' parameter feature vectors}, journal={in progress}, author={'
'Zimmermann, N. E. R. and Jain, A.}, year={2017}}')
def implementors(self):
return (['Nils E. R. Zimmermann', 'Alireza Faghaninia', 'Anubhav Jain'])
@staticmethod
def n_numerical_modes(data_lst, n=2, dl=0.1):
"""
Returns the n first modes of a data set that are obtained with
a finite bin size for the underlying frequency distribution.
Args:
data_lst ([float]): data values.
n (integer): number of most frequent elements to be determined.
dl (float): bin size of underlying (coarsened) distribution.
Returns:
([float]): first n most frequent entries (or nan if not found).
"""
if len(set(data_lst)) == 1:
return [data_lst[0]] + [float('NaN') for _ in range(n-1)]
hist, bins = np.histogram(data_lst, bins=np.arange(
min(data_lst), max(data_lst), dl), density=False)
modes = list(bins[np.argsort(hist)[-n:]][::-1])
return modes + [float('NaN') for _ in range(n-len(modes))]