def similarity(_parents, target):
featurizer = MultipleFeaturizer([
SiteStatsFingerprint.from_preset("CoordinationNumber_ward-prb-2017"),
StructuralHeterogeneity(),
ChemicalOrdering(),
MaximumPackingEfficiency(),
SiteStatsFingerprint.from_preset(
"LocalPropertyDifference_ward-prb-2017"),
StructureComposition(Stoichiometry()),
StructureComposition(ElementProperty.from_preset("magpie")),
StructureComposition(ValenceOrbital(props=["frac"])),
StructureComposition(IonProperty(fast=True)),
])
# HACK celery doesn't work with multiprocessing (used by matminer)
try:
from celery import current_task
if current_task:
featurizer.set_n_jobs(1)
except ImportError:
pass
x_target = pd.DataFrame.from_records([featurizer.featurize(target)],
columns=featurizer.feature_labels())
x_parent = pd.DataFrame.from_records(
featurizer.featurize_many(_parents, ignore_errors=True, pbar=False),
columns=featurizer.feature_labels(),
)
nulls = x_parent[x_parent.isnull().any(axis=1)].index.values
x_parent.fillna(100000, inplace=True)
x_target = x_target.reindex(sorted(x_target.columns), axis=1)
x_parent = x_parent.reindex(sorted(x_parent.columns), axis=1)
with open(os.path.join(settings.rxn_files, "scaler2.pickle"), "rb") as f:
scaler = pickle.load(f)
with open(os.path.join(settings.rxn_files, "quantiles.pickle"), "rb") as f:
quantiles = pickle.load(f)
X = scaler.transform(x_parent.append(x_target))
D = [pairwise_distances(np.array([row, X[-1]]))[0, 1] for row in X[:-1]]
_res = []
for d in D:
_res.append(np.linspace(0, 1, 101)[np.abs(quantiles - d).argmin()])
_res = np.array(_res)
_res[nulls] = -1
return _res
def test_multifeatures(self):
# Make a test dataset with two input variables
data = self.make_test_data()
data['x2'] = [4, 5, 6]
# Create a second featurizer
class MultiArgs2(SingleFeaturizerMultiArgs):
def featurize(self, *x):
# Making a 2D array to test whether MutliFeaturizer
# can handle featurizers that have both 1D vectors with
# singleton dimensions (e.g., shape==(4,1)) and those
# without (e.g., shape==(4,))
return [super(MultiArgs2, self).featurize(*x)]
def feature_labels(self):
return ['y2']
multiargs2 = MultiArgs2()
# Create featurizer
multi_f = MultipleFeaturizer([self.multiargs, multiargs2])
multi_f.set_n_jobs(1)
# Test featurize with multiple arguments
features = multi_f.featurize(0, 2)
self.assertArrayAlmostEqual([2, 2], features)
# Test dataframe
data = multi_f.featurize_dataframe(data, ['x', 'x2'])
self.assertEquals(['y', 'y2'], multi_f.feature_labels())
self.assertArrayAlmostEqual([[5, 5], [7, 7], [9, 9]], data[['y',
'y2']])
def test_multifeatures_multiargs(self):
multiargs2 = MultiArgs2()
# test iterating over both entries and featurizers
for iter_entries in [True, False]:
# Make a test dataset with two input variables
data = self.make_test_data()
data['x2'] = [4, 5, 6]
# Create featurizer
multi_f = MultipleFeaturizer([self.multiargs, multiargs2],
iterate_over_entries=iter_entries)
# Test featurize with multiple arguments
features = multi_f.featurize(0, 2)
self.assertArrayAlmostEqual([2, 2], features)
# Test dataframe
data = multi_f.featurize_dataframe(data, ['x', 'x2'])
self.assertEqual(['y', 'y2'], multi_f.feature_labels())
self.assertArrayAlmostEqual([[5, 5], [7, 7], [9, 9]],
data[['y', 'y2']])
# Test with multiindex
data = multi_f.featurize_dataframe(data, ['x', 'x2'],
multiindex=True)
self.assertIn(("MultiArgs2", "y2"), data.columns)
self.assertIn(("SingleFeaturizerMultiArgs", "y"), data.columns)
self.assertArrayAlmostEqual([[5, 5], [7, 7], [9, 9]], data[[
("SingleFeaturizerMultiArgs", "y"), ("MultiArgs2", "y2")
]])
def get_structure_properties(structure: Structure, mode: str = 'all') -> dict:
if mode == 'all':
featurizer = MultipleFeaturizer([
SiteStatsFingerprint.from_preset(
'CoordinationNumber_ward-prb-2017'),
StructuralHeterogeneity(),
ChemicalOrdering(),
DensityFeatures(),
MaximumPackingEfficiency(),
SiteStatsFingerprint.from_preset(
'LocalPropertyDifference_ward-prb-2017'),
StructureComposition(Stoichiometry()),
StructureComposition(ElementProperty.from_preset('magpie')),
StructureComposition(ValenceOrbital(props=['frac'])),
])
else:
# Calculate only those which do not need a Voronoi tesselation
featurizer = MultipleFeaturizer([
DensityFeatures(),
StructureComposition(Stoichiometry()),
StructureComposition(ElementProperty.from_preset('magpie')),
StructureComposition(ValenceOrbital(props=['frac'])),
])
X = featurizer.featurize(structure)
matminer_dict = dict(list(zip(featurizer.feature_labels(), X)))
matminer_dict['volume'] = structure.volume
return matminer_dict
def test_multifeatures(self):
# Make a test dataset with two input variables
data = self.make_test_data()
data['x2'] = [4, 5, 6]
multiargs2 = MultiArgs2()
# Create featurizer
multi_f = MultipleFeaturizer([self.multiargs, multiargs2])
# Test featurize with multiple arguments
features = multi_f.featurize(0, 2)
self.assertArrayAlmostEqual([2, 2], features)
# Test dataframe
data = multi_f.featurize_dataframe(data, ['x', 'x2'])
self.assertEquals(['y', 'y2'], multi_f.feature_labels())
self.assertArrayAlmostEqual([[5, 5], [7, 7], [9, 9]], data[['y', 'y2']])
def test_multitype_multifeat(self):
"""Test Multifeaturizer when a featurizer returns a non-numeric type"""
# Make the featurizer
f = MultipleFeaturizer([SingleFeaturizer(), MultiTypeFeaturizer()])
f.set_n_jobs(1)
# Make the test data
data = self.make_test_data()
# Add the columns
data = f.featurize_dataframe(data, 'x')
# Make sure the types are as expected
labels = f.feature_labels()
self.assertArrayEqual(['int64', 'object', 'int64'],
data[labels].dtypes.astype(str).tolist())
self.assertArrayAlmostEqual(data['y'], [2, 3, 4])
def test_multitype_multifeat(self):
"""Test Multifeaturizer when a featurizer returns a non-numeric type"""
# test both iteration over entries and featurizers
for iter_entries in [True, False]:
# Make the featurizer
f = MultipleFeaturizer([SingleFeaturizer(), MultiTypeFeaturizer()],
iterate_over_entries=iter_entries)
f.set_n_jobs(1)
# Make the test data
data = self.make_test_data()
# Add the columns
data = f.featurize_dataframe(data, 'x')
# Make sure the types are as expected
labels = f.feature_labels()
self.assertArrayEqual(['int64', 'object', 'int64'],
data[labels].dtypes.astype(str).tolist())
self.assertArrayAlmostEqual(data['y'], [2, 3, 4])
(original_count - len(data), original_count))
# 用逻辑和的方式筛选[-20,5]范围内的delta_e
original_count = len(data)
data = data[np.logical_and(data['delta_e'] >= -20, data['delta_e'] <= 5)]
print('Removed %d/%d entries' %
(original_count - len(data), original_count))
print(data.head(3))
# 设定化学计算规范：使用MagpieData数据源初始化元素属性，返回各层轨道电子数量信息，假设元素以单一氧化态存在
feature_calculators = MultipleFeaturizer([
cf.Stoichiometry(),
cf.ElementProperty.from_preset("magpie"),
cf.ValenceOrbital(props=['avg']),
cf.IonProperty(fast=False)
])
# 获得特征名
feature_labels = feature_calculators.feature_labels()
# 计算特征量
data = feature_calculators.featurize_dataframe(data,
col_id='composition_obj')
print('Generated %d features' % len(feature_labels))
print('Training set size:',
'x'.join([str(x) for x in data[feature_labels].shape]))
# 去除空值缺省值
original_count = len(data)
data = data[~data[feature_labels].isnull().any(axis=1)]
print('Removed %d/%d entries' %
(original_count - len(data), original_count))
print(data.head(3))
# 调用随机森林
# “随机森林”算法通过训练许多不同的决策树模型来工作，
# 其中每个模型都在数据集的不同子集上进行训练。