def __init__(self, exclude=None):
super(CompositionFeaturizers, self).__init__(exclude=exclude)
self._fast_featurizers = [
cf.AtomicOrbitals(),
cf.ElementProperty.from_preset("matminer"),
cf.ElementProperty.from_preset("magpie"),
cf.ElementFraction(),
cf.Stoichiometry(),
cf.TMetalFraction(),
cf.BandCenter(),
cf.ValenceOrbital()
]
self._slow_featurizers = [
cf.Miedema(),
cf.AtomicPackingEfficiency(), # slower than the rest
cf.CohesiveEnergy() # requires mpid present
]
self._need_oxi_featurizers = [
cf.CationProperty.from_preset(preset_name='deml'),
cf.OxidationStates.from_preset(preset_name='deml'),
cf.ElectronAffinity(),
cf.ElectronegativityDiff(),
cf.YangSolidSolution(),
cf.IonProperty()
]
def express(self):
fs = [
cf.ElementProperty.from_preset("magpie"),
cf.OxidationStates.from_preset(preset_name='deml'),
cf.ElectronAffinity(),
cf.IonProperty(),
cf.YangSolidSolution(),
cf.Miedema(),
]
return self._get_featurizers(fs)
def __init__(self):
self.feature_calculators = MultipleFeaturizer([
cf.ElementProperty.from_preset(preset_name="magpie"),
cf.Stoichiometry(),
cf.ValenceOrbital(props=['frac']),
cf.IonProperty(fast=True),
cf.BandCenter(),
cf.ElementFraction(),
])
self.str2composition = StrToComposition()
def all(self):
fs = [
cf.AtomicOrbitals(),
cf.ElementProperty.from_preset("matminer"),
cf.ElementProperty.from_preset("magpie"),
cf.ElementProperty.from_preset("matscholar_el"),
cf.ElementProperty.from_preset("deml"),
cf.ElementFraction(),
cf.Stoichiometry(),
cf.TMetalFraction(),
cf.BandCenter(),
cf.ValenceOrbital(),
cf.YangSolidSolution(),
cf.CationProperty.from_preset(preset_name='deml'),
cf.OxidationStates.from_preset(preset_name='deml'),
cf.ElectronAffinity(),
cf.ElectronegativityDiff(),
cf.IonProperty(),
cf.Miedema(),
cf.AtomicPackingEfficiency(), # slower than the rest
cf.CohesiveEnergy() # requires mpid present
]
return self._get_featurizers(fs)
data['composition'] = data['structure'].apply(lambda x: x.composition)
data['integer_formula'] = data['composition'].apply(
lambda x: x.get_integer_formula_and_factor()[0])
data.sort_values('e_above_hull', ascending=True, inplace=True)
data.drop_duplicates('integer_formula', keep='first', inplace=True)
print('Reduced dataset to {} unique compositions.'.format(len(data)))
data.reset_index(inplace=True, drop=True)
# Create the featurizer, which will take the composition as input
featurizer = MultipleFeaturizer([
cf.Stoichiometry(),
cf.ElementProperty.from_preset('magpie'),
cf.ValenceOrbital(props=['frac']),
cf.IonProperty(fast=True)
])
# Compute the features
featurizer.set_n_jobs(1)
X = featurizer.featurize_many(data['composition'])
# Make the model
model = Pipeline([('imputer', Imputer()), ('model', RandomForestRegressor())])
model.fit(X, data['formation_energy_per_atom'])
print('Trained a RandomForest model')
# Save the model, featurizer, and data using pickle
with open('model.pkl', 'wb') as fp:
pkl.dump(model, fp)
with open('featurizer.pkl', 'wb') as fp:
def load_data_zT():
results_dir = setResDir()
## Metadata
keys_response = [
'Seebeck coefficient; squared', 'Electrical resistivity',
'Thermal conductivity'
]
sign = np.array([
+1, # Seebeck
-1, # Electric resistivity
-1 # Thermal conductivity
])
## Load data, if possible
# --------------------------------------------------
try:
df_X_all = pd.read_csv(results_dir + file_features)
X_all = df_X_all.drop(df_X_all.columns[0], axis=1).values
df_Y_all = pd.read_csv(results_dir + file_responses)
Y_all = df_Y_all.drop(df_Y_all.columns[0], axis=1).values
print("Cached data loaded.")
except FileNotFoundError:
## Data Import
# --------------------------------------------------
# Initialize client
print("Accessing data from Citrination...")
site = 'https://citrination.com' # Citrination
client = CitrinationClient(api_key=os.environ['CITRINATION_API_KEY'],
site=site)
search_client = client.search
# Aluminum dataset
dataset_id = 178480 # ucsb_te_roomtemp_seebeck
system_query = PifSystemReturningQuery(
size=1000,
query=DataQuery(dataset=DatasetQuery(id=Filter(
equal=str(dataset_id)))))
query_result = search_client.pif_search(system_query)
print(" Found {} PIFs in dataset {}.".format(
query_result.total_num_hits, dataset_id))
## Wrangle
# --------------------------------------------------
pifs = [x.system for x in query_result.hits]
# Utility function will tabularize PIFs
df_response = pifs2df(pifs)
# Down-select columns to play well with to_numeric
df_response = df_response[[
'Seebeck coefficient', 'Electrical resistivity',
'Thermal conductivity'
]]
df_response = df_response.apply(pd.to_numeric)
# Parse chemical compositions
formulas = [pif.chemical_formula for pif in pifs]
df_comp = pd.DataFrame(columns=['chemical_formula'], data=formulas)
# Join
df_data = pd.concat([df_comp, df_response], axis=1)
print(" Accessed data.")
# Featurize
print("Featurizing data...")
df_data['composition'] = df_data['chemical_formula'].apply(
get_compostion)
f = MultipleFeaturizer([
cf.Stoichiometry(),
cf.ElementProperty.from_preset("magpie"),
cf.ValenceOrbital(props=['avg']),
cf.IonProperty(fast=True)
])
X = np.array(f.featurize_many(df_data['composition']))
# Find valid response values
keys_original = [
'Seebeck coefficient', 'Electrical resistivity',
'Thermal conductivity'
]
index_valid_response = {
key: df_data[key].dropna().index.values
for key in keys_original
}
index_valid_all = df_data[keys_original].dropna().index.values
X_all = X[index_valid_all, :]
Y_all = df_data[keys_original].iloc[index_valid_all].values
# Manipulate columns for proper objective values
Y_all[:, 0] = Y_all[:, 0]**2 # Squared seebeck
print(" Data prepared; {0:} valid observations.".format(
X_all.shape[0]))
# Cache data
pd.DataFrame(data=X_all).to_csv(results_dir + file_features)
pd.DataFrame(data=Y_all, columns=keys_response).to_csv(results_dir +
file_responses)
print("Data cached in results directory.")
return X_all, Y_all, sign, keys_response, prefix
data.sort_values('delta_e', ascending=True, inplace=True)
data.drop_duplicates('composition', keep='first', inplace=True)
print('Removed %d/%d entries' %
(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))