def test_load_elastic_tensor(self):
df = load_elastic_tensor()
self.assertTrue(isinstance(df, pd.DataFrame))
self.assertEqual(len(df.columns), 17)
df = load_elastic_tensor(include_metadata=True)
self.assertTrue(isinstance(df, pd.DataFrame))
self.assertEqual(len(df.columns), 20)
def test_load_elastic_tensor(self):
df = load_elastic_tensor()
self.assertTrue(isinstance(df, pd.DataFrame))
self.assertEqual(len(df.columns), 17)
df = load_elastic_tensor(include_metadata=True)
self.assertTrue(isinstance(df, pd.DataFrame))
self.assertEqual(len(df.columns), 20)
def load_tutorial_data():
"""
Helper function to load tutorial data, loads
the elastic tensor data from the MatMiner/MP API
drops columns and renames the VRH K and G to
bulk and shear modulus, rounds to 1 decimal
point, and sets the index to the material id
"""
data = load_elastic_tensor()
data = data.drop(
[
'nsites',
# 'space_group',
'elastic_anisotropy',
'structure',
'volume',
'G_Voigt',
'G_Reuss',
'K_Voigt',
'K_Reuss',
'compliance_tensor',
'elastic_tensor',
'elastic_tensor_original',
'poisson_ratio'
],
axis=1)
data = data.rename({
"K_VRH": "bulk_modulus",
"G_VRH": "shear_modulus"
},
axis='columns')
data = data.round(1)
data = data.set_index('material_id')
return data
def test_files():
df=load_elastic_tensor()
df.to_csv('原始elastic数据.csv')
print(df.columns)
unwanted_columns=['volume','nsites','compliance_tensor','elastic_tensor','elastic_tensor_original','K_Voigt','G_Voigt','K_Reuss','G_Reuss']
df=df.drop(unwanted_columns,axis=1)
print(df.head())
df.to_csv('扔掉不需要的部分.csv')
def generate_data():
df = load_elastic_tensor()
df.to_csv('原始elastic数据.csv')
print(df.columns)
unwanted_columns = [
'volume', 'nsites', 'compliance_tensor', 'elastic_tensor',
'elastic_tensor_original', 'K_Voigt', 'G_Voigt', 'K_Reuss', 'G_Reuss'
]
df = df.drop(unwanted_columns, axis=1)
print(df.head())
df.to_csv('扔掉不需要的部分.csv')
#首先使用describe获得对于数据的整体把握
print(df.describe())
df.describe().to_csv('general_look.csv')
#通过观察数据发现并没有什么异常之处
df = StrToComposition().featurize_dataframe(df, 'formula')
print(df.head())
df.to_csv('引入composition.csv')
#下一步，我们需要其中一个特征化来增加一系列的特征算符
ep_feat = ElementProperty.from_preset(preset_name='magpie')
df = ep_feat.featurize_dataframe(
df, col_id='composition') #将composition这一列作为特征化的输入
print(df.head())
print(ep_feat.citations())
df.to_csv('将composition特征化后.csv')
#开始引入新的特征化算符吧
df = CompositionToOxidComposition().featurize_dataframe(
df, 'composition') #引入了氧化态的相关特征
os_feat = OxidationStates()
df = os_feat.featurize_dataframe(df, col_id='composition_oxid')
print(df.head())
df.to_csv('引入氧化态之后.csv')
#其实除了基于composition的特征之外还有很多其他的，比如基于结构的
df_feat = DensityFeatures()
df = df_feat.featurize_dataframe(df, 'structure')
print(df.head())
df.to_csv('引入结构中的密度.csv')
print(df_feat.feature_labels())
from matminer.datasets.convenience_loaders import load_elastic_tensor
df = load_elastic_tensor()
print(df.columns)
"""
Index(['material_id', 'formula', 'nsites', 'space_group', 'volume',
'structure', 'elastic_anisotropy', 'G_Reuss', 'G_VRH', 'G_Voigt',
'K_Reuss', 'K_VRH', 'K_Voigt', 'poisson_ratio', 'compliance_tensor',
'elastic_tensor', 'elastic_tensor_original'],
dtype='object')
"""
unwanted_columns = ["volume", "nsites", "compliance_tensor", "elastic_tensor",
"elastic_tensor_original", "K_Voigt", "G_Voigt", "K_Reuss", "G_Reuss"]
df = df.drop(unwanted_columns, axis=1)
from matminer.featurizers.conversions import StrToComposition
df = StrToComposition().featurize_dataframe(df, 'formula')
from matminer.featurizers.composition import ElementProperty
ep_feat = ElementProperty.from_preset(preset_name="magpie")
df = ep_feat.featurize_dataframe(df, col_id='composition')
from matminer.featurizers.conversions import CompositionToOxidComposition
from matminer.featurizers.composition import OxidationStates
df = CompositionToOxidComposition().featurize_dataframe(df, "composition")
os_feat = OxidationStates()
df = os_feat.featurize_dataframe(df, "composition_oxid")