def composition_featurizer(df_input: pd.DataFrame, **kwargs) -> pd.DataFrame:
"""Return a Pandas DataFrame with all compositional features"""
# generate the "composition" column
df_comp = StrToComposition().featurize_dataframe(df_input,
col_id="Compound")
# generate features based on elemental properites
ep_featurizer = ElementProperty.from_preset(preset_name="magpie")
ep_featurizer.featurize_dataframe(df_comp,
col_id="composition",
inplace=True)
# generate the "composition_oxid" column based on guessed oxidation states
CompositionToOxidComposition(
return_original_on_error=True, **kwargs).featurize_dataframe(
# ignore errors from non-integer stoichiometries
df_comp,
"composition",
ignore_errors=True,
inplace=True)
# correct oxidation states
df_comp = correct_comp_oxid(df_comp)
# generate features based on oxidation states
os_featurizer = OxidationStates()
os_featurizer.featurize_dataframe(df_comp,
"composition_oxid",
ignore_errors=True,
inplace=True)
# remove compounds with predicted oxidation states of 0
return df_comp[df_comp["minimum oxidation state"] != 0]
def generate_data(name):
#这个函数作用，输入是指定的文件名，输出增加了gaps，is_daoti，以及其他共计145特征的完整向量矩阵
#name='test_plus_gaps.csv'
df=pd.read_csv(name,index_col=[0])
df['gaps']=-10.0
df_gap=pd.read_csv("gaps.csv",index_col = [0])
print(df_gap.index)
i=0
str_s=""
for j in range(len(df_gap.index)):
#先打印二者的id
# print(df.index[i])
str_s='mp-'+str(df_gap.index[j])
if(str_s==df.index[i]):
df.iloc[i,-1]=df_gap.iloc[j,0]
i=i+1
#print("确实一样")
print("合并完毕")
#同样的方法我们来建立不同的分类
df['is_daoti']=-2
for i in range(len(df.index)):
if(df.ix[i,-2]==0):
df.ix[i,-1]=1
else:
df.ix[i,-1]=0
print("分类feature建立完成")
#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_jie.csv')
#通过观察数据发现并没有什么异常之处
df=StrToComposition().featurize_dataframe(df,'full_formula',ignore_errors=True)
print(df.head())
#print(df['composition'])
ep_feat=ElementProperty.from_preset(preset_name='magpie')
df=ep_feat.featurize_dataframe(df,col_id='composition',ignore_errors=True)#将composition这一列作为特征化的输入
print(df.head())
#print(ep_feat.citations())
#df.to_csv("plus the composition.csv")
#以上这部分是将formula转化为composition并转化feature
df=CompositionToOxidComposition().featurize_dataframe(df,col_id='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')
new_name='2d_vector_plus.csv'
df.to_csv(new_name)
def test_featurizers():
df = pd.read_csv('test.csv', index_col=[0])
df = StrToComposition().featurize_dataframe(df, 'formula')
print(df.head())
#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('after_test.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())
def add_cs_features(df,rdf_flag=False):
df["composition"] = str_to_composition(df["pretty_formula"])
df["composition_oxid"] = composition_to_oxidcomposition(df["composition"])
df["structure"] = dict_to_object(df["structure"])
vo = ValenceOrbital()
df = vo.featurize_dataframe(df,"composition")
ox = OxidationStates()
df = ox.featurize_dataframe(df, "composition_oxid")
# structure features
den = DensityFeatures()
df = den.featurize_dataframe(df, "structure")
if rdf_flag:
rdf = RadialDistributionFunction(cutoff=15.0,bin_size=0.2)
df = rdf.featurize_dataframe(df, "structure")
return df
# Featurization
# This part is done with reference to the matiner examples
from matminer.featurizers.composition import ElementProperty
ep_feat = ElementProperty.from_preset(preset_name="magpie")
data_3 = ep_feat.featurize_dataframe(data_3, col_id="composition")
from matminer.featurizers.conversions import CompositionToOxidComposition
from matminer.featurizers.composition import OxidationStates
data_3 = CompositionToOxidComposition().featurize_dataframe(
data_3, "composition")
os_feat = OxidationStates()
data_3 = os_feat.featurize_dataframe(data_3, "composition_oxid")
from matminer.featurizers.structure import DensityFeatures
df_feat = DensityFeatures()
data_3 = df_feat.featurize_dataframe(data_3, "structure")
unwanted_columns = [
"elasticity", "material_id", "nsites", "compliance_tensor",
"elastic_tensor", "elastic_tensor_original", "K_Voigt", "G_Voigt",
"K_Reuss", "G_Reuss", "warnings"
]
data_4 = data_3.drop(unwanted_columns, axis=1)
# In[ ]:
for col in fdf.columns:
if 'MagpieData' in col:
new_col = col.split('MagpieData ', 1)
del new_col[0]
fin_col = ''.join(new_col)
new_cols.append(fin_col)
cols_dict = dict(zip(magpie_cols, new_cols))
fdf = fdf.rename(columns=cols_dict)
# -- end F1
# -- start F3 --
from matminer.featurizers.composition import OxidationStates
os_feat = OxidationStates()
fdf = os_feat.featurize_dataframe(fdf, 'composition_oxid', ignore_errors=True)
# -- end F3
# -- start F4 --
from matminer.featurizers.composition import AtomicOrbitals
ao_feat = AtomicOrbitals()
fdf = ao_feat.featurize_dataframe(fdf,
col_id='composition',
ignore_errors=True)
# -- end F4
# -- start F5
from matminer.featurizers.composition import BandCenter
bce_feat = BandCenter()
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")
from matminer.featurizers.structure import DensityFeatures
df_feat = DensityFeatures()
df = df_feat.featurize_dataframe(df, col_id='structure')
y = df['K_VRH'].values
excluded = ["G_VRH", "K_VRH", "elastic_anisotropy", "formula", "material_id",
"poisson_ratio", "structure", "composition", "composition_oxid"]
X = df.drop(excluded, axis=1)
print("There are {} possible descriptors:\n\n{}".format(X.shape[1], X.columns.values))
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error
import numpy as np
def AddFeatures(df): # Add features by Matminer
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"
) # input the "composition" column to the featurizer
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")
from matminer.featurizers.composition import ElectronAffinity
ea_feat = ElectronAffinity()
df = ea_feat.featurize_dataframe(df,
"composition_oxid",
ignore_errors=True)
from matminer.featurizers.composition import BandCenter
bc_feat = BandCenter()
df = bc_feat.featurize_dataframe(df,
"composition_oxid",
ignore_errors=True)
from matminer.featurizers.composition import CohesiveEnergy
ce_feat = CohesiveEnergy()
df = ce_feat.featurize_dataframe(df,
"composition_oxid",
ignore_errors=True)
from matminer.featurizers.composition import Miedema
m_feat = Miedema()
df = m_feat.featurize_dataframe(df, "composition_oxid", ignore_errors=True)
from matminer.featurizers.composition import TMetalFraction
tmf_feat = TMetalFraction()
df = tmf_feat.featurize_dataframe(df,
"composition_oxid",
ignore_errors=True)
from matminer.featurizers.composition import ValenceOrbital
vo_feat = ValenceOrbital()
df = vo_feat.featurize_dataframe(df,
"composition_oxid",
ignore_errors=True)
from matminer.featurizers.composition import YangSolidSolution
yss_feat = YangSolidSolution()
df = yss_feat.featurize_dataframe(df,
"composition_oxid",
ignore_errors=True)
from matminer.featurizers.structure import GlobalSymmetryFeatures
# This is the border between compositional features and structural features. Comment out the following featurizers to use only compostional features.
gsf_feat = GlobalSymmetryFeatures()
df = gsf_feat.featurize_dataframe(df, "structure", ignore_errors=True)
from matminer.featurizers.structure import StructuralComplexity
sc_feat = StructuralComplexity()
df = sc_feat.featurize_dataframe(df, "structure", ignore_errors=True)
from matminer.featurizers.structure import ChemicalOrdering
co_feat = ChemicalOrdering()
df = co_feat.featurize_dataframe(df, "structure", ignore_errors=True)
from matminer.featurizers.structure import MaximumPackingEfficiency
mpe_feat = MaximumPackingEfficiency()
df = mpe_feat.featurize_dataframe(df, "structure", ignore_errors=True)
from matminer.featurizers.structure import MinimumRelativeDistances
mrd_feat = MinimumRelativeDistances()
df = mrd_feat.featurize_dataframe(df, "structure", ignore_errors=True)
from matminer.featurizers.structure import StructuralHeterogeneity
sh_feat = StructuralHeterogeneity()
df = sh_feat.featurize_dataframe(df, "structure", ignore_errors=True)
from matminer.featurizers.structure import SiteStatsFingerprint
from matminer.featurizers.site import AverageBondLength
from pymatgen.analysis.local_env import CrystalNN
bl_feat = SiteStatsFingerprint(
AverageBondLength(CrystalNN(search_cutoff=20)))
df = bl_feat.featurize_dataframe(df, "structure", ignore_errors=True)
from matminer.featurizers.site import AverageBondAngle
ba_feat = SiteStatsFingerprint(
AverageBondAngle(CrystalNN(search_cutoff=20)))
df = ba_feat.featurize_dataframe(df, "structure", ignore_errors=True)
from matminer.featurizers.site import BondOrientationalParameter
bop_feat = SiteStatsFingerprint(BondOrientationalParameter())
df = bop_feat.featurize_dataframe(df, "structure", ignore_errors=True)
from matminer.featurizers.site import CoordinationNumber
cn_feat = SiteStatsFingerprint(CoordinationNumber())
df = cn_feat.featurize_dataframe(df, "structure", ignore_errors=True)
from matminer.featurizers.structure import DensityFeatures
df_feat = DensityFeatures()
df = df_feat.featurize_dataframe(df, "structure", ignore_errors=True)
return (df)
df = sc_feat.featurize_dataframe(df, col_id='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
co_feat = CompositionToOxidComposition()
df = co_feat.featurize_dataframe(df, col_id='composition')
from matminer.featurizers.composition import OxidationStates
os_feat = OxidationStates()
df = os_feat.featurize_dataframe(df, col_id='composition_oxid')
from matminer.featurizers.structure import DensityFeatures
df_feat = DensityFeatures()
df = df_feat.featurize_dataframe(df, col_id='structure')
"""
formula, structure, elastic_anisotropy, G_Reuss, G_VRH, G_Voigt, K_Reuss, K_VRH, K_Voigt,
poisson_ratio, compliance_tensor, elastic_tensor, elastic_tensor_original, composition
"""
y = df['K_VRH'].values
excluded = ['formula', 'structure', 'elastic_anisotropy', 'G_Reuss', 'G_VRH', 'G_Voigt',
'K_Reuss', 'K_VRH', 'K_Voigt', 'poisson_ratio', 'compliance_tensor',
'elastic_tensor', 'elastic_tensor_original', 'composition', 'composition_oxid']