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 __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)
from matminer.featurizers import composition as cf
from matminer.featurizers.conversions import StrToComposition
from pymatgen.core.composition import Composition
import numpy as np
import pandas as pd
import bz2
import _pickle as cPickle
import argparse
feature_calculators = MultipleFeaturizer([
cf.ElementProperty.from_preset(preset_name="magpie"),
cf.Stoichiometry(),
cf.ValenceOrbital(props=['frac']),
cf.IonProperty(fast=True),
cf.BandCenter(),
cf.ElementFraction(),
])
def generate(fake_df, ignore_errors=False):
fake_df = np.array([fake_df])
fake_df = pd.DataFrame(fake_df)
fake_df.columns = ['full_formula']
# print(fake_df)
fake_df = StrToComposition().featurize_dataframe(
fake_df, "full_formula", ignore_errors=ignore_errors)
fake_df = fake_df.dropna()
fake_df = feature_calculators.featurize_dataframe(
fake_df, col_id='composition', ignore_errors=ignore_errors)
fake_df["NComp"] = fake_df["composition"].apply(len)
return fake_df