How to use the matminer.featurizers.composition function in matminer

data.columns.tolist())

# Get only the minimum energy structure at each composition
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')

print('Loaded {} rows with {} columns:'.format(len(data), len(data.columns)),
      data.columns.tolist())

# Get only the minimum energy structure at each composition
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')

def debug(self):
        return self._get_featurizers([cf.ElementProperty.from_preset("magpie")])

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.Meredig(),
            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(fast=True),
            cf.Miedema(),
            cf.AtomicPackingEfficiency(),  # slower than the rest
            cf.CohesiveEnergy(),  # requires mpid present
        ]
        return self._get_featurizers(fs)