CBFVGenerator

class mastml.feature_generators.CBFVGenerator(featurize_df, featurization_method='oliynyk', drop_duplicates=False)

Bases: BaseGenerator

Class that is used to create elemental-type features using the Composition-based feature vector (CBFV) package: https://github.com/Kaaiian/CBFV

Args:

featurize_df: (pd.DataFrame), dataframe containing vector of chemical compositions (strings) to generate elemental features from

featurization_method: (str), string argument specifying which type of features to generate. Choices are: ‘magpie’,

‘jarvis’, ‘mat2vec’, ‘oliynyk’.

drop_duplicates: (bool), whether to remove duplicate columns from the generated feature set

Methods:

fit: pass through, copies input columns as pre-generated features

Args:

X: (pd.DataFrame), input dataframe containing X data

y: (pd.Series), series containing y data

transform: generate the elemental feature matrix from composition strings

Args:

None.

Returns:

X: (dataframe), output dataframe containing generated features

y: (series), output y data as series

Methods Summary

fit([X, y])
transform([X])

Methods Documentation

fit(X=None, y=None)

transform(X=None)