so_magic.data.backend.panda_handling.df_encoding

Complexity

Total Complexity

2

Size/Duplication

Total Lines	15
Duplicated Lines	0 %

Importance

Changes

0

2 Methods

Rating	Name	Duplication	Size	Complexity
A	DFEncoderFactory.nominal_encoder()	0	2	1
A	NominalEncoder.encode()	0	3	1

import pandas as pd
from data.encoding import EncoderFactory, AbstractEncoder


class NominalEncoder(AbstractEncoder):
    def encode(self, *args, **kwargs):
        dataset, feature = args[0], args[1]
        return pd.get_dummies(dataset.datapoints.observations.df, f'{feature.label}-{feature.state.current}')


@EncoderFactory.register_as_subclass('pandas')
class DFEncoderFactory(EncoderFactory):
    def nominal_encoder(self, feature, **kwargs):
        return NominalEncoder()