def _generate_labels(self, inputs: container.DataFrame) -> None:
self._labels = {}
for col_idx, (label, col) in enumerate(inputs.iteritems()):
# Get all the unique data in the column and assign each element an int representation.
# We reserve 0 for unseen labels so we increment the encodings by one
unique_data = col.unique()
self._labels[col_idx] = {
label: encoded + 1
for encoded, label in enumerate(unique_data)
}
def _encode_labels(self,
inputs: container.DataFrame) -> container.DataFrame:
for col_idx, (label, col) in enumerate(inputs.iteritems()):
encodes = [self._labels[col_idx].get(label, 0) for label in col]
inputs.iloc[:, col_idx] = encodes
return inputs