NaNLabelEncoder

class pytorch_forecasting.data.encoders.NaNLabelEncoder(add_nan: bool = False, warn: bool = True)

Bases: sklearn.base.BaseEstimator, sklearn.base.TransformerMixin

Labelencoder that can optionally always encode nan and unknown classes (in transform) as class 0

init NaNLabelEncoder

Parameters

• add_nan – if to force encoding of nan at 0

• warn – if to warn if additional nans are added because items are unknown

Inherited-members

Methods

fit(y)	Fit transformer
fit_transform(y)	Fit and transform data.
get_params([deep])	Get parameters for this estimator.
inverse_transform(y)	Decode data, i.e. transform from integers to labels.
is_numeric(y)	Determine if series is numeric or not.
set_params(**params)	Set the parameters of this estimator.
transform(y)	Encode iterable with integers.

fit(y: pandas.core.series.Series)

Fit transformer

Parameters

y (pd.Series) – input data to fit on

Returns

self

Return type

NaNLabelEncoder

fit_transform(y: pandas.core.series.Series) → numpy.ndarray

Fit and transform data.

Parameters

y (pd.Series) – input data

Returns

encoded data

Return type

np.ndarray

inverse_transform(y: Union[torch.Tensor, numpy.ndarray]) → numpy.ndarray

Decode data, i.e. transform from integers to labels.

Parameters

y (Union[torch.Tensor, np.ndarray]) – encoded data

Raises

KeyError – if unknown elements should be decoded

Returns

decoded data

Return type

np.ndarray

static is_numeric(y: pandas.core.series.Series) → bool

Determine if series is numeric or not. Will also return True if series is a categorical type with underlying integers.

Parameters

y (pd.Series) – series for which to carry out assessment

Returns

True if series is numeric

Return type

bool

transform(y: Iterable) → Union[torch.Tensor, numpy.ndarray]

Encode iterable with integers.

Parameters

y (Iterable) – iterable to encode

Returns

returns encoded data as torch tensor or numpy array depending on input type

Return type

Union[torch.Tensor, np.ndarray]

GroupNormalizer TorchNormalizer