NaNLabelEncoder#

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

Bases: InitialParameterRepresenterMixIn, BaseEstimator, TransformerMixin, TransformMixIn

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

init NaNLabelEncoder

Returns:

  • 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

extra_repr()

Return extra information about parameters for representation/logging.

fit(y[, overwrite])

Fit transformer

fit_transform(y[, overwrite])

Fit and transform data.

get_metadata_routing()

Get metadata routing of this object.

get_parameters([groups, group_names])

Get fitted scaling parameters for a given group.

get_params([deep])

Get parameters for this estimator.

get_transform(transformation)

Return transformation functions.

inverse_preprocess(y)

Inverse preprocess re-scaled data (e.g. take exp).

inverse_transform(y)

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

is_numeric(y)

Determine if series is numeric or not.

preprocess(y)

Preprocess input data (e.g. take log).

set_fit_request(*[, overwrite])

Configure whether metadata should be requested to be passed to the fit method.

set_output(*[, transform])

Set output container.

set_params(**params)

Set the parameters of this estimator.

set_transform_request(*[, ignore_na, ...])

Configure whether metadata should be requested to be passed to the transform method.

transform(y[, return_norm, target_scale, ...])

Encode iterable with integers.

Attributes

TRANSFORMATIONS

static is_numeric(y: Series) → bool[source]#

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

fit(y: Series, overwrite: bool = False)[source]#

Fit transformer

Parameters:

  • y (pd.Series) – input data to fit on

  • overwrite (bool) – whether to overwrite current mappings or if to add to it.

Returns:

NaNLabelEncoder

Return type:

self

fit_transform(y: Series, overwrite: bool = False) → ndarray[source]#

Fit and transform data.

Parameters:

  • y (pd.Series) – input data

  • overwrite (bool) – if to overwrite current mappings or if to add to it.

Returns:

encoded data

Return type:

np.ndarray

get_parameters(groups=None, group_names=None) → ndarray[source]#

Get fitted scaling parameters for a given group.

All parameters are unused - exists for compatibility.

Returns:

zero array.

Return type:

np.ndarray

inverse_transform(y: Tensor | ndarray) → ndarray[source]#

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

set_fit_request(*, overwrite: bool | None | str = '$UNCHANGED$') → NaNLabelEncoder#

Configure whether metadata should be requested to be passed to the fit method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

  • True: metadata is requested, and passed to fit if provided. The request is ignored if metadata is not provided.

  • False: metadata is not requested and the meta-estimator will not pass it to fit.

  • None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

  • str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

overwrite (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for overwrite parameter in fit.

Returns:

self – The updated object.

Return type:

object

set_transform_request(*, ignore_na: bool | None | str = '$UNCHANGED$', return_norm: bool | None | str = '$UNCHANGED$', target_scale: bool | None | str = '$UNCHANGED$') → NaNLabelEncoder#

Configure whether metadata should be requested to be passed to the transform method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

  • True: metadata is requested, and passed to transform if provided. The request is ignored if metadata is not provided.

  • False: metadata is not requested and the meta-estimator will not pass it to transform.

  • None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

  • str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

  • ignore_na (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for ignore_na parameter in transform.

  • return_norm (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for return_norm parameter in transform.

  • target_scale (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for target_scale parameter in transform.

Returns:

self – The updated object.

Return type:

object

transform(y: Iterable, return_norm: bool = False, target_scale=None, ignore_na: bool = False) → Tensor | ndarray[source]#

Encode iterable with integers.

Parameters:

  • y (Iterable) – iterable to encode

  • return_norm – only exists for compatibility with other encoders - returns a tuple if true.

  • target_scale – only exists for compatibility with other encoders - has no effect.

  • ignore_na (bool) – if to ignore na values and map them to zeros (this is different to add_nan=True option which maps ONLY NAs to zeros while this options maps the first class and NAs to zeros)

Returns:

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

Return type:

Union[torch.Tensor, np.ndarray]