statistics¶

Classes

`MADTransform`(in_column, window[, ...])	MADTransform computes Mean Absolute Deviation over the window.
`MaxTransform`(in_column, window[, ...])	MaxTransform computes max value for given window.
`MeanTransform`(in_column, window[, ...])	MeanTransform computes average value for given window.
`MedianTransform`(in_column, window[, ...])	MedianTransform computes median value for given window.
`MinMaxDifferenceTransform`(in_column, window)	MinMaxDifferenceTransform computes difference between max and min values for given window.
`MinTransform`(in_column, window[, ...])	MinTransform computes min value for given window.
`QuantileTransform`(in_column, quantile, window)	QuantileTransform computes quantile value for given window.
`StdTransform`(in_column, window[, ...])	StdTransform computes std value for given window.
`SumTransform`(in_column, window[, ...])	SumTransform computes sum of values over given window.
`WindowStatisticsTransform`(in_column, ...[, ...])	WindowStatisticsTransform handles computation of statistical features on windows.

class MADTransform(in_column: str, window: int, seasonality: int = 1, min_periods: int = 1, fillna: float = 0, out_column: Optional[str] = None)[source]¶

MADTransform computes Mean Absolute Deviation over the window.

Init MADTransform.

Parameters

in_column (str) – name of processed column
window (int) – size of window to aggregate
seasonality (int) – seasonality of lags to compute window’s aggregation with
min_periods (int) – min number of targets in window to compute aggregation; if there is less than min_periods number of targets return None
fillna (float) – value to fill results NaNs with
out_column (str, optional) – result column name. If not given use self.__repr__()

fit(ts: etna.datasets.tsdataset.TSDataset) → etna.transforms.math.statistics.WindowStatisticsTransform¶

Fit the transform.

Parameters: ts (etna.datasets.tsdataset.TSDataset) –
Return type: etna.transforms.math.statistics.WindowStatisticsTransform

fit_transform(ts: etna.datasets.tsdataset.TSDataset) → etna.datasets.tsdataset.TSDataset¶

Fit and transform TSDataset.

May be reimplemented. But it is not recommended.

Parameters: ts (etna.datasets.tsdataset.TSDataset) – TSDataset to transform.
Returns: Transformed TSDataset.
Return type: etna.datasets.tsdataset.TSDataset

get_regressors_info() → List[str]¶

Return the list with regressors created by the transform.

Return type: List[str]

inverse_transform(ts: etna.datasets.tsdataset.TSDataset) → etna.datasets.tsdataset.TSDataset¶

Inverse transform TSDataset.

Do nothing.

Parameters: ts (etna.datasets.tsdataset.TSDataset) – TSDataset to be inverse transformed.
Returns: TSDataset after applying inverse transformation.
Return type: etna.datasets.tsdataset.TSDataset

classmethod load(path: pathlib.Path) → typing_extensions.Self¶

Load an object.

Warning

This method uses dill module which is not secure. It is possible to construct malicious data which will execute arbitrary code during loading. Never load data that could have come from an untrusted source, or that could have been tampered with.

Parameters: path (pathlib.Path) – Path to load object from.
Returns: Loaded object.
Return type: typing_extensions.Self

params_to_tune() → Dict[str, etna.distributions.distributions.BaseDistribution]¶

Get default grid for tuning hyperparameters.

This grid tunes only window parameter. Other parameters are expected to be set by the user.

Returns: Grid to tune.
Return type: Dict[str, etna.distributions.distributions.BaseDistribution]

save(path: pathlib.Path)¶

Save the object.

Parameters: path (pathlib.Path) – Path to save object to.

set_params(**params: dict) → etna.core.mixins.TMixin¶

Return new object instance with modified parameters.

Method also allows to change parameters of nested objects within the current object. For example, it is possible to change parameters of a model in a Pipeline.

Nested parameters are expected to be in a <component_1>.<...>.<parameter> form, where components are separated by a dot.

Parameters

**params – Estimator parameters
self (etna.core.mixins.TMixin) –
params (dict) –

Returns

New instance with changed parameters

Return type

etna.core.mixins.TMixin

Examples

>>> from etna.pipeline import Pipeline
>>> from etna.models import NaiveModel
>>> from etna.transforms import AddConstTransform
>>> model = model=NaiveModel(lag=1)
>>> transforms = [AddConstTransform(in_column="target", value=1)]
>>> pipeline = Pipeline(model, transforms=transforms, horizon=3)
>>> pipeline.set_params(**{"model.lag": 3, "transforms.0.value": 2})
Pipeline(model = NaiveModel(lag = 3, ), transforms = [AddConstTransform(in_column = 'target', value = 2, inplace = True, out_column = None, )], horizon = 3, )

to_dict()¶: Collect all information about etna object in dict.

transform(ts: etna.datasets.tsdataset.TSDataset) → etna.datasets.tsdataset.TSDataset¶

Transform TSDataset inplace.

Parameters: ts (etna.datasets.tsdataset.TSDataset) – Dataset to transform.
Returns: Transformed TSDataset.
Return type: etna.datasets.tsdataset.TSDataset

class MaxTransform(in_column: str, window: int, seasonality: int = 1, min_periods: int = 1, fillna: float = 0, out_column: Optional[str] = None)[source]¶

MaxTransform computes max value for given window.

Init MaxTransform.

Parameters

in_column (str) – name of processed column
window (int) – size of window to aggregate
seasonality (int) – seasonality of lags to compute window’s aggregation with
min_periods (int) – min number of targets in window to compute aggregation; if there is less than min_periods number of targets return None
fillna (float) – value to fill results NaNs with
out_column (str, optional) – result column name. If not given use self.__repr__()

fit(ts: etna.datasets.tsdataset.TSDataset) → etna.transforms.math.statistics.WindowStatisticsTransform¶

Fit the transform.

Parameters: ts (etna.datasets.tsdataset.TSDataset) –
Return type: etna.transforms.math.statistics.WindowStatisticsTransform

fit_transform(ts: etna.datasets.tsdataset.TSDataset) → etna.datasets.tsdataset.TSDataset¶

Fit and transform TSDataset.

May be reimplemented. But it is not recommended.

Parameters: ts (etna.datasets.tsdataset.TSDataset) – TSDataset to transform.
Returns: Transformed TSDataset.
Return type: etna.datasets.tsdataset.TSDataset

get_regressors_info() → List[str]¶

Return the list with regressors created by the transform.

Return type: List[str]

inverse_transform(ts: etna.datasets.tsdataset.TSDataset) → etna.datasets.tsdataset.TSDataset¶

Inverse transform TSDataset.

Do nothing.

Parameters: ts (etna.datasets.tsdataset.TSDataset) – TSDataset to be inverse transformed.
Returns: TSDataset after applying inverse transformation.
Return type: etna.datasets.tsdataset.TSDataset

classmethod load(path: pathlib.Path) → typing_extensions.Self¶

Load an object.

Warning

This method uses dill module which is not secure. It is possible to construct malicious data which will execute arbitrary code during loading. Never load data that could have come from an untrusted source, or that could have been tampered with.

Parameters: path (pathlib.Path) – Path to load object from.
Returns: Loaded object.
Return type: typing_extensions.Self

params_to_tune() → Dict[str, etna.distributions.distributions.BaseDistribution]¶

Get default grid for tuning hyperparameters.

This grid tunes only window parameter. Other parameters are expected to be set by the user.

Returns: Grid to tune.
Return type: Dict[str, etna.distributions.distributions.BaseDistribution]

save(path: pathlib.Path)¶

Save the object.

Parameters: path (pathlib.Path) – Path to save object to.

set_params(**params: dict) → etna.core.mixins.TMixin¶

Return new object instance with modified parameters.

Method also allows to change parameters of nested objects within the current object. For example, it is possible to change parameters of a model in a Pipeline.

Nested parameters are expected to be in a <component_1>.<...>.<parameter> form, where components are separated by a dot.

Parameters

**params – Estimator parameters
self (etna.core.mixins.TMixin) –
params (dict) –

Returns

New instance with changed parameters

Return type

etna.core.mixins.TMixin

Examples

>>> from etna.pipeline import Pipeline
>>> from etna.models import NaiveModel
>>> from etna.transforms import AddConstTransform
>>> model = model=NaiveModel(lag=1)
>>> transforms = [AddConstTransform(in_column="target", value=1)]
>>> pipeline = Pipeline(model, transforms=transforms, horizon=3)
>>> pipeline.set_params(**{"model.lag": 3, "transforms.0.value": 2})
Pipeline(model = NaiveModel(lag = 3, ), transforms = [AddConstTransform(in_column = 'target', value = 2, inplace = True, out_column = None, )], horizon = 3, )

to_dict()¶: Collect all information about etna object in dict.

transform(ts: etna.datasets.tsdataset.TSDataset) → etna.datasets.tsdataset.TSDataset¶

Transform TSDataset inplace.

Parameters: ts (etna.datasets.tsdataset.TSDataset) – Dataset to transform.
Returns: Transformed TSDataset.
Return type: etna.datasets.tsdataset.TSDataset

class MeanTransform(in_column: str, window: int, seasonality: int = 1, alpha: float = 1, min_periods: int = 1, fillna: float = 0, out_column: Optional[str] = None)[source]¶

MeanTransform computes average value for given window.

\[MeanTransform(x_t) = \sum_{i=1}^{window}{x_{t - i}\cdot\alpha^{i - 1}}\]

Init MeanTransform.

Parameters

in_column (str) – name of processed column
window (int) – size of window to aggregate
seasonality (int) – seasonality of lags to compute window’s aggregation with
alpha (float) – autoregressive coefficient
min_periods (int) – min number of targets in window to compute aggregation; if there is less than min_periods number of targets return None
fillna (float) – value to fill results NaNs with
out_column (str, optional) – result column name. If not given use self.__repr__()

fit(ts: etna.datasets.tsdataset.TSDataset) → etna.transforms.math.statistics.WindowStatisticsTransform¶

Fit the transform.

Parameters: ts (etna.datasets.tsdataset.TSDataset) –
Return type: etna.transforms.math.statistics.WindowStatisticsTransform

fit_transform(ts: etna.datasets.tsdataset.TSDataset) → etna.datasets.tsdataset.TSDataset¶

Fit and transform TSDataset.

May be reimplemented. But it is not recommended.

Parameters: ts (etna.datasets.tsdataset.TSDataset) – TSDataset to transform.
Returns: Transformed TSDataset.
Return type: etna.datasets.tsdataset.TSDataset

get_regressors_info() → List[str]¶

Return the list with regressors created by the transform.

Return type: List[str]

inverse_transform(ts: etna.datasets.tsdataset.TSDataset) → etna.datasets.tsdataset.TSDataset¶

Inverse transform TSDataset.

Do nothing.

Parameters: ts (etna.datasets.tsdataset.TSDataset) – TSDataset to be inverse transformed.
Returns: TSDataset after applying inverse transformation.
Return type: etna.datasets.tsdataset.TSDataset

classmethod load(path: pathlib.Path) → typing_extensions.Self¶

Load an object.

Warning

This method uses dill module which is not secure. It is possible to construct malicious data which will execute arbitrary code during loading. Never load data that could have come from an untrusted source, or that could have been tampered with.

Parameters: path (pathlib.Path) – Path to load object from.
Returns: Loaded object.
Return type: typing_extensions.Self

params_to_tune() → Dict[str, etna.distributions.distributions.BaseDistribution][source]¶

Get default grid for tuning hyperparameters.

This grid tunes parameters: window, alpha. Other parameters are expected to be set by the user.

Returns: Grid to tune.
Return type: Dict[str, etna.distributions.distributions.BaseDistribution]

save(path: pathlib.Path)¶

Save the object.

Parameters: path (pathlib.Path) – Path to save object to.

set_params(**params: dict) → etna.core.mixins.TMixin¶

Return new object instance with modified parameters.

Method also allows to change parameters of nested objects within the current object. For example, it is possible to change parameters of a model in a Pipeline.

Nested parameters are expected to be in a <component_1>.<...>.<parameter> form, where components are separated by a dot.

Parameters

**params – Estimator parameters
self (etna.core.mixins.TMixin) –
params (dict) –

Returns

New instance with changed parameters

Return type

etna.core.mixins.TMixin

Examples

>>> from etna.pipeline import Pipeline
>>> from etna.models import NaiveModel
>>> from etna.transforms import AddConstTransform
>>> model = model=NaiveModel(lag=1)
>>> transforms = [AddConstTransform(in_column="target", value=1)]
>>> pipeline = Pipeline(model, transforms=transforms, horizon=3)
>>> pipeline.set_params(**{"model.lag": 3, "transforms.0.value": 2})
Pipeline(model = NaiveModel(lag = 3, ), transforms = [AddConstTransform(in_column = 'target', value = 2, inplace = True, out_column = None, )], horizon = 3, )

to_dict()¶: Collect all information about etna object in dict.

transform(ts: etna.datasets.tsdataset.TSDataset) → etna.datasets.tsdataset.TSDataset¶

Transform TSDataset inplace.

Parameters: ts (etna.datasets.tsdataset.TSDataset) – Dataset to transform.
Returns: Transformed TSDataset.
Return type: etna.datasets.tsdataset.TSDataset

class MedianTransform(in_column: str, window: int, seasonality: int = 1, min_periods: int = 1, fillna: float = 0, out_column: Optional[str] = None)[source]¶

MedianTransform computes median value for given window.

Init MedianTransform.

Parameters

in_column (str) – name of processed column
window (int) – size of window to aggregate
seasonality (int) – seasonality of lags to compute window’s aggregation with
min_periods (int) – min number of targets in window to compute aggregation; if there is less than min_periods number of targets return None
fillna (float) – value to fill results NaNs with
out_column (str, optional) – result column name. If not given use self.__repr__()

fit(ts: etna.datasets.tsdataset.TSDataset) → etna.transforms.math.statistics.WindowStatisticsTransform¶

Fit the transform.

Parameters: ts (etna.datasets.tsdataset.TSDataset) –
Return type: etna.transforms.math.statistics.WindowStatisticsTransform

fit_transform(ts: etna.datasets.tsdataset.TSDataset) → etna.datasets.tsdataset.TSDataset¶

Fit and transform TSDataset.

May be reimplemented. But it is not recommended.

Parameters: ts (etna.datasets.tsdataset.TSDataset) – TSDataset to transform.
Returns: Transformed TSDataset.
Return type: etna.datasets.tsdataset.TSDataset

get_regressors_info() → List[str]¶

Return the list with regressors created by the transform.

Return type: List[str]

inverse_transform(ts: etna.datasets.tsdataset.TSDataset) → etna.datasets.tsdataset.TSDataset¶

Inverse transform TSDataset.

Do nothing.

Parameters: ts (etna.datasets.tsdataset.TSDataset) – TSDataset to be inverse transformed.
Returns: TSDataset after applying inverse transformation.
Return type: etna.datasets.tsdataset.TSDataset

classmethod load(path: pathlib.Path) → typing_extensions.Self¶

Load an object.

Warning

This method uses dill module which is not secure. It is possible to construct malicious data which will execute arbitrary code during loading. Never load data that could have come from an untrusted source, or that could have been tampered with.

Parameters: path (pathlib.Path) – Path to load object from.
Returns: Loaded object.
Return type: typing_extensions.Self

params_to_tune() → Dict[str, etna.distributions.distributions.BaseDistribution]¶

Get default grid for tuning hyperparameters.

This grid tunes only window parameter. Other parameters are expected to be set by the user.

Returns: Grid to tune.
Return type: Dict[str, etna.distributions.distributions.BaseDistribution]

save(path: pathlib.Path)¶

Save the object.

Parameters: path (pathlib.Path) – Path to save object to.

set_params(**params: dict) → etna.core.mixins.TMixin¶

Return new object instance with modified parameters.

Method also allows to change parameters of nested objects within the current object. For example, it is possible to change parameters of a model in a Pipeline.

Nested parameters are expected to be in a <component_1>.<...>.<parameter> form, where components are separated by a dot.

Parameters

**params – Estimator parameters
self (etna.core.mixins.TMixin) –
params (dict) –

Returns

New instance with changed parameters

Return type

etna.core.mixins.TMixin

Examples

>>> from etna.pipeline import Pipeline
>>> from etna.models import NaiveModel
>>> from etna.transforms import AddConstTransform
>>> model = model=NaiveModel(lag=1)
>>> transforms = [AddConstTransform(in_column="target", value=1)]
>>> pipeline = Pipeline(model, transforms=transforms, horizon=3)
>>> pipeline.set_params(**{"model.lag": 3, "transforms.0.value": 2})
Pipeline(model = NaiveModel(lag = 3, ), transforms = [AddConstTransform(in_column = 'target', value = 2, inplace = True, out_column = None, )], horizon = 3, )

to_dict()¶: Collect all information about etna object in dict.

transform(ts: etna.datasets.tsdataset.TSDataset) → etna.datasets.tsdataset.TSDataset¶

Transform TSDataset inplace.

Parameters: ts (etna.datasets.tsdataset.TSDataset) – Dataset to transform.
Returns: Transformed TSDataset.
Return type: etna.datasets.tsdataset.TSDataset

class MinMaxDifferenceTransform(in_column: str, window: int, seasonality: int = 1, min_periods: int = 1, fillna: float = 0, out_column: Optional[str] = None)[source]¶

MinMaxDifferenceTransform computes difference between max and min values for given window.

Init MaxTransform.

Parameters

in_column (str) – name of processed column
window (int) – size of window to aggregate
seasonality (int) – seasonality of lags to compute window’s aggregation with
min_periods (int) – min number of targets in window to compute aggregation; if there is less than min_periods number of targets return None
fillna (float) – value to fill results NaNs with
out_column (str, optional) – result column name. If not given use self.__repr__()

fit(ts: etna.datasets.tsdataset.TSDataset) → etna.transforms.math.statistics.WindowStatisticsTransform¶

Fit the transform.

Parameters: ts (etna.datasets.tsdataset.TSDataset) –
Return type: etna.transforms.math.statistics.WindowStatisticsTransform

fit_transform(ts: etna.datasets.tsdataset.TSDataset) → etna.datasets.tsdataset.TSDataset¶

Fit and transform TSDataset.

May be reimplemented. But it is not recommended.

Parameters: ts (etna.datasets.tsdataset.TSDataset) – TSDataset to transform.
Returns: Transformed TSDataset.
Return type: etna.datasets.tsdataset.TSDataset

get_regressors_info() → List[str]¶

Return the list with regressors created by the transform.

Return type: List[str]

inverse_transform(ts: etna.datasets.tsdataset.TSDataset) → etna.datasets.tsdataset.TSDataset¶

Inverse transform TSDataset.

Do nothing.

Parameters: ts (etna.datasets.tsdataset.TSDataset) – TSDataset to be inverse transformed.
Returns: TSDataset after applying inverse transformation.
Return type: etna.datasets.tsdataset.TSDataset

classmethod load(path: pathlib.Path) → typing_extensions.Self¶

Load an object.

Warning

This method uses dill module which is not secure. It is possible to construct malicious data which will execute arbitrary code during loading. Never load data that could have come from an untrusted source, or that could have been tampered with.

Parameters: path (pathlib.Path) – Path to load object from.
Returns: Loaded object.
Return type: typing_extensions.Self

params_to_tune() → Dict[str, etna.distributions.distributions.BaseDistribution]¶

Get default grid for tuning hyperparameters.

This grid tunes only window parameter. Other parameters are expected to be set by the user.

Returns: Grid to tune.
Return type: Dict[str, etna.distributions.distributions.BaseDistribution]

save(path: pathlib.Path)¶

Save the object.

Parameters: path (pathlib.Path) – Path to save object to.

set_params(**params: dict) → etna.core.mixins.TMixin¶

Return new object instance with modified parameters.

Method also allows to change parameters of nested objects within the current object. For example, it is possible to change parameters of a model in a Pipeline.

Nested parameters are expected to be in a <component_1>.<...>.<parameter> form, where components are separated by a dot.

Parameters

**params – Estimator parameters
self (etna.core.mixins.TMixin) –
params (dict) –

Returns

New instance with changed parameters

Return type

etna.core.mixins.TMixin

Examples

>>> from etna.pipeline import Pipeline
>>> from etna.models import NaiveModel
>>> from etna.transforms import AddConstTransform
>>> model = model=NaiveModel(lag=1)
>>> transforms = [AddConstTransform(in_column="target", value=1)]
>>> pipeline = Pipeline(model, transforms=transforms, horizon=3)
>>> pipeline.set_params(**{"model.lag": 3, "transforms.0.value": 2})
Pipeline(model = NaiveModel(lag = 3, ), transforms = [AddConstTransform(in_column = 'target', value = 2, inplace = True, out_column = None, )], horizon = 3, )

to_dict()¶: Collect all information about etna object in dict.

transform(ts: etna.datasets.tsdataset.TSDataset) → etna.datasets.tsdataset.TSDataset¶

Transform TSDataset inplace.

Parameters: ts (etna.datasets.tsdataset.TSDataset) – Dataset to transform.
Returns: Transformed TSDataset.
Return type: etna.datasets.tsdataset.TSDataset

class MinTransform(in_column: str, window: int, seasonality: int = 1, min_periods: int = 1, fillna: float = 0, out_column: Optional[str] = None)[source]¶

MinTransform computes min value for given window.

Init MinTransform.

Parameters

in_column (str) – name of processed column
window (int) – size of window to aggregate
seasonality (int) – seasonality of lags to compute window’s aggregation with
min_periods (int) – min number of targets in window to compute aggregation; if there is less than min_periods number of targets return None
fillna (float) – value to fill results NaNs with
out_column (str, optional) – result column name. If not given use self.__repr__()

fit(ts: etna.datasets.tsdataset.TSDataset) → etna.transforms.math.statistics.WindowStatisticsTransform¶

Fit the transform.

Parameters: ts (etna.datasets.tsdataset.TSDataset) –
Return type: etna.transforms.math.statistics.WindowStatisticsTransform

fit_transform(ts: etna.datasets.tsdataset.TSDataset) → etna.datasets.tsdataset.TSDataset¶

Fit and transform TSDataset.

May be reimplemented. But it is not recommended.

Parameters: ts (etna.datasets.tsdataset.TSDataset) – TSDataset to transform.
Returns: Transformed TSDataset.
Return type: etna.datasets.tsdataset.TSDataset

get_regressors_info() → List[str]¶

Return the list with regressors created by the transform.

Return type: List[str]

inverse_transform(ts: etna.datasets.tsdataset.TSDataset) → etna.datasets.tsdataset.TSDataset¶

Inverse transform TSDataset.

Do nothing.

Parameters: ts (etna.datasets.tsdataset.TSDataset) – TSDataset to be inverse transformed.
Returns: TSDataset after applying inverse transformation.
Return type: etna.datasets.tsdataset.TSDataset

classmethod load(path: pathlib.Path) → typing_extensions.Self¶

Load an object.

Warning

This method uses dill module which is not secure. It is possible to construct malicious data which will execute arbitrary code during loading. Never load data that could have come from an untrusted source, or that could have been tampered with.

Parameters: path (pathlib.Path) – Path to load object from.
Returns: Loaded object.
Return type: typing_extensions.Self

params_to_tune() → Dict[str, etna.distributions.distributions.BaseDistribution]¶

Get default grid for tuning hyperparameters.

This grid tunes only window parameter. Other parameters are expected to be set by the user.

Returns: Grid to tune.
Return type: Dict[str, etna.distributions.distributions.BaseDistribution]

save(path: pathlib.Path)¶

Save the object.

Parameters: path (pathlib.Path) – Path to save object to.

set_params(**params: dict) → etna.core.mixins.TMixin¶

Return new object instance with modified parameters.

Method also allows to change parameters of nested objects within the current object. For example, it is possible to change parameters of a model in a Pipeline.

Nested parameters are expected to be in a <component_1>.<...>.<parameter> form, where components are separated by a dot.

Parameters

**params – Estimator parameters
self (etna.core.mixins.TMixin) –
params (dict) –

Returns

New instance with changed parameters

Return type

etna.core.mixins.TMixin

Examples

>>> from etna.pipeline import Pipeline
>>> from etna.models import NaiveModel
>>> from etna.transforms import AddConstTransform
>>> model = model=NaiveModel(lag=1)
>>> transforms = [AddConstTransform(in_column="target", value=1)]
>>> pipeline = Pipeline(model, transforms=transforms, horizon=3)
>>> pipeline.set_params(**{"model.lag": 3, "transforms.0.value": 2})
Pipeline(model = NaiveModel(lag = 3, ), transforms = [AddConstTransform(in_column = 'target', value = 2, inplace = True, out_column = None, )], horizon = 3, )

to_dict()¶: Collect all information about etna object in dict.

transform(ts: etna.datasets.tsdataset.TSDataset) → etna.datasets.tsdataset.TSDataset¶

Transform TSDataset inplace.

Parameters: ts (etna.datasets.tsdataset.TSDataset) – Dataset to transform.
Returns: Transformed TSDataset.
Return type: etna.datasets.tsdataset.TSDataset

class QuantileTransform(in_column: str, quantile: float, window: int, seasonality: int = 1, min_periods: int = 1, fillna: float = 0, out_column: Optional[str] = None)[source]¶

QuantileTransform computes quantile value for given window.

Init QuantileTransform.

Parameters

in_column (str) – name of processed column
quantile (float) – quantile to calculate
window (int) – size of window to aggregate
seasonality (int) – seasonality of lags to compute window’s aggregation with
min_periods (int) – min number of targets in window to compute aggregation; if there is less than min_periods number of targets return None
fillna (float) – value to fill results NaNs with
out_column (str, optional) – result column name. If not given use self.__repr__()

fit(ts: etna.datasets.tsdataset.TSDataset) → etna.transforms.math.statistics.WindowStatisticsTransform¶

Fit the transform.

Parameters: ts (etna.datasets.tsdataset.TSDataset) –
Return type: etna.transforms.math.statistics.WindowStatisticsTransform

fit_transform(ts: etna.datasets.tsdataset.TSDataset) → etna.datasets.tsdataset.TSDataset¶

Fit and transform TSDataset.

May be reimplemented. But it is not recommended.

Parameters: ts (etna.datasets.tsdataset.TSDataset) – TSDataset to transform.
Returns: Transformed TSDataset.
Return type: etna.datasets.tsdataset.TSDataset

get_regressors_info() → List[str]¶

Return the list with regressors created by the transform.

Return type: List[str]

inverse_transform(ts: etna.datasets.tsdataset.TSDataset) → etna.datasets.tsdataset.TSDataset¶

Inverse transform TSDataset.

Do nothing.

Parameters: ts (etna.datasets.tsdataset.TSDataset) – TSDataset to be inverse transformed.
Returns: TSDataset after applying inverse transformation.
Return type: etna.datasets.tsdataset.TSDataset

classmethod load(path: pathlib.Path) → typing_extensions.Self¶

Load an object.

Warning

This method uses dill module which is not secure. It is possible to construct malicious data which will execute arbitrary code during loading. Never load data that could have come from an untrusted source, or that could have been tampered with.

Parameters: path (pathlib.Path) – Path to load object from.
Returns: Loaded object.
Return type: typing_extensions.Self

params_to_tune() → Dict[str, etna.distributions.distributions.BaseDistribution][source]¶

Get default grid for tuning hyperparameters.

This grid tunes parameters: window, quantile. Other parameters are expected to be set by the user.

Returns: Grid to tune.
Return type: Dict[str, etna.distributions.distributions.BaseDistribution]

save(path: pathlib.Path)¶

Save the object.

Parameters: path (pathlib.Path) – Path to save object to.

set_params(**params: dict) → etna.core.mixins.TMixin¶

Return new object instance with modified parameters.

Method also allows to change parameters of nested objects within the current object. For example, it is possible to change parameters of a model in a Pipeline.

Nested parameters are expected to be in a <component_1>.<...>.<parameter> form, where components are separated by a dot.

Parameters

**params – Estimator parameters
self (etna.core.mixins.TMixin) –
params (dict) –

Returns

New instance with changed parameters

Return type

etna.core.mixins.TMixin

Examples

>>> from etna.pipeline import Pipeline
>>> from etna.models import NaiveModel
>>> from etna.transforms import AddConstTransform
>>> model = model=NaiveModel(lag=1)
>>> transforms = [AddConstTransform(in_column="target", value=1)]
>>> pipeline = Pipeline(model, transforms=transforms, horizon=3)
>>> pipeline.set_params(**{"model.lag": 3, "transforms.0.value": 2})
Pipeline(model = NaiveModel(lag = 3, ), transforms = [AddConstTransform(in_column = 'target', value = 2, inplace = True, out_column = None, )], horizon = 3, )

to_dict()¶: Collect all information about etna object in dict.

transform(ts: etna.datasets.tsdataset.TSDataset) → etna.datasets.tsdataset.TSDataset¶

Transform TSDataset inplace.

Parameters: ts (etna.datasets.tsdataset.TSDataset) – Dataset to transform.
Returns: Transformed TSDataset.
Return type: etna.datasets.tsdataset.TSDataset

class StdTransform(in_column: str, window: int, seasonality: int = 1, min_periods: int = 1, fillna: float = 0, out_column: Optional[str] = None, ddof: int = 1)[source]¶

StdTransform computes std value for given window.

Notes

Note that pd.Series([1]).std() is np.nan.

Init StdTransform.

Parameters

in_column (str) – name of processed column
window (int) – size of window to aggregate
seasonality (int) – seasonality of lags to compute window’s aggregation with
min_periods (int) – min number of targets in window to compute aggregation; if there is less than min_periods number of targets return None
fillna (float) – value to fill results NaNs with
out_column (str, optional) – result column name. If not given use self.__repr__()
ddof (int) – delta degrees of freedom; the divisor used in calculations is N - ddof, where N is the number of elements

fit(ts: etna.datasets.tsdataset.TSDataset) → etna.transforms.math.statistics.WindowStatisticsTransform¶

Fit the transform.

Parameters: ts (etna.datasets.tsdataset.TSDataset) –
Return type: etna.transforms.math.statistics.WindowStatisticsTransform

fit_transform(ts: etna.datasets.tsdataset.TSDataset) → etna.datasets.tsdataset.TSDataset¶

Fit and transform TSDataset.

May be reimplemented. But it is not recommended.

Parameters: ts (etna.datasets.tsdataset.TSDataset) – TSDataset to transform.
Returns: Transformed TSDataset.
Return type: etna.datasets.tsdataset.TSDataset

get_regressors_info() → List[str]¶

Return the list with regressors created by the transform.

Return type: List[str]

inverse_transform(ts: etna.datasets.tsdataset.TSDataset) → etna.datasets.tsdataset.TSDataset¶

Inverse transform TSDataset.

Do nothing.

Parameters: ts (etna.datasets.tsdataset.TSDataset) – TSDataset to be inverse transformed.
Returns: TSDataset after applying inverse transformation.
Return type: etna.datasets.tsdataset.TSDataset

classmethod load(path: pathlib.Path) → typing_extensions.Self¶

Load an object.

Warning

This method uses dill module which is not secure. It is possible to construct malicious data which will execute arbitrary code during loading. Never load data that could have come from an untrusted source, or that could have been tampered with.

Parameters: path (pathlib.Path) – Path to load object from.
Returns: Loaded object.
Return type: typing_extensions.Self

params_to_tune() → Dict[str, etna.distributions.distributions.BaseDistribution]¶

Get default grid for tuning hyperparameters.

This grid tunes only window parameter. Other parameters are expected to be set by the user.

Returns: Grid to tune.
Return type: Dict[str, etna.distributions.distributions.BaseDistribution]

save(path: pathlib.Path)¶

Save the object.

Parameters: path (pathlib.Path) – Path to save object to.

set_params(**params: dict) → etna.core.mixins.TMixin¶

Return new object instance with modified parameters.

Method also allows to change parameters of nested objects within the current object. For example, it is possible to change parameters of a model in a Pipeline.

Nested parameters are expected to be in a <component_1>.<...>.<parameter> form, where components are separated by a dot.

Parameters

**params – Estimator parameters
self (etna.core.mixins.TMixin) –
params (dict) –

Returns

New instance with changed parameters

Return type

etna.core.mixins.TMixin

Examples

>>> from etna.pipeline import Pipeline
>>> from etna.models import NaiveModel
>>> from etna.transforms import AddConstTransform
>>> model = model=NaiveModel(lag=1)
>>> transforms = [AddConstTransform(in_column="target", value=1)]
>>> pipeline = Pipeline(model, transforms=transforms, horizon=3)
>>> pipeline.set_params(**{"model.lag": 3, "transforms.0.value": 2})
Pipeline(model = NaiveModel(lag = 3, ), transforms = [AddConstTransform(in_column = 'target', value = 2, inplace = True, out_column = None, )], horizon = 3, )

to_dict()¶: Collect all information about etna object in dict.

transform(ts: etna.datasets.tsdataset.TSDataset) → etna.datasets.tsdataset.TSDataset¶

Transform TSDataset inplace.

Parameters: ts (etna.datasets.tsdataset.TSDataset) – Dataset to transform.
Returns: Transformed TSDataset.
Return type: etna.datasets.tsdataset.TSDataset

class SumTransform(in_column: str, window: int, seasonality: int = 1, min_periods: int = 1, fillna: float = 0, out_column: Optional[str] = None)[source]¶

SumTransform computes sum of values over given window.

Init SumTransform.

Parameters

in_column (str) – name of processed column
window (int) – size of window to aggregate, if window == -1 compute rolling sum all over the given series
seasonality (int) – seasonality of lags to compute window’s aggregation with
min_periods (int) – min number of targets in window to compute aggregation; if there is less than min_periods number of targets return None
fillna (float) – value to fill results NaNs with
out_column (Optional[str]) – result column name. If not given use self.__repr__()

fit(ts: etna.datasets.tsdataset.TSDataset) → etna.transforms.math.statistics.WindowStatisticsTransform¶

Fit the transform.

Parameters: ts (etna.datasets.tsdataset.TSDataset) –
Return type: etna.transforms.math.statistics.WindowStatisticsTransform

fit_transform(ts: etna.datasets.tsdataset.TSDataset) → etna.datasets.tsdataset.TSDataset¶

Fit and transform TSDataset.

May be reimplemented. But it is not recommended.

Parameters: ts (etna.datasets.tsdataset.TSDataset) – TSDataset to transform.
Returns: Transformed TSDataset.
Return type: etna.datasets.tsdataset.TSDataset

get_regressors_info() → List[str]¶

Return the list with regressors created by the transform.

Return type: List[str]

inverse_transform(ts: etna.datasets.tsdataset.TSDataset) → etna.datasets.tsdataset.TSDataset¶

Inverse transform TSDataset.

Do nothing.

Parameters: ts (etna.datasets.tsdataset.TSDataset) – TSDataset to be inverse transformed.
Returns: TSDataset after applying inverse transformation.
Return type: etna.datasets.tsdataset.TSDataset

classmethod load(path: pathlib.Path) → typing_extensions.Self¶

Load an object.

Warning

This method uses dill module which is not secure. It is possible to construct malicious data which will execute arbitrary code during loading. Never load data that could have come from an untrusted source, or that could have been tampered with.

Parameters: path (pathlib.Path) – Path to load object from.
Returns: Loaded object.
Return type: typing_extensions.Self

params_to_tune() → Dict[str, etna.distributions.distributions.BaseDistribution]¶

Get default grid for tuning hyperparameters.

This grid tunes only window parameter. Other parameters are expected to be set by the user.

Returns: Grid to tune.
Return type: Dict[str, etna.distributions.distributions.BaseDistribution]

save(path: pathlib.Path)¶

Save the object.

Parameters: path (pathlib.Path) – Path to save object to.

set_params(**params: dict) → etna.core.mixins.TMixin¶

Return new object instance with modified parameters.

Method also allows to change parameters of nested objects within the current object. For example, it is possible to change parameters of a model in a Pipeline.

Nested parameters are expected to be in a <component_1>.<...>.<parameter> form, where components are separated by a dot.

Parameters

**params – Estimator parameters
self (etna.core.mixins.TMixin) –
params (dict) –

Returns

New instance with changed parameters

Return type

etna.core.mixins.TMixin

Examples

>>> from etna.pipeline import Pipeline
>>> from etna.models import NaiveModel
>>> from etna.transforms import AddConstTransform
>>> model = model=NaiveModel(lag=1)
>>> transforms = [AddConstTransform(in_column="target", value=1)]
>>> pipeline = Pipeline(model, transforms=transforms, horizon=3)
>>> pipeline.set_params(**{"model.lag": 3, "transforms.0.value": 2})
Pipeline(model = NaiveModel(lag = 3, ), transforms = [AddConstTransform(in_column = 'target', value = 2, inplace = True, out_column = None, )], horizon = 3, )

to_dict()¶: Collect all information about etna object in dict.

transform(ts: etna.datasets.tsdataset.TSDataset) → etna.datasets.tsdataset.TSDataset¶

Transform TSDataset inplace.

Parameters: ts (etna.datasets.tsdataset.TSDataset) – Dataset to transform.
Returns: Transformed TSDataset.
Return type: etna.datasets.tsdataset.TSDataset

class WindowStatisticsTransform(in_column: str, out_column: str, window: int, seasonality: int = 1, min_periods: int = 1, fillna: float = 0, **kwargs)[source]¶

WindowStatisticsTransform handles computation of statistical features on windows.

Init WindowStatisticsTransform.

Parameters

in_column (str) – name of processed column
out_column (str) – result column name
window (int) – size of window to aggregate, if -1 is set all history is used
seasonality (int) – seasonality of lags to compute window’s aggregation with
min_periods (int) – min number of targets in window to compute aggregation; if there is less than min_periods number of targets return None
fillna (float) – value to fill results NaNs with

fit(ts: etna.datasets.tsdataset.TSDataset) → etna.transforms.math.statistics.WindowStatisticsTransform[source]¶

Fit the transform.

Parameters: ts (etna.datasets.tsdataset.TSDataset) –
Return type: etna.transforms.math.statistics.WindowStatisticsTransform

fit_transform(ts: etna.datasets.tsdataset.TSDataset) → etna.datasets.tsdataset.TSDataset¶

Fit and transform TSDataset.

May be reimplemented. But it is not recommended.

Parameters: ts (etna.datasets.tsdataset.TSDataset) – TSDataset to transform.
Returns: Transformed TSDataset.
Return type: etna.datasets.tsdataset.TSDataset

get_regressors_info() → List[str][source]¶

Return the list with regressors created by the transform.

Return type: List[str]

inverse_transform(ts: etna.datasets.tsdataset.TSDataset) → etna.datasets.tsdataset.TSDataset¶

Inverse transform TSDataset.

Do nothing.

Parameters: ts (etna.datasets.tsdataset.TSDataset) – TSDataset to be inverse transformed.
Returns: TSDataset after applying inverse transformation.
Return type: etna.datasets.tsdataset.TSDataset

classmethod load(path: pathlib.Path) → typing_extensions.Self¶

Load an object.

Warning

This method uses dill module which is not secure. It is possible to construct malicious data which will execute arbitrary code during loading. Never load data that could have come from an untrusted source, or that could have been tampered with.

Parameters: path (pathlib.Path) – Path to load object from.
Returns: Loaded object.
Return type: typing_extensions.Self

params_to_tune() → Dict[str, etna.distributions.distributions.BaseDistribution][source]¶

Get default grid for tuning hyperparameters.

This grid tunes only window parameter. Other parameters are expected to be set by the user.

Returns: Grid to tune.
Return type: Dict[str, etna.distributions.distributions.BaseDistribution]

save(path: pathlib.Path)¶

Save the object.

Parameters: path (pathlib.Path) – Path to save object to.

set_params(**params: dict) → etna.core.mixins.TMixin¶

Return new object instance with modified parameters.

Method also allows to change parameters of nested objects within the current object. For example, it is possible to change parameters of a model in a Pipeline.

Nested parameters are expected to be in a <component_1>.<...>.<parameter> form, where components are separated by a dot.

Parameters

**params – Estimator parameters
self (etna.core.mixins.TMixin) –
params (dict) –

Returns

New instance with changed parameters

Return type

etna.core.mixins.TMixin

Examples

>>> from etna.pipeline import Pipeline
>>> from etna.models import NaiveModel
>>> from etna.transforms import AddConstTransform
>>> model = model=NaiveModel(lag=1)
>>> transforms = [AddConstTransform(in_column="target", value=1)]
>>> pipeline = Pipeline(model, transforms=transforms, horizon=3)
>>> pipeline.set_params(**{"model.lag": 3, "transforms.0.value": 2})
Pipeline(model = NaiveModel(lag = 3, ), transforms = [AddConstTransform(in_column = 'target', value = 2, inplace = True, out_column = None, )], horizon = 3, )

to_dict()¶: Collect all information about etna object in dict.

transform(ts: etna.datasets.tsdataset.TSDataset) → etna.datasets.tsdataset.TSDataset¶

Transform TSDataset inplace.

Parameters: ts (etna.datasets.tsdataset.TSDataset) – Dataset to transform.
Returns: Transformed TSDataset.
Return type: etna.datasets.tsdataset.TSDataset