Lag transforms - Nixtla

`RollingQuantile`

RollingQuantile(
    p, window_size, min_samples=None, global_=False, groupby=None, **kwargs
)

Bases: _RollingBase Rolling statistic

`RollingMax`

Bases: _RollingBase Rolling statistic

`RollingMin`

Bases: _RollingBase Rolling statistic

`RollingStd`

Bases: _RollingBase Rolling statistic

`RollingMean`

Bases: _RollingBase Rolling statistic

`SeasonalRollingQuantile`

SeasonalRollingQuantile(
    p,
    season_length,
    window_size,
    min_samples=None,
    global_=False,
    groupby=None,
    **kwargs
)

Bases: _Seasonal_RollingBase Rolling statistic over seasonal periods

`SeasonalRollingMax`

Bases: _Seasonal_RollingBase Rolling statistic over seasonal periods

`SeasonalRollingMin`

Bases: _Seasonal_RollingBase Rolling statistic over seasonal periods

`SeasonalRollingStd`

Bases: _Seasonal_RollingBase Rolling statistic over seasonal periods

`SeasonalRollingMean`

Bases: _Seasonal_RollingBase Rolling statistic over seasonal periods

`ExpandingQuantile`

ExpandingQuantile(p, global_=False, groupby=None, **kwargs)

Bases: _ExpandingBase Expanding statistic Parameters:

Name	Type	Description	Default
`global_`	`bool`	If True, compute the statistic across all series aggregated by timestamp. Requires all series to end at the same timestamp. Defaults to False.	required
`groupby`	`Sequence[str]`	Column names to group by before computing the statistic. Columns must be static features. Mutually exclusive with `global_`. Defaults to None.	required

`ExpandingMax`

Bases: _ExpandingBase Expanding statistic Parameters:

Name	Type	Description	Default
`global_`	`bool`	If True, compute the statistic across all series aggregated by timestamp. Requires all series to end at the same timestamp. Defaults to False.	required
`groupby`	`Sequence[str]`	Column names to group by before computing the statistic. Columns must be static features. Mutually exclusive with `global_`. Defaults to None.	required

`ExpandingMin`

Bases: _ExpandingBase Expanding statistic Parameters:

Name	Type	Description	Default
`global_`	`bool`	If True, compute the statistic across all series aggregated by timestamp. Requires all series to end at the same timestamp. Defaults to False.	required
`groupby`	`Sequence[str]`	Column names to group by before computing the statistic. Columns must be static features. Mutually exclusive with `global_`. Defaults to None.	required

`ExpandingStd`

Bases: _ExpandingBase Expanding statistic Parameters:

Name	Type	Description	Default
`global_`	`bool`	If True, compute the statistic across all series aggregated by timestamp. Requires all series to end at the same timestamp. Defaults to False.	required
`groupby`	`Sequence[str]`	Column names to group by before computing the statistic. Columns must be static features. Mutually exclusive with `global_`. Defaults to None.	required

`ExpandingMean`

Bases: _ExpandingBase Expanding statistic Parameters:

Name	Type	Description	Default
`global_`	`bool`	If True, compute the statistic across all series aggregated by timestamp. Requires all series to end at the same timestamp. Defaults to False.	required
`groupby`	`Sequence[str]`	Column names to group by before computing the statistic. Columns must be static features. Mutually exclusive with `global_`. Defaults to None.	required

`ExponentiallyWeightedMean`

ExponentiallyWeightedMean(alpha, global_=False, groupby=None, **kwargs)

Bases: _BaseLagTransform Exponentially weighted average Parameters:

Name	Type	Description	Default
`alpha`	`float`	Smoothing factor.	required
`global_`	`bool`	If True, compute the statistic across all series aggregated by timestamp. Requires all series to end at the same timestamp. Defaults to False.	`False`
`groupby`	`Sequence[str]`	Column names to group by before computing the statistic. Columns must be static features. Mutually exclusive with `global_`. Defaults to None.	`None`

`Offset`

Offset(tfm, n)

Bases: _BaseLagTransform Shift series before computing transformation Parameters:

Name	Type	Description	Default
`tfm`	`LagTransform`	Transformation to be applied	required
`n`	`int`	Number of positions to shift (lag) series before applying the transformation	required

`Combine`

Combine(tfm1, tfm2, operator)

Bases: _BaseLagTransform Combine two lag transformations using an operator Parameters:

Name	Type	Description	Default
`tfm1`	`LagTransform`	First transformation.	required
`tfm2`	`LagTransform`	Second transformation.	required
`operator`	`callable`	Binary operator that defines how to combine the two transformations.	required

Target transforms Feature engineering | MLForecast

⌘I