OutliersTransform

class OutliersTransform(in_column: str)

Bases: etna.transforms.base.Transform, abc.ABC

Finds outliers in specific columns of DataFrame and replaces it with NaNs.

Create instance of OutliersTransform.

Parameters

in_column (str) – name of processed column

Inherited-members

Methods

detect_outliers(ts)	Call function for detection outliers with self parameters.
fit(df)	Find outliers using detection method.
fit_transform(df)	May be reimplemented.
inverse_transform(df)	Inverse transformation.
transform(df)	Replace found outliers with NaNs.

abstract detect_outliers(ts: etna.datasets.tsdataset.TSDataset) → Dict[str, List[pandas._libs.tslibs.timestamps.Timestamp]]

Call function for detection outliers with self parameters.

Parameters

ts (etna.datasets.tsdataset.TSDataset) – dataset to process

Returns

dict of outliers in format {segment: [outliers_timestamps]}

Return type

Dict[str, List[pandas._libs.tslibs.timestamps.Timestamp]]

fit(df: pandas.core.frame.DataFrame) → etna.transforms.outliers.base.OutliersTransform

Find outliers using detection method.

Parameters

df (pandas.core.frame.DataFrame) – dataframe with series to find outliers

Returns

result – instance with saved outliers

Return type

OutliersTransform

inverse_transform(df: pandas.core.frame.DataFrame) → pandas.core.frame.DataFrame

Inverse transformation. Returns back deleted values.

Parameters

df (pandas.core.frame.DataFrame) – data to transform

Returns

result – data with reconstructed values

Return type

pd.DataFrame

transform(df: pandas.core.frame.DataFrame) → pandas.core.frame.DataFrame

Replace found outliers with NaNs.

Parameters

df (pandas.core.frame.DataFrame) – transform in_column series of given dataframe

Returns

result – dataframe with in_column series with filled with NaNs

Return type

pd.DataFrame