Transforms

Details and available algorithms

See the API documentation for further details on available feature extractions and transformations:

etna.transforms.math.add_constant.AddConstTransform(...)

AddConstTransform add constant for given series.

etna.transforms.decomposition.change_points_based.base.BaseChangePointsTransform()

Base class for all the change points based transforms.

etna.transforms.math.power.BoxCoxTransform([...])

BoxCoxTransform applies Box-Cox transformation to DataFrame.

etna.transforms.decomposition.change_points_based.level.ChangePointsLevelTransform(...)

Transform that makes a detrending of change-point intervals.

etna.transforms.decomposition.change_points_based.segmentation.ChangePointsSegmentationTransform(...)

Transform that makes label encoding of change-point intervals.

etna.transforms.decomposition.change_points_based.detrend.ChangePointsTrendTransform(...)

Transform that makes a detrending of change-point intervals.

etna.transforms.timestamp.date_flags.DateFlagsTransform([...])

DateFlagsTransform is a class that implements extraction of the main date-based features from datetime column.

etna.transforms.outliers.point_outliers.DensityOutliersTransform(...)

Transform that uses get_anomalies_density() to find anomalies in data.

etna.transforms.decomposition.deseasonal.DeseasonalityTransform(...)

Transform that uses statsmodels.tsa.seasonal.seasonal_decompose() to subtract seasonal component from the data.

etna.transforms.math.differencing.DifferencingTransform(...)

Calculate a time series differences.

etna.transforms.math.lags.ExogShiftTransform(lag)

Shifts exogenous variables from a given dataframe.

etna.transforms.feature_selection.filter.FilterFeaturesTransform([...])

Filters features in each segment of the dataframe.

etna.transforms.timestamp.fourier.FourierTransform(period)

Adds fourier features to the dataset.

etna.transforms.feature_selection.gale_shapley.GaleShapleyFeatureSelectionTransform(...)

Transform that provides feature filtering by Gale-Shapley matching algorithm according to the relevance table.

etna.transforms.timestamp.holiday.HolidayTransform([...])

HolidayTransform generates series that indicates holidays in given dataframe.

etna.transforms.decomposition.change_points_based.base.IrreversibleChangePointsTransform(...)

IrreversibleChangePointsTransform class is a base class for all irreversible transforms that work with change point.

etna.transforms.base.IrreversiblePerSegmentWrapper(...)

Class to apply irreversible transform in per segment manner.

etna.transforms.base.IrreversibleTransform(...)

Base class to create irreversible transforms.

etna.transforms.encoders.categorical.LabelEncoderTransform(...)

Encode categorical feature with value between 0 and n_classes-1.

etna.transforms.math.lags.LagTransform(...)

Generates series of lags from given dataframe.

etna.transforms.math.apply_lambda.LambdaTransform(...)

LambdaTransform applies input function for given series.

etna.transforms.decomposition.detrend.LinearTrendTransform(...)

Transform that uses linear regression with polynomial features to make a detrending.

etna.transforms.math.log.LogTransform(in_column)

LogTransform applies logarithm transformation for given series.

etna.transforms.math.statistics.MADTransform(...)

MADTransform computes Mean Absolute Deviation over the window.

etna.transforms.feature_selection.feature_importance.MRMRFeatureSelectionTransform(...)

Transform that selects features according to MRMR variable selection method adapted to the timeseries case.

etna.transforms.math.scalers.MaxAbsScalerTransform([...])

Scale each feature by its maximum absolute value.

etna.transforms.math.statistics.MaxTransform(...)

MaxTransform computes max value for given window.

etna.transforms.encoders.mean_segment_encoder.MeanSegmentEncoderTransform()

Makes expanding mean target encoding of the segment.

etna.transforms.math.statistics.MeanTransform(...)

MeanTransform computes average value for given window.

etna.transforms.outliers.point_outliers.MedianOutliersTransform(...)

Transform that uses get_anomalies_median() to find anomalies in data.

etna.transforms.math.statistics.MedianTransform(...)

MedianTransform computes median value for given window.

etna.transforms.math.statistics.MinMaxDifferenceTransform(...)

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

etna.transforms.math.scalers.MinMaxScalerTransform([...])

Transform features by scaling each feature to a given range.

etna.transforms.math.statistics.MinTransform(...)

MinTransform computes min value for given window.

etna.transforms.encoders.categorical.OneHotEncoderTransform(...)

Encode categorical feature as a one-hot numeric features.

etna.transforms.base.OneSegmentTransform()

Base class to create one segment transforms to apply to data.

etna.transforms.base.PerSegmentWrapper(...)

Class to apply transform in per segment manner.

etna.transforms.outliers.point_outliers.PredictionIntervalOutliersTransform(...)

Transform that uses get_anomalies_prediction_interval() to find anomalies in data.

etna.transforms.math.statistics.QuantileTransform(...)

QuantileTransform computes quantile value for given window.

etna.transforms.missing_values.resample.ResampleWithDistributionTransform(...)

ResampleWithDistributionTransform resamples the given column using the distribution of the other column.

etna.transforms.decomposition.change_points_based.base.ReversibleChangePointsTransform(...)

ReversibleChangePointsTransform class is a base class for all reversible transforms that work with change point.

etna.transforms.base.ReversiblePerSegmentWrapper(...)

Class to apply reversible transform in per segment manner.

etna.transforms.base.ReversibleTransform(...)

Base class to create reversible transforms.

etna.transforms.math.scalers.RobustScalerTransform([...])

Scale features using statistics that are robust to outliers.

etna.transforms.decomposition.stl.STLTransform(...)

Transform that uses statsmodels.tsa.seasonal.STL to subtract season and trend from the data.

etna.transforms.encoders.segment_encoder.SegmentEncoderTransform()

Encode segment label to categorical.

etna.transforms.timestamp.special_days.SpecialDaysTransform([...])

SpecialDaysTransform generates series that indicates is weekday/monthday is special in given dataframe.

etna.transforms.math.scalers.StandardScalerTransform([...])

Standardize features by removing the mean and scaling to unit variance.

etna.transforms.math.statistics.StdTransform(...)

StdTransform computes std value for given window.

etna.transforms.math.statistics.SumTransform(...)

SumTransform computes sum of values over given window.

etna.transforms.decomposition.detrend.TheilSenTrendTransform(...)

Transform that uses Theil–Sen regression with polynomial features to make a detrending.

etna.transforms.timestamp.time_flags.TimeFlagsTransform([...])

TimeFlagsTransform is a class that implements extraction of the main time-based features from datetime column.

etna.transforms.missing_values.imputation.TimeSeriesImputerTransform([...])

Transform to fill NaNs in series of a given dataframe.

etna.transforms.base.Transform(required_features)

Base class to create any transforms to apply to data.

etna.transforms.feature_selection.feature_importance.TreeFeatureSelectionTransform(...)

Transform that selects features according to tree-based models feature importance.

etna.transforms.decomposition.change_points_based.trend.TrendTransform(...)

Transform that adds trend as a feature.

etna.transforms.math.power.YeoJohnsonTransform([...])

YeoJohnsonTransform applies Yeo-Johns transformation to a DataFrame.