yohou.preprocessing¶

Time series transformers for feature engineering, scaling, imputation, outlier handling, and resampling.

Name	Description
`SeasonalImputer`	Seasonal decomposition-based imputation for missing values.
`SimpleImputer`	Simple imputation using sklearn's SimpleImputer.
`SimpleTimeImputer`	Time series imputation using interpolation or filling methods.
`TransformedSpaceKNNImputer`	K-nearest neighbors imputation in a transformed feature space.

Name	Description
`OutlierPercentileHandler`	Handle outliers based on percentile thresholds.
`OutlierThresholdHandler`	Handle outliers based on fixed threshold values.

Name	Description
`Downsampler`	Downsample time series to a lower frequency using aggregation.
`Upsampler`	Upsample time series to a higher frequency using interpolation.

Name	Description
`SklearnScaler`	Wrapper to integrate sklearn scalers into the Yohou pipeline.
`StandardScaler`	Standardize features by removing the mean and scaling to unit variance.
`MaxAbsScaler`	Scale each feature by its maximum absolute value.
`MinMaxScaler`	Transform features by scaling each feature to a given range.
`Normalizer`	Normalize samples individually to unit norm.
`RobustScaler`	Scale features using statistics that are robust to outliers.

Name	Description
`CalendarFeatureTransformer`	Extract calendar-based features (month, day of week, etc.) from the time column.
`HolidayFeatureTransformer`	Binary holiday indicator from a user-provided DataFrame of dates.
`FourierFeatureTransformer`	Generate Fourier sin/cos harmonics at a specified seasonal period.
`TimeIndexTransformer`	Convert the time column to a numeric index with optional polynomial terms.

Name	Description
`SklearnTransformer`	Wrapper to integrate sklearn transformers into the Yohou pipeline.
`LagTransformer`	Create lagged features from time series data.
`ExponentialMovingAverage`	Exponentially Weighted Moving Average (EWMA) transformer.
`PolynomialFeatures`	Generate polynomial and interaction features.
`PowerTransformer`	Apply a power transform featurewise to make data more Gaussian-like.
`QuantileTransformer`	Transform features using quantiles information.
`SplineTransformer`	Generate univariate B-spline bases for features.
`FunctionTransformer`	Constructs a transformer from an arbitrary callable.
`SlidingWindowFunctionTransformer`	Transform time series by applying a function over sliding windows.
`RollingStatisticsTransformer`	Compute rolling window statistics for time series.

Name	Description
`NumericalDifferentiator`	Numerical differentiation transformer for time series signals.
`NumericalFilter`	Apply digital IIR or FIR filters to time series data.
`NumericalIntegrator`	Numerical integration transformer for time series signals.