mizarlabs.transformers.sampling package

Submodules

mizarlabs.transformers.sampling.average_uniqueness module

class mizarlabs.transformers.sampling.average_uniqueness.AverageUniqueness(event_end_time_column_name: str = 'event_end_time')

Bases: sklearn.base.BaseEstimator, sklearn.base.TransformerMixin

Calculates the average uniqueness of samples.

transform(X: pandas.core.frame.DataFrame) → pandas.core.series.Series

mizarlabs.transformers.sampling.down_sampling module

class mizarlabs.transformers.sampling.down_sampling.CUSUMFilter(threshold: float)

Bases: sklearn.base.BaseEstimator, sklearn.base.TransformerMixin

Downsamples a timeseries to filter out non significant value changing samples.

Parameters

threshold (float) – Sets the threshold to trigger a sample, setting the threshold higher will result in less samples being selected.

transform(X: pandas.core.series.Series) → pandas.core.indexes.datetimes.DatetimeIndex

Returns a pandas DatetimeIndex indicating which samples have been selected by the CUSUM filter.

Parameters

X (pd.Series) – Time series with time indices.

Returns

DatetimeIndex indicating which samples have been selected.

Return type

pd.DatetimeIndex

Module contents