filter_away_flatline_chunks#
- openstef_beam.benchmarking.target_provider.filter_away_flatline_chunks(measurement_series: Series, min_length: int = 96, threshold: float = 1.0) Series[source]#
Mask long flatline segments in a target series.
Detects contiguous segments where the standard deviation inside both centered and right-aligned windows falls below threshold times the global standard deviation for at least min_length samples. Values inside those segments are replaced with NaN so downstream logic can drop them and derive a clean evaluation mask.
- Parameters:
measurement_series (
Series) – Time-indexed series containing the target observations.min_length (
int) – Minimum length (in samples) for a chunk to be treated as a flatline.threshold (
float) – Multiplier on the global standard deviation to define the flatline cutoff.measurement_series
min_length
threshold
- Returns:
A copy of measurement_series with flatline chunks set to NaN.
- Return type: