tsdive.screen ¶

screen(
    archive: str | Path,
    baseline: str,
    window: str,
    *,
    method: str = "mad",
    k: float = 3.0,
    mode: str | Path | None = None,
    basis: str
    | CalculationBasis = CalculationBasis.TIME_WEIGHTED,
    stepped: bool = False,
) -> ScreenAnalysis

Screen one window of a single-tag archive against a baseline.

Parameters:

Name	Type	Description	Default
`archive`	`str \| Path`	parquet archive carrying `tsdive.meta`.	required
`baseline`	`str`	`START/END` in ISO 8601 UTC for the history.	required
`window`	`str`	`START/END` in ISO 8601 UTC to screen.	required
`method`	`str`	`"mad"` or `"moving-range"`; ignored with `mode`.	`'mad'`
`k`	`float`	flag beyond `k` times the scale from the center.	`3.0`
`mode`	`str \| Path \| None`	MODE archive; one baseline per regime instead of one for the window.	`None`
`basis`	`str \| CalculationBasis`	calculation basis declared on the read.	`TIME_WEIGHTED`
`stepped`	`bool`	stepped interpolation between samples.	`False`

Raises:

Type	Description
`ValueError`	malformed window, overlapping windows, unknown method.
`TSDiveError`	a censored baseline, or any typed refusal from the read path.

Examples:

>>> import tsdive
>>> s = tsdive.screen("data/demo/fic101_demo.parquet",
...                   "2024-03-30T20:00:00Z/2024-03-31T01:00:00Z",  # baseline
...                   "2024-03-31T01:00:00Z/2024-03-31T06:00:00Z")  # window
>>> s.to_dict()["n_flagged"], s.to_dict()["n_screened"]
(29, 300)
>>> len(s.frame)
29