pub struct DetectConfig {Show 20 fields
pub point_threshold: f64,
pub point_min_n: usize,
pub column_roles: bool,
pub point_fdr_q: Option<f64>,
pub dist_alpha: f64,
pub psi_threshold: f64,
pub psi_bins: usize,
pub dist_min_n: usize,
pub struct_null_rate: f64,
pub mv_alpha: f64,
pub mv_min_n: usize,
pub mv_ridge: f64,
pub ctx_period: usize,
pub ctx_threshold: f64,
pub ctx_min_per_phase: usize,
pub coll_min_n: usize,
pub coll_threshold: f64,
pub cadence_column: Option<String>,
pub cad_max_cv: f64,
pub cad_min_n: usize,
}Fields§
§point_threshold: f64Modified z-score threshold for the point detector (Iglewicz–Hoaglin default is 3.5).
point_min_n: usizeMinimum count of finite numeric values a column needs before the point detector will assess it. Below this, statistics are unreliable.
column_roles: boolWhen set, detectors consult each column’s Role and skip
columns where their statistic is meaningless (e.g. the point detector
skips identifier/categorical/sequence columns). Roles are always reported
in the envelope; this only governs whether they affect detection.
point_fdr_q: Option<f64>Optional false-discovery-rate (FDR) level for the point detector. When
set, the per-cell modified-z threshold is replaced by Benjamini–Hochberg
control at this level, applied within each column: a cell is flagged only
if its two-sided p-value survives BH, bounding the expected proportion of
false flags at q. None keeps the fixed point_threshold behavior.
dist_alpha: f64Significance level for the KS and chi-square drift tests. A column is flagged when the test’s p-value falls below this.
psi_threshold: f64Population Stability Index threshold; PSI above this signals drift (0.1 ≈ moderate, 0.2 ≈ significant by convention).
psi_bins: usizeNumber of (baseline-quantile) bins used for PSI.
dist_min_n: usizeMinimum sample size (per side) before a distributional test runs.
struct_null_rate: f64Null fraction above which the structural detector flags a column.
mv_alpha: f64Significance level for the Mahalanobis multivariate test (per row). Smaller than the per-column α because every row is tested.
mv_min_n: usizeMinimum number of complete (no-missing) rows before the multivariate detector will estimate a covariance and run.
mv_ridge: f64Relative ridge added to the covariance diagonal for numerical stability (handles collinear / zero-variance columns). Scaled by the mean variance.
ctx_period: usizeSeasonal period for the contextual detector. 0 (or 1) disables it —
seasonality is never guessed, so without a declared period the detector
reports honest absence.
ctx_threshold: f64Modified z-score threshold within a seasonal subseries.
ctx_min_per_phase: usizeMinimum finite values a phase needs before it is assessed.
coll_min_n: usizeMinimum length of an ordered numeric column before the collective (change-point) detector will run.
coll_threshold: f64Standardized mean-shift threshold for the collective detector. Set conservatively because the change point is chosen by maximization.
cadence_column: Option<String>Column to assess for metronomic cadence (interpreted as event times).
None disables the cadence detector — which timestamps mean “time” is
never guessed, so without this it reports honest absence.
cad_max_cv: f64Coefficient-of-variation threshold below which inter-arrival intervals are flagged as suspiciously regular (automated).
cad_min_n: usizeMinimum number of intervals before cadence is assessed.
Implementations§
Trait Implementations§
Source§impl Clone for DetectConfig
impl Clone for DetectConfig
Source§fn clone(&self) -> DetectConfig
fn clone(&self) -> DetectConfig
1.0.0 (const: unstable) · Source§fn clone_from(&mut self, source: &Self)
fn clone_from(&mut self, source: &Self)
source. Read moreSource§impl Debug for DetectConfig
impl Debug for DetectConfig
Source§impl Default for DetectConfig
impl Default for DetectConfig
Source§impl<'de> Deserialize<'de> for DetectConfig
impl<'de> Deserialize<'de> for DetectConfig
Source§fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>where
__D: Deserializer<'de>,
fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>where
__D: Deserializer<'de>,
Auto Trait Implementations§
impl Freeze for DetectConfig
impl RefUnwindSafe for DetectConfig
impl Send for DetectConfig
impl Sync for DetectConfig
impl Unpin for DetectConfig
impl UnsafeUnpin for DetectConfig
impl UnwindSafe for DetectConfig
Blanket Implementations§
Source§impl<T> BorrowMut<T> for Twhere
T: ?Sized,
impl<T> BorrowMut<T> for Twhere
T: ?Sized,
Source§fn borrow_mut(&mut self) -> &mut T
fn borrow_mut(&mut self) -> &mut T
Source§impl<T> CloneToUninit for Twhere
T: Clone,
impl<T> CloneToUninit for Twhere
T: Clone,
Source§impl<SS, SP> SupersetOf<SS> for SPwhere
SS: SubsetOf<SP>,
impl<SS, SP> SupersetOf<SS> for SPwhere
SS: SubsetOf<SP>,
Source§fn to_subset(&self) -> Option<SS>
fn to_subset(&self) -> Option<SS>
self from the equivalent element of its
superset. Read moreSource§fn is_in_subset(&self) -> bool
fn is_in_subset(&self) -> bool
self is actually part of its subset T (and can be converted to it).Source§fn to_subset_unchecked(&self) -> SS
fn to_subset_unchecked(&self) -> SS
self.to_subset but without any property checks. Always succeeds.Source§fn from_subset(element: &SS) -> SP
fn from_subset(element: &SS) -> SP
self to the equivalent element of its superset.