Enum TransformationNormalError 

pub enum TransformationNormalError {
    InvalidInput {
        reason: String,
    },
    DesignDegenerate {
        reason: String,
    },
    NonFinite {
        reason: String,
    },
    MonotonicityViolated {
        reason: String,
    },
    NumericalFailure {
        reason: String,
    },
}

Typed errors emitted by the transformation-normal family pipeline.

Each variant carries a pre-formatted reason so Display is byte-equivalent to the original format!(...) strings the module used before the typed-error migration. The category split lets callers pattern-match on the failure kind (e.g. distinguish a degenerate covariate design from a non-finite intermediate) without parsing text.

Public/trait boundaries (e.g. CustomFamily::evaluate) still return Result<_, String>; the From<TransformationNormalError> for String impl below provides the shim so every typed error flushes through ? or .into() at the boundary without per-callsite .map_err.

Variants

InvalidInput

Shape/length/dimension/contract violations on inputs to a routine (e.g. response/covariate row mismatch, beta length mismatch, wrong number of blocks, malformed configuration parameters).

Fields

reason: String

DesignDegenerate

A required covariate design or weight configuration cannot support the routine — empty design, zero total weight, residual variance not representable, warm-start coefficients all non-finite.

Fields

reason: String

NonFinite

A numeric intermediate (response transform, derivative, log-likelihood, weight, offset, gradient component, calibration quantity) came out non-finite or non-positive where positive finite is required.

Fields

reason: String

MonotonicityViolated

The fitted monotone transform’s derivative dropped to or below zero, or the response endpoint ordering required by the latent score (lower < h < upper) was not satisfied at evaluation time.

Fields

reason: String

NumericalFailure

A numerical step that maps through the standard-normal CDF (endpoint mass, log-difference, PIT probability, derivative ratio) underflowed or became non-representable at the requested arguments.

Fields

reason: String

Trait Implementations

impl Clone for TransformationNormalError

fn clone(&self) -> TransformationNormalError

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for TransformationNormalError

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Display for TransformationNormalError

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Error for TransformationNormalError

fn source(&self) -> Option<&(dyn Error + 'static)>

Returns the lower-level source of this error, if any.

fn description(&self) -> &str

👎Deprecated since 1.42.0:

use the Display impl or to_string()

fn cause(&self) -> Option<&dyn Error>

👎Deprecated since 1.33.0:

replaced by Error::source, which can support downcasting

fn provide<'a>(&'a self, request: &mut Request<'a>)

🔬This is a nightly-only experimental API. (error_generic_member_access)

Provides type-based access to context intended for error reports.

impl From<BlockCountMismatch> for TransformationNormalError

fn from(err: BlockCountMismatch) -> TransformationNormalError

Converts to this type from the input type.

impl From<TransformationNormalError> for String

fn from(err: TransformationNormalError) -> String

Converts to this type from the input type.