Skip to content
fastlowess-wasm

API Reference

fastlowess-wasm

fastlowess-wasm / SmoothOptions

Interface: SmoothOptions

Section titled “Interface: SmoothOptions”

Defined in: fastlowess_wasm.d.ts:25

Configuration options for LOWESS smoothing.

Properties

Section titled “Properties”

auto_converge?

Section titled “auto_converge?”

optional auto_converge?: number

Defined in: fastlowess_wasm.d.ts:51

Auto-convergence tolerance. Disabled when absent.

boundary_policy?

Section titled “boundary_policy?”

optional boundary_policy?: string

Defined in: fastlowess_wasm.d.ts:47

Boundary handling (“extend”, “reflect”, “zero”, “noboundary”). Default: “extend”.

cv?

Section titled “cv?”

optional cv?: CVOptions

Defined in: fastlowess_wasm.d.ts:31

Grouped cross-validation configuration.

delta?

Section titled “delta?”

optional delta?: number

Defined in: fastlowess_wasm.d.ts:39

Delta for interpolation speedup. Default: auto. Set to 0 to disable.

fraction?

Section titled “fraction?”

optional fraction?: number

Defined in: fastlowess_wasm.d.ts:35

Smoothing fraction (0 < fraction <= 1). Default: 0.67.

intervals?

Section titled “intervals?”

optional intervals?: IntervalsOptions

Defined in: fastlowess_wasm.d.ts:29

Grouped confidence/prediction levels and optional residual-bootstrap refits.

iterations?

Section titled “iterations?”

optional iterations?: number

Defined in: fastlowess_wasm.d.ts:37

Number of robustness iterations. Default: 3.

missing?

Section titled “missing?”

optional missing?: string

Defined in: fastlowess_wasm.d.ts:55

Policy for non-finite (NaN/Inf) values in input data (“error”, “drop”). Default: “error”.

outputs?

Section titled “outputs?”

optional outputs?: string[]

Defined in: fastlowess_wasm.d.ts:27

Optional output components: se, diagnostics, residuals, weights, derivative, sorted.

parallel?

Section titled “parallel?”

optional parallel?: boolean

Defined in: fastlowess_wasm.d.ts:53

Enable parallel execution. Ignored by OnlineLowess (it processes one point at a time). Default: true.

retain_model?

Section titled “retain_model?”

optional retain_model?: boolean

Defined in: fastlowess_wasm.d.ts:57

Retain the fitted model’s training data, enabling LowessResult.predict(). Batch (Lowess) only. Default: false.

robustness_method?

Section titled “robustness_method?”

optional robustness_method?: string

Defined in: fastlowess_wasm.d.ts:43

Robustness method (“bisquare”, “huber”, “talwar”). Default: “bisquare”.

scaling_method?

Section titled “scaling_method?”

optional scaling_method?: string

Defined in: fastlowess_wasm.d.ts:49

Scaling method (“mad”, “mar”, “mean”). Default: “mad”.

seed?

Section titled “seed?”

optional seed?: number | bigint

Defined in: fastlowess_wasm.d.ts:33

Safe-integer Number or unsigned 64-bit BigInt seed for CV/bootstrap; 0 is valid. Does not enable either by itself.

weight_function?

Section titled “weight_function?”

optional weight_function?: string

Defined in: fastlowess_wasm.d.ts:41

Kernel function (“tricube”, “epanechnikov”, “gaussian”, “uniform”, “biweight”, “triangle”, “cosine”). Default: “tricube”.

zero_weight_fallback?

Section titled “zero_weight_fallback?”

optional zero_weight_fallback?: string

Defined in: fastlowess_wasm.d.ts:45

Fallback when all weights are zero (“use_local_mean”, “return_original”, “return_none”). Default: “use_local_mean”.