API Reference

fastloess-wasm

---

fastloess-wasm / OnlineSmoothOptions

Interface: OnlineSmoothOptions

Defined in: fastloess_wasm.d.ts:134

Configuration options for online LOESS smoothing. A subset of SmoothOptions: diagnostics, residuals, parallel execution, and cross-validation have no equivalent here. confidence_intervals/prediction_intervals and the se output require update_mode: "full".

Properties

auto_converge?

optional auto_converge?: number

Defined in: fastloess_wasm.d.ts:154

Auto-convergence tolerance. Disabled when absent.

---

boundary_degree_fallback?

optional boundary_degree_fallback?: boolean

Defined in: fastloess_wasm.d.ts:170

Fall back to lower polynomial degree at boundaries. Default: true.

---

boundary_policy?

optional boundary_policy?: string

Defined in: fastloess_wasm.d.ts:150

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

---

cell?

optional cell?: number

Defined in: fastloess_wasm.d.ts:166

Cell parameter for interpolation (fraction of data). Default: 0.2.

---

degree?

optional degree?: string

Defined in: fastloess_wasm.d.ts:156

Polynomial degree (“constant”, “linear”, “quadratic”, “cubic”, “quartic”). Default: “linear”.

---

dimensions?

optional dimensions?: number

Defined in: fastloess_wasm.d.ts:158

Number of predictor dimensions. Default: 1.

---

distance_metric?

optional distance_metric?: string

Defined in: fastloess_wasm.d.ts:160

Distance metric (“normalized”, “euclidean”, “manhattan”, “chebyshev”, “minkowski:p”, “weighted”). Default: “normalized”.

---

fraction?

optional fraction?: number

Defined in: fastloess_wasm.d.ts:139

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

---

interpolation_vertices?

optional interpolation_vertices?: number

Defined in: fastloess_wasm.d.ts:168

Number of interpolation vertices. Default: auto.

---

intervals?

optional intervals?: IntervalsOptions

Defined in: fastloess_wasm.d.ts:137

---

iterations?

optional iterations?: number

Defined in: fastloess_wasm.d.ts:142

Number of robustness iterations. Default: 0; positive values require update_mode: "full".

---

missing?

optional missing?: string

Defined in: fastloess_wasm.d.ts:172

Policy for non-finite (NaN/Inf) x/y values passed to add_point (“error”, “drop”). Default: “error”.

---

outputs?

optional outputs?: string[]

Defined in: fastloess_wasm.d.ts:136

Optional output components: weights, gradient (or derivative), se.

---

robustness_method?

optional robustness_method?: string

Defined in: fastloess_wasm.d.ts:146

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

---

scaling_method?

optional scaling_method?: string

Defined in: fastloess_wasm.d.ts:152

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

---

surface_mode?

optional surface_mode?: string

Defined in: fastloess_wasm.d.ts:162

Surface computation mode (“interpolation” or “direct”). Default: “interpolation”.

---

weight_function?

optional weight_function?: string

Defined in: fastloess_wasm.d.ts:144

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

---

weighted_metric_weights?

optional weighted_metric_weights?: number[]

Defined in: fastloess_wasm.d.ts:164

Per-dimension weights for the weighted distance metric.

---

zero_weight_fallback?

optional zero_weight_fallback?: string

Defined in: fastloess_wasm.d.ts:148

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