Struct LogNormal 

pub struct LogNormal;

Log-normal peak: A · exp(−(ln(x/c))² / (2σ²)) for x > 0, else 0.

Parameters (in order): [amplitude, center, sigma]

• amplitude is the peak height attained at x == center.
• center > 0 is the peak location (log-space mode).
• sigma is the log-space width.

The kernel is defined only for x > 0; at x <= 0 it returns 0.0 (the log argument is undefined there). The numpy benchmark formula is identical — np.where(x > 0, A·exp(−(ln(x/c))²/(2σ²)), 0) — so numpy↔Rust parity is exact.

Trait Implementations

impl Model for LogNormal

fn jacobian(&self, x: &[f64], params: &[f64]) -> Vec<f64>

Central finite-difference Jacobian.

The closed form has a logarithmic singularity at x == 0, so a numerical (central-difference) Jacobian is used rather than an analytical one. Step h = 1e-7 · |p[i]|.max(1e-7) (relative + absolute floor), matching the trait’s default magnitude.

fn eval(&self, x: &[f64], params: &[f64]) -> f64

Evaluate the model at coordinate x with the given params.

fn param_names(&self) -> Vec<Cow<'static, str>>

Ordered parameter names, matching the layout expected by eval and jacobian.

fn jacobian_into(&self, x: &[f64], params: &[f64], out: &mut [f64])

Fill a pre-allocated slice with Jacobian values (one entry per parameter).

fn eval_slice_into(&self, xs: &[f64], params: &[f64], out: &mut [f64])

Batch evaluation of a 1-D model: fill out[i] = eval([xs[i]], params).

fn jac_slice_into(&self, xs: &[f64], params: &[f64], out: &mut [f64])

Batch Jacobian for a 1-D model: fill out in row-major layout [i * params.len() + j] = d(model)/d(params[j]) at xs[i].

fn n_dims(&self) -> usize

Number of coordinate dimensions consumed from x. Defaults to 1.