SpatialDE.SpatialPatternParameters

class SpatialDE.SpatialPatternParameters(nclasses=None, lengthscales=None, pattern_prune_threshold=1e-06, method='l-bfgs-b', tol=1e-09, maxiter=1000, gamma_1=1e-14, gamma_2=1e-14, eta_1=1, eta_2=1)

Parameters for automated expession histology.

Parameters:

  • nclasses (Optional[Integral]) – Maximum number of regions to consider. Defaults to the square root of the number of observations.

  • lengthscales (Union[Real, List[Real], None]) – List of kernel lenthscales. Defaults to a single lengthscale of the minimum distance between observations.

  • pattern_prune_threshold (float) – Probability threshold at which unused patterns are removed. Defaults to 1e-6.

  • method (str) – Optimization algorithm, must be known to scipy.optimize.minimize. Defaults to l-bfgs-b.

  • tol (Optional[Real]) – Convergence tolerance. Defaults to 1e-9.

  • maxiter (Integral) – Maximum number of iterations. Defaults to 1000.

  • gamma_1 (Real) – Parameter of the noise variance prior, defaults to 1e-14.

  • gamma_2 (Real) – Parameter of the noise variance prior, defaults to 1e-14.

  • eta_1 (Real) – Parameter of the Dirichlet process hyperprior, defaults to 1.

  • eta_2 (Real) – Parameter of the Dirichlet process hyperprior, defaults to 1.