Module compute::functions[][src]

Expand description

Various mathematical and statistical functions.

Functions

Calculates the beta function using the relationship between the beta function and the gamma function.

Calculates the binomial coefficient nCk for two integers n and k, with n >= k.

An alternative method for computing binomial coefficients. There is no significant difference between the compute time using the binom_coeff method and this method. This method becomes slightly inaccurate (by 1 or 2) starting at n ~ 50.

Calculates the one-parameter Box-Cox transformation with some power parameter lambda.

Calculates the two-parameter Box-Cox transformation with some power parameter lambda and some shift parameter alpha.

Calculates the digamma function, which is the logarithmic derivative of the gamma function. It obeys the equation digamma(x+1) = digamma(x) + 1/x. The approximation works better for large values. If the value is small, this function will shift it up using the digamma recurrence relation.

Calculates the error function erf(x).

Calculates the Gamma function using the Lanczos approximation. It obeys the equation gamma(x+1) = gamma(x) * x. This approximation uses the reflection formula to extend the calculation to the entire complex plane.

Calculates the standard logistic function

Calculates the logit function

Calculates the softmax (the normalized exponential) function, which is a generalization of the logistic function to multiple dimensions.