random - Stochastic calculus library in python -
I am looking for a Python Library that will allow me to calculate the Stochastic calculus content, such as a random (conditional ) The expected process will define the spread I was putting a look at a simpy (simpy.sourceforge.net), but it does not cover my needs.
This is for quick prototype and experimentation. In Java, I have experimented with some success (now inactive) library.
The problem is not difficult in itself, but to do very little trivial, boilerplate things (efficient memory usage, variable reduction techniques, and so on).
Ideally, I can write something like this (just illustrative):
def my_diffusion (t, dt, past_values, world, ** kwargs): W1, W2 = World.correlated_brownians_pair (correlation = kwargs ['rho']) X = past_values [-1] sigma_1 = kwargs ['sigma1'] sigma_2 = kwargs ['sigma 2'] dX = kwargs ['mu'] * X * Dt + sigma_1 * w1 * x * math.sqrt (dt) + sigma_2 * w2 * x * x * math.sqrt (dt) returns x + dx x = randomprocess (expansion = my_diffusion, x0 = 1.0) print x Exacticity (T = 252, DT = 1/252, N_assumul = 50000, World = World (Random_Gieter = 'SOBOL'), Sigma1 = 0.3, sigma2 = 0.01, rho = -0.1)
Does anyone know something else than reimplementing it in the numpy for example?
have you seen?
Comments
Post a Comment