def update_params(self, loc=0.0, scale=1.0, use="scipy", **params):
self.__update_params__(
loc,
scale,
use,
mu=make_float(params.get("mu", params.get("loc", self.mu))),
sigma=make_float(
params.get("sigma", params.get("scale", self.sigma))))
def __init__(self, **params):
self.type = ProbabilityDistributionTypes.NORMAL
self.scipy_name = "norm"
self.numpy_name = ProbabilityDistributionTypes.NORMAL
self.mu = make_float(params.get("mu", params.get("loc", 0.0)))
self.sigma = make_float(
make_float(params.get("sigma", params.get("scale", 1.0))))
self.constraint_string = "sigma > 0"
self.__update_params__(mu=self.mu, sigma=self.sigma)
def update_params(self, loc=0.0, scale=1.0, use="scipy", **params):
self.__update_params__(
loc,
scale,
use,
alpha=make_float(params.get("alpha", params.get("a", self.alpha))),
beta=make_float(params.get("beta", params.get("b", self.beta))))
self.a = self.alpha
self.b = self.beta
def __init__(self, **params):
self.type = ProbabilityDistributionTypes.BETA
self.scipy_name = ProbabilityDistributionTypes.BETA
self.numpy_name = ProbabilityDistributionTypes.BETA
self.constraint_string = "alpha > 0 and beta > 0"
self.alpha = make_float(params.get("alpha", params.get("a", 2.0)))
self.beta = make_float(params.get("beta", params.get("b", 2.0)))
self.a = self.alpha
self.b = self.beta
self.__update_params__(alpha=self.alpha, beta=self.beta)
def update_params(self, loc=0.0, scale=1.0, use="scipy", **params):
self.__update_params__(
loc,
scale,
use,
mu=make_float(
params.get("mu", np.log(params.get("scale",
np.exp(self.mu))))),
sigma=make_float(
params.get("sigma", params.get("shape", self.shape))))
self.shape = self.sigma
def __init__(self, **params):
self.type = ProbabilityDistributionTypes.GAMMA
self.scipy_name = ProbabilityDistributionTypes.GAMMA
self.numpy_name = ProbabilityDistributionTypes.GAMMA
self.constraint_string = "alpha > 0 and beta > 0"
self.alpha = make_float(
params.get("alpha", params.get("k", params.get("shape", 2.0))))
self.beta = make_float(
params.get(
"beta",
params.get("rate", 1.0 /
params.get("theta", params.get("scale", 0.5)))))
self.k = self.alpha
self.theta = 1.0 / self.beta
self.__update_params__(alpha=self.alpha, theta=self.theta)
def update_params(self, loc=0.0, scale=1.0, use="scipy", **params):
self.__update_params__(
loc,
scale,
use,
a=make_float(
params.get("a", params.get("low", params.get("loc", self.a)))),
b=make_float(
params.get(
"b",
params.get("high",
params.get("scale", self.b - self.a) +
self.a))))
self.low = self.a
self.high = self.b
def __init__(self, **params):
self.type = ProbabilityDistributionTypes.BERNOULLI
self.scipy_name = ProbabilityDistributionTypes.BERNOULLI
self.numpy_name = ""
self.constraint_string = "0 < p < 1"
self.p = make_float(params.get("p", 0.5))
self.__update_params__(p=self.p)
def update_params(self, loc=0.0, scale=1.0, use="scipy", **params):
self.__update_params__(
loc,
scale,
use,
alpha=make_float(
params.get("alpha",
params.get("k", params.get("shape", self.alpha)))),
beta=make_float(
params.get(
"beta", 1.0 / params.get(
"theta",
params.get("scale", params.get("rate",
1.0 / self.beta))))))
self.k = self.alpha
self.theta = 1.0 / self.beta
def __init__(self, **params):
self.type = ProbabilityDistributionTypes.EXPONENTIAL
self.scipy_name = "expon"
self.numpy_name = ProbabilityDistributionTypes.EXPONENTIAL
self.constraint_string = "scale > 0"
self.lamda = make_float(params.get("lamda", params.get("rate", 1.0 / params.get("scale", 1.0))))
self.rate = self.lamda
self.__update_params__(lamda=self.lamda)
def __init__(self, **params):
self.type = ProbabilityDistributionTypes.BINOMIAL
self.scipy_name = "binom"
self.numpy_name = ProbabilityDistributionTypes.BINOMIAL
self.constraint_string = "n > 0 and 0 < p < 1"
self.n = make_int(params.get("n", 1))
self.p = make_float(params.get("p", 0.5))
self.__update_params__(n=self.n, p=self.p)
def __init__(self, **params):
self.type = ProbabilityDistributionTypes.POISSON
self.scipy_name = ProbabilityDistributionTypes.POISSON
self.numpy_name = ProbabilityDistributionTypes.POISSON
self.lamda = make_float(
params.get("lamda", params.get("lam", params.get("mu", 0.5))))
self.constraint_string = "0 < lamda < 1"
self.__update_params__(lamda=self.lamda)
self.mu = self.lamda
def __init__(self, **params):
self.type = ProbabilityDistributionTypes.UNIFORM
self.scipy_name = ProbabilityDistributionTypes.UNIFORM
self.numpy_name = ProbabilityDistributionTypes.UNIFORM
self.constraint_string = "a < b"
self.a = make_float(
params.get("a",
params.get("low", params.get("loc",
DEFAULT_LOW_VALUE))))
self.b = make_float(
params.get(
"b",
params.get(
"high",
params.get("scale", 2.0 * DEFAULT_HIGH_VALUE) -
DEFAULT_HIGH_VALUE)))
self.__update_params__(a=self.a, b=self.b)
self.low = self.a
self.high = self.b
def update_params(self, loc=0.0, scale=1.0, use="scipy", **params):
self.__update_params__(loc,
scale,
use,
lamda=make_float(
params.get(
"lamda",
params.get("lam",
params.get("mu",
self.lamda)))))
self.mu = self.lamda
def update_params(self, loc=0.0, scale=1.0, use="scipy", **params):
self.__update_params__(loc,
scale,
use,
n=make_int(params.get("n", self.n)),
p=make_float(params.get("p", self.p)))
def _update_params(self, use="scipy", **params):
self.loc = make_float(params.pop("loc", self.loc))
self.scale = make_float(params.pop("scale", self.scale))
self.update_params(self.loc, self.scale, use=use, **params)
return self
def update_params(self, loc=0.0, scale=1.0, use="scipy", **params):
self.__update_params__(loc, scale, use,
lamda=make_float(params.get("lamda", params.get("rate", 1.0 / params.get("scale",
1.0 / self.lamda)))))
self.rate = self.lamda