def mc_sample(self, nruns):
"""Monte carlo sampled parameter values
Return a defined set (nruns values) of Monte Carlo sampled parameter
values from the parameter distribution.
Parameters
----------
nruns : int
Number of Monte Carlo samples to take
Returns
--------
mcsample : array
Numpy array with the specified number of Monte Carlo samples
"""
if self.pardistribution == 'randomUniform':
return randomUniform(left=self.min, right=self.max,
rnsize=nruns)
# if self.pardistribution == 'discreteUniform':
# return randomUniform(left = self.min, right = self.max,
# rnsize = nruns)
elif self.pardistribution == 'randomTriangular':
return randomTriangular(left = self.min, mode = self.mode,
right = self.max, rnsize = nruns)
elif self.pardistribution == 'randomTrapezoidal':
return randomTrapezoidal(left = self.min, mode1 = self.mode1,
mode2 = self.mode2, right = self.max,
rnsize = nruns)
elif self.pardistribution == 'randomNormal':
return randomNormal(mu = self.mu, sigma = self.sigma,
rnsize = nruns)
elif self.pardistribution == 'randomLogNormal':
return randomLogNormal(mu = self.mu, sigma = self.sigma,
rnsize = nruns)
def avalue(self):
"""return single sampled value
Return a single Monte Carlo sampled parameter
value from the parameter distribution.
"""
if self.pardistribution == 'randomUniform':
return randomUniform(left=self.min, right=self.max,
rnsize=1)[0]
elif self.pardistribution == 'randomTriangular':
return randomTriangular(left=self.min, mode=self.mode,
right=self.max, rnsize=1)[0]
elif self.pardistribution == 'randomTrapezoidal':
return randomTrapezoidal(left=self.min, mode1=self.mode1,
mode2=self.mode2, right=self.max,
rnsize=1)[0]
elif self.pardistribution == 'randomNormal':
return randomNormal(mu=self.mu, sigma=self.sigma,
rnsize=1)[0]
elif self.pardistribution == 'randomLogNormal':
return randomLogNormal(mu=self.mu, sigma=self.sigma,
rnsize=1)[0]
def avalue(self):
"""return single sampled value
Return a single Monte Carlo sampled parameter
value from the parameter distribution.
"""
if self.pardistribution == 'randomUniform':
return randomUniform(left=self.min, right=self.max, rnsize=1)[0]
elif self.pardistribution == 'randomTriangular':
return randomTriangular(left=self.min,
mode=self.mode,
right=self.max,
rnsize=1)[0]
elif self.pardistribution == 'randomTrapezoidal':
return randomTrapezoidal(left=self.min,
mode1=self.mode1,
mode2=self.mode2,
right=self.max,
rnsize=1)[0]
elif self.pardistribution == 'randomNormal':
return randomNormal(mu=self.mu, sigma=self.sigma, rnsize=1)[0]
elif self.pardistribution == 'randomLogNormal':
return randomLogNormal(mu=self.mu, sigma=self.sigma, rnsize=1)[0]
def mc_sample(self, nruns):
"""Monte carlo sampled parameter values
Return a defined set (nruns values) of Monte Carlo sampled parameter
values from the parameter distribution.
Parameters
----------
nruns : int
Number of Monte Carlo samples to take
Returns
--------
mcsample : array
Numpy array with the specified number of Monte Carlo samples
"""
if self.pardistribution == 'randomUniform':
return randomUniform(left=self.min, right=self.max, rnsize=nruns)
# if self.pardistribution == 'discreteUniform':
# return randomUniform(left = self.min, right = self.max,
# rnsize = nruns)
elif self.pardistribution == 'randomTriangular':
return randomTriangular(left=self.min,
mode=self.mode,
right=self.max,
rnsize=nruns)
elif self.pardistribution == 'randomTrapezoidal':
return randomTrapezoidal(left=self.min,
mode1=self.mode1,
mode2=self.mode2,
right=self.max,
rnsize=nruns)
elif self.pardistribution == 'randomNormal':
return randomNormal(mu=self.mu, sigma=self.sigma, rnsize=nruns)
elif self.pardistribution == 'randomLogNormal':
return randomLogNormal(mu=self.mu, sigma=self.sigma, rnsize=nruns)