How to use the orbitize.priors.LinearPrior function in orbitize

def test_run_sampler():

    # initialize sampler
    myDriver = orbitize.driver.Driver(input_file, 'OFTI',
                                      1, 1.22, 56.95, mass_err=0.08, plx_err=0.26)

    s = myDriver.sampler

    # change eccentricity prior
    myDriver.system.sys_priors[1] = priors.LinearPrior(-2.18, 2.01)

    # test num_samples=1
    s.run_sampler(0, num_samples=1)

    # test to make sure outputs are reasonable
    start = time.time()
    orbits = s.run_sampler(1000, num_cores=4)

    end = time.time()
    print()
    print("Runtime: "+str(end-start) + " s")
    print()
    print(orbits[0])

    # test that lnlikes being saved are correct
    returned_lnlike_test = s.results.lnlike[0]

import numpy as np
import pytest
from scipy.stats import norm as nm

import orbitize.priors as priors

threshold = 1e-1

initialization_inputs = {
	priors.GaussianPrior : [1000., 1.], 
	priors.LogUniformPrior : [1., 2.], 
	priors.UniformPrior : [0., 1.], 
	priors.SinPrior : [], 
	priors.LinearPrior : [-2., 2.]
}

expected_means_mins_maxes = {
	priors.GaussianPrior : (1000.,0.,np.inf), 
	priors.LogUniformPrior : (1/np.log(2),1., 2.), 
	priors.UniformPrior : (0.5, 0., 1.), 
	priors.SinPrior : (np.pi/2., 0., np.pi), 
	priors.LinearPrior : (1./3.,0.,1.0)
}

lnprob_inputs = {
	priors.GaussianPrior : np.array([-3.0, np.inf, 1000., 999.]),
	priors.LogUniformPrior : np.array([-1., 0., 1., 1.5, 2., 2.5]),
	priors.UniformPrior : np.array([0., 0.5, 1., -1., 2.]),
	priors.SinPrior : np.array([0., np.pi/2., np.pi, 10., -1.]),
	priors.LinearPrior : np.array([0., 0.5, 1., 2., -1.])

def test_run_sampler():

    # initialize sampler
    myDriver = orbitize.driver.Driver(input_file, 'OFTI',
                                      1, 1.22, 56.95, mass_err=0.08, plx_err=0.26)

    s = myDriver.sampler

    # change eccentricity prior
    myDriver.system.sys_priors[1] = priors.LinearPrior(-2.18, 2.01)

    # test num_samples=1
    s.run_sampler(0, num_samples=1)

    # test to make sure outputs are reasonable
    start = time.time()
    orbits = s.run_sampler(1000, num_cores=4)

    end = time.time()
    print()
    print("Runtime: "+str(end-start) + " s")
    print()
    print(orbits[0])

    # test that lnlikes being saved are correct
    returned_lnlike_test = s.results.lnlike[0]

Returns:
        float: prior probability of this set of parameters
    """
    logp = 0.
    for param, prior in zip(params, priors):
        param = np.array([param])

        logp += prior.compute_lnprob(param)  # retrun a float

    return logp


if __name__ == '__main__':

    myPrior = LinearPrior(-1., 1.)
    mySamples = myPrior.draw_samples(1000)
    print(mySamples)
    myProbs = myPrior.compute_lnprob(mySamples)
    print(myProbs)

    myPrior = GaussianPrior(1.3, 0.2)
    mySamples = myPrior.draw_samples(1)
    print(mySamples)

    myProbs = myPrior.compute_lnprob(mySamples)
    print(myProbs)