Skip to main content

sampling from univariate distributions

Project description

samplepy implements three sampling methods for univariate distributions. The package includes:

  • Importance sampling: samplepy.Importance

  • Rejection sampling: samplepy.Rejection

  • Metropolis-Hastings sampling: samplepy.MH


from samplepy import Rejection
import matplotlib.pyplot as plt
import numpy as np

Rejection sampling example from 2 different functions
# define a unimodal function to sample under
f = lambda x: 2.0*np.exp(-2.0*x)
rej = Rejection(f, [0.01, 3.0])  # instantiate Rejection sampling with f and interval
sample = rej.sample(10000, 1)    # create a sample of 10K points

x = np.arange(0.01, 3.0, (3.0-0.01)/10000)
fx = f(x)

figure, axis = plt.subplots()
axis.hist(sample, normed=1, bins=40)
axis2 = axis.twinx()
axis2.plot(x, fx, 'g', label="f(x)=2.0*exp(-2*x)")

More examples and package documentation can be found at <>


pip install samplepy

Project details

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution (147.6 kB view hashes)

Uploaded source

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page