Skip to main content

Methods to model all kinds of stochastic processes.

Project description


This repository aims to model and uncover the properties of all kinds of stochastic processes (processes that are based on some kind of underlying phenomenon like a coin toss for which we can't know the outcome for sure).

Some of these are taken from the book, Introduction to probability models by Sheldon Ross.

The best way to demonstrate the capabilities of this library is to describe some stochastic processes it can model and show how to use it to extract some of their properties.


To install the library, run (pyray was taken on pypi):

pip install stochproc

Make sure you have all the requirements (requirements.txt) installed. If not, you can run:

pip install -r requirements.txt

Alternately, you can fork/download the code and run from the main folder:

python install

Machine reliability

Let's say we start up a machine. It stays up some random amount of time before succumbing to failure. The amount of time it stays up is a random variable. This variable models the mean time between failures.

And once the machine is down, it takes a certain amount of time to get repaired. This is the mean time to repair.

The question is at any time t, what is the probability the machine is up and running?

Chapter 11 of [1] provides a closed form. However, we want to validate this with simulation.

from stochproc.reliability.machinerepair import *

for i in range(10):
	probs = []
	stds = []
	for t in range(1,100):
		prob, std = updown(t)
	plt.plot(np.arange(1,100), probs,alpha=0.4,color='pink')

xs = np.arange(1,100)
plt.plot(xs, closed_form(xs),color='red')
plt.ylabel('Reliability of system')

This leads to the following plot.

Image formed by above method

Coin toss sequences

Let's say you and I start tossing fair coins. What is the probability you'll reach three consecutive heads before I reach two consecutive heads? What about in general you reaching (n+1) consecutive heads before I reach n consecutive heads?

from stochproc.competitivecointoss.smallmarkov import *

ns = np.arange(2,15)
win_probs = []
for n in ns:
    # The losing markov sequence of coin tosses that needs (n-1) heads.
    lose_seq = MarkovSequence(get_consecutive_heads_mat(n))
    # The winning markov sequence of coin tosses that needs n heads.
    win_seq = MarkovSequence(get_consecutive_heads_mat(n+1))
    # If you multiply the two sequence objects, you get the probability
    # that the first one beats the second one.
    win_prob = win_seq*lose_seq

plt.plot(ns, win_probs)

This leads to the following plot:

Image formed by above method

Project details

Download files

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

Source Distributions

No source distribution files available for this release. See tutorial on generating distribution archives.

Built Distribution

stochproc-0.0.10-py3-none-any.whl (60.5 kB view hashes)

Uploaded py3

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