SciPy

Plots for Continuous Distributions

Importing

To use the continuous plots, you must import the plots module. Plot_continuous and Plot_norm are the only functions that don’t require you to import the plots module.

In [1]: from prob140.plots import *

Quick Reference

The normal syntax for plotting a distribution is Plot_distribution(x_limits, parameters, optional_arguments)

Click the links below to see detailed information for plotting any distribution. Note that we won’t use most of these for Prob140

Plot_norm(x_limits, mu, sigma, **kwargs) Plots a gaussian distribution.
Plot_arcsine(x_limits, **kwargs) Plots an arcsine distribution.
Plot_beta(x_limits, a, b, **kwargs) Plots a beta distribution.
Plot_cauchy(x_limits[, loc, scale]) Plots a cauchy distribution.
Plot_chi2(x_limits, df, **kwargs) Plots a chi-squared distribution.
Plot_erlang(x_limits, r, lamb, **kwargs) Plots an erlang distribution.
Plot_expon(x_limits, lamb, **kwargs) Plots an exponential distribution
Plot_f(x_limits, dfn, dfd, **kwargs) Plots an F distribution.
Plot_gamma(x_limits, r, lamb, **kwargs) Plots a gamma distribution.
Plot_lognorm(x_limits, mu, sigma, **kwargs) Plots a log-normal distribution.
Plot_pareto(x_limits, alpha, **kwargs) Plots an alpha distribution.
Plot_powerlaw(x_limits, a, **kwargs) Plots a powerlaw distribution.
Plot_rayleigh(x_limits, sigma, **kwargs) Plots a rayleigh distribution.
Plot_t(x_limits, df, **kwargs) Plots a t distribution.
Plot_triang(x_limits, a, b, c, **kwargs) Plots a triangular distribution.
Plot_uniform(x_limits, a, b, **kwargs) Plots a uniform distribution.
Plot_continuous(x_limits, func, *args, **kwargs) Plots a continuous distribution

Plotting events

The optional parameters left_end= and right_end= define the left and right side to be shaded. These optional parameters should work for all the continuous distribution plots

In [2]: Plot_norm(x_limits=(-2, 2), mu=0, sigma=1, left_end=-1)
_images/norm_left_end.png
In [3]: Plot_norm(x_limits=(-2, 2), mu=0, sigma=1, right_end=1)
_images/norm_right_end.png
In [4]: Plot_norm(x_limits=(-2, 2), mu=0, sigma=1, left_end=-1, right_end=1)
_images/norm_left_right_end.png

We can also set the parameter tails=True to invert the direction to be shaded.

In [5]: Plot_norm(x_limits=(-2, 2), mu=0, sigma=1, left_end=-1, right_end=1, tails=True)
_images/norm_left_end_tails.png

CDF

For all the plot functions except Plot_continuous, you can pass the parameter cdf=True to plot the cumulative distribution function instead of the probability density function. This also works with left_end/right_end

In [6]: Plot_norm(x_limits=(-2, 2), mu=0, sigma=1, cdf=True)
_images/norm_cdf.png

Plot Examples

Plot_norm

In [7]: Plot_norm(x_limits=(-2, 2), mu=0, sigma=1)
_images/norm.png

Plot_arcsine

In [8]: Plot_arcsine(x_limits=(0.01, 0.99))
_images/arcsine.png

Plot_beta

In [9]: Plot_beta(x_limits=(0, 1), a=2, b=2)
_images/beta.png

Plot_cauchy

In [10]: Plot_cauchy(x_limits=(-5, 5))
_images/cauchy.png

Plot_chi2

In [11]: Plot_chi2(x_limits=(0, 8), df=3)
_images/chi2.png

Plot_erlang

In [12]: Plot_erlang(x_limits=(0, 12), r=3, lamb=0.5)
_images/erlang.png

Plot_expon

In [13]: Plot_expon(x_limits=(0, 5), lamb=1)
_images/expon.png

Plot_f

In [14]: Plot_f(x_limits=(0.01, 5), dfn=5, dfd=2)
_images/f.png

Plot_gamma

In [15]: Plot_gamma(x_limits=(0, 20), r=5, lamb=0.5)
_images/gamma.png

Plot_lognorm

In [16]: Plot_lognorm(x_limits=(0, 5), mu=0, sigma=0.25)
_images/lognorm.png

Plot_rayleigh

In [17]: Plot_rayleigh(x_limits=(0, 10), sigma=2)
_images/rayleigh.png

Plot_pareto

In [18]: Plot_pareto(x_limits=(0, 5), alpha=3)
_images/pareto.png

Plot_powerlaw

In [19]: Plot_powerlaw(x_limits=(0, 1), a=1.6)
_images/powerlaw.png

Plot_t

In [20]: Plot_t(x_limits=(-3, 3), df=2)
_images/t.png

Plot_triang

In [21]: Plot_triang(x_limits=(0, 10), a=2, b=10, c=3)
_images/triang.png

Plot_uniform

In [22]: Plot_uniform(x_limits=(0, 5), a=2, b=4)
_images/uniform.png