Python Programming for Biology: Bioinformatics and Beyond

Statistics in Python

Although you can use knowledge of the underlying mathematics to design and code your

own  statistics  software,  for  anything  beyond  the  simplest  analysis  it  is  common  to  use

existing  statistical  routines.  For  the  examples  in  this  chapter  we  will  primarily  be  using

data held in NumPy arrays in combination with the SciPy

2

module scipy.stats. At the time

of  writing  the  statistical  package  R

3

 is  very  commonly  used  in  biology.  R  has  its  own

language, but there is a Python wrapper around it called RPy,

4

so you can use R tools in

Python programs, including with NumPy arrays. In the Appendix we will illustrate the use

of RPy for some of the most common statistical tests.