Math and statistics toolboxes

A variety of computation tools for doing math and statistics in data analysis.

See also: General programming info on some of the tools mentioned below

General numerical tools

  • NumPy- Implements n-dimensional arrays and related numerical methods. Most python math/stats toolboxes are built on this module.


  • SciPy
  • gretl- Gnu regression, Econometrics and Time-series library.
  • pandas- the Python Data Analysis Library.
  • Has DataFrame objects - equivalent to the data.frame object in R
  • Has tools for many statistics (covariance, correlation, regression)
  • Timeseries analysis
  • Missing data functions
  • Some stats may be moved to StatsModels (below)
  • StatsModels- Python module with classes and functions for many statistical models, tests, and data exploration.

Symbolic Math

  • Maxima- a computer algebra system (similar to Mathematica/Maple)
  • SymPy- Symbolic math/algebra with Python.