Python for Data Analysis

Python is a powerful programming language and it interfaces well with other languages and platforms. One reason I like it so much is that it is free and I can use it interactively (similar to MATLAB).

To install Python go to: Python 3.x is dramatically different from Python 2.x. I will use 2.7.11. To use it for analysis, you’ll need to download and import some packages. Some keys ones are:


Since I am on a Windows system, the easiest installation process is to install a Python distribution with SciPy already included. One option is WinPython (Windows only!). Another option is Anaconda (Windows, Mac, Linux).

The next package you will may need if you want to perform some computer vision or image processing analyses is OpenCV. Since I am using Windows, you can download it at here from

Another great package to have available for data analysis and data mining is SciKit-Lean, which is open source and contains NumPy, SciPy, and matplotlib.