Python is a language that can be used in many contexts and can be adapted to any type of use through specialized libraries. It is, however, particularly used as a scripting language to automate simple but time-consuming tasks, such as a script that would retrieve weather from the Internet or integrate into computer-aided design software to automate repetitive action sequences. It is also used as a prototype development language when you need a functional application before optimizing it with a lower level language. It is particularly popular in the scientific world, and has many extensions for mathematical computation. Since machine learning data and algorithms are essentially defined as mathematical objects and procedures (with algebra, matrix manipulations, derivatives, etc), Python is one of the best languages to elaborate and perform machine learning methods.
There are a lot of multiple distributions of Python and in this tutorial we propose to use the Anaconda Python Continuum distribution, which is a very convenient packaged solution to write Python scripts and comes with a pleasant and practical IDE called : Spyder. You can download and install Anaconda Python Continuum suite from their website.
NOTE : Some people have reported that Anaconda Navigator crashes just after being launched. To solve this problem, you can remove and reinstall the navigator by opening a terminal and launching these two commands in sequence « conda remove anaconda-navigator » and « conda install anaconda-navigator ».
This is the Anaconda Navigator interface :
Anaconda Navigator
The Python IDE can be opened by clicking on « Launch » in the « Spyder » windows and looks like this :
Spyder Startup Page
Once Python and the IDE installed, we have to analyse and prepare the data.