A shell called xonsh

A review of Xonsh, a new Python-facing shell
tools productivity computing

Any computational scientist who spends their time writing and using tools or analyzing data has certainly had to spend a great deal of his/her time interacting with a command line interface (as an aside, I at one point spent so much time staring at the command line that I wrote a set of scripts to provide me with comical quotes to break up the monotony of my work – it can be found here). Despite the extensive use that it sees, shell languages that operate from a terminal (or from the command line) are rather few in number; moreover, the vast majority of such languages sport syntax that is nearly mind-numbing (and have steep learning curves, making them incredibly unfriendly to new practitioners). To solve this problem, the xonsh shell has recently been developed, taking python as inspiration for implementing its scripting language.

By clever use of some of Python’s existing modules, and a great deal of work, the community around xonsh has been able to successfully provide a shell that is ideally suited to the purposes of most computational scientists, from statisticians to physicists, and beyond. Though xonsh is rather new and will certainly undergo a great deal of further development, it is already mature enough for use for most day-to-day purposes. I’ve even adopted it as a secondary shell for most of my own work…

Though xonsh will certainly not replace the likes of GNU Bash anytime in the near future, the friendly (pythonic) syntax, support of python modules from a command line interface, and development of new tools for extending its capabilities certainly provides xonsh with numerous advantages over bash. Look, you can make histograms (and view them easily) in the terminal with bashplotlib! Or, perhaps even better (so good, I gave it a whole blog post already), you can have automatic GitHub completion in your terminal with gitsome, which is based on the python REPL used by xonsh.

Want to install xonsh and use it for your own (…and maybe some of these other tools too)? Easy. Just use pip with your Python 3.4+. That’s right, they’re all on PyPi.

On most machines, installing xonsh and gitsome is as easy as:

pip3 install xonsh
pip3 install gitsome

Back to Linux - Adventures with the X1 Carbon

A review of getting a new 6th-generation X1 Carbon set up with Ubuntu Linux
computing productivity open source

2018 - a midyear review

A midway review of my professional life in 2018
statistics graduate school productivity

Taking blogdown for a test drive

Trying out RStudio's new blogging framework
R data science tools productivity
comments powered by Disqus