Stats Series - Course Two Halfway Point
in Training / PH_525_series on Statistics, Harvard, R, Python, Jupyter
Just concluded Week 2 of 4!
I had followed recommendations to this Harvard series when looking for some coursework on Linear Algebra. That’s this second course in this series. I chose to back up and do the first course beforehand. That was more prudent than I’d thought. I actually needed that first course as a refresher for Stats more than I need this. Furthermore, that first course covers things such as Data Visualization and Data Exploration.
I’m breezing through this second course for a few reasons. First, the actual work is similar enough to what I’d been doing earlier on HackerRank. So the mechanics are easier. I’m getting better practice doing things different ways. But it’s not the same as figuring out matplotlib stuff trying to do the same thing in R and Python.
If I had, at the moment, to summarize the differences between R and Python, it’d be:
- REMEMBER R is 1-based, Python is 0-based
- Everything in Python is backwards
But, even within Python you have to be careful. Does that columns of ones in my coeefficient matrix go on the right or on the left? That may depend on what module or function you’re using.
However, I still have a lingering feeling I need to go out and find a raw Linear Algebra refresher. This course is very tailored towards how to use Linear Algebra for the purpose of statistics. That’s good for what I’m doing at the moment though.