We used it at uni a lot but these days I tend to use it as a last mile language. Get the data, format it etc in python/f# then bring in the big R guns.
Things like BMA or survival analysis barely exist in python.
I have a great R stats book that I'll post when I get home (can't remember the name off the top of my head)
Edit: to be clear I wouldn't recommend that pipeline! Most of my professional work has been in the above so I'm just more comfortable with it
Here's a link to the book http://www-bcf.usc.edu/~gareth/ISL/, you can dl it from that page. Depending on how much stats theory you already know, you might find the labs sections the most useful.
As for the course, I'd love to advise but I really don't feel qualified as I don't know much about it, your background or what you want to achieve from it. I've generally found msoft resources to be excellent in the past though.
Generally where are you at? Do you have a good knowledge of the stats but not much programming or are you relatively new to both?
Thanks for the book. I don't know much of a stat theory.
At work, I enjoy working with numbers and data analyzing. I feel like I am "stuck" using excel. I didn't know that subject of data science existed until few weeks ago. I didn't know where to start so I decided to start with MSFT course.
I am fairly new to programming. I have done simple IOT projects. I would happy learning how to program while learning data science stuff.
Hey, I love to work with different languages and expand my knowledge. I wanted to know where should I start and focus initially. I will be interested in learning Python so I can do cool web applications.
PS: I love your blog! I have saved and bookmarked it!
To elaborate a bit, I use R for dplyr/ggplot2, both irreleplaceable for tabular data manipulation and visualization. Python I used for getting data, working with nontabular data from APIs (e.g JSON), and using Python tricks like list comprehensions and zip.
FWIW I wasn't suggesting sticking to one language exclusively, some of the biggest jumps I've made have been caused by exposure to different paradigms. But for beginners I think it can be helpful to keep focus in one place. There's a lot of overhead involved in a language (tooling, IDEs, best practices, quirks etc.) that can get in the way of seeing the important stuff.
Things like BMA or survival analysis barely exist in python.
I have a great R stats book that I'll post when I get home (can't remember the name off the top of my head)
Edit: to be clear I wouldn't recommend that pipeline! Most of my professional work has been in the above so I'm just more comfortable with it