4
$\begingroup$

I would like to learn both Python and R for usage in data science projects.

I am currently unemployed, fresh out of university, scouting around for jobs and thought it would be good if I get some Kaggle projects under my profile.

However, I have very little knowledge in either language. Have used Matlab and C/C++ in the past. But I haven't produced production quality code or developed an application or software in either language. It has been dirty coding for academic usage all along.

I have used a little bit of Python, in a university project, but I dont know the fundamentals like what is a package , etc etc. ie havent read the intricacies of the language using a standard Python Textbook etc..

Have done some amount of coding in C/C++ way back (3-4 years back then switched over to Matlab/Octave).

I would like to get started in Python Numpy Scipy scikit-learn and pandas etc. but just reading up Wikipedia articles or Python textbooks is going to be infeasible for me.

And same goes with R, except that I have zero knowledge of R.

Does anyone have any suggestions?

$\endgroup$
  • 1
    $\begingroup$ This is probably off topic if you're just asking for tutorials and resources. Please elaborate with the specific issues you are facing with these tools. $\endgroup$ – Sean Owen Oct 21 '14 at 13:59
  • $\begingroup$ Here are some guidelines about posts here. datascience.stackexchange.com/help/dont-ask $\endgroup$ – sheldonkreger Nov 13 '14 at 0:18
2
$\begingroup$

There is an online data science "game" that takes you from learning how to use Python for loading a csv and using scikit to machine learning algorithms such as support vector machines. Here is a blog post with a demo video and the actual site is Explore Data Science. Personally, I think its genius.

| improve this answer | |
$\endgroup$
  • $\begingroup$ Look pretty cool, but also a bit expensive. Anyway I like the idea. $\endgroup$ – Damian Melniczuk Nov 7 '14 at 7:41
1
$\begingroup$

I have found the video tutorial/IPython notebook format really helped me get into the python ecosystem.

There were two tutorials at SciPy 2013 that cover sklearn (part 1 of 1st tutorial, github repo for notebooks).

Similar tutorials, from PyCon2012 and PyData2012, are out there for pandas but I don't have the rep to link searching for pandas tutorial on youtube should allow you to find them.

Since you mention Kaggle, I guess you will have seen their getting started with python tutorial for the titanic passenger dataset (I don't have the rep here to provide a link but searching for Getting Started with Python: Kaggle's Titanic Competition should get you there).

| improve this answer | |
$\endgroup$
1
$\begingroup$

There are really so many good resources now. If you want to stay away from textbooks, both O'Reilly Media and Packt Publishing offer much lighter but effective reading on a lot of great topics. These books are much more applied in practice.

As far as learning the languages go, Coursera, Udacity, Code Acadmey, and Code School have great tutorials. I would recommend taking a look at the following:

Coursera AI and Stats Courses

Udacity Data Science courses

| improve this answer | |
$\endgroup$
0
$\begingroup$

I can only recommend Advanced R by Hadley Wickham. I think it is at the same time incredibly rich in content and easy to read. You say you have zero knowledge in R, but I believe since you already have programming skills in other languages this book can complement very fruitfully any classical "R beginner manual" (for the latter see here).

| improve this answer | |
$\endgroup$
0
$\begingroup$

The Art of R Programming by Normal Matloff is a great way to find your way towards being an R user. I've recommended this book to several people navigating the tutorial / book universe and to my knowledge they've all stuck with it.

| improve this answer | |
$\endgroup$
0
$\begingroup$

The R Programming Wikibook is a nice collaborative handbook for R.

| improve this answer | |
$\endgroup$
0
$\begingroup$

If you prefer quick hands-on/interactive tutorials, below are my suggestions -

Python - codeacademy, Google Python Class

R - CodeSchool's 'Try R' and DataCamp (suggested above)

| improve this answer | |
$\endgroup$
0
$\begingroup$

I would recommend those materials:

| improve this answer | |
$\endgroup$
0
$\begingroup$

Also, Green Tea Press offers free books on related topics such as an intro to Python and using python with Probability and Stats.

| improve this answer | |
$\endgroup$

Not the answer you're looking for? Browse other questions tagged or ask your own question.