Course: Computing for Data Analysis

When I signed to course Computing for Data Analysis on Coursera (since mid of 2nd week I am doing Signature track which is more challenging). I did not expect that it should be so time consuming and so tough. It is. But this strictness doesn't allow me to go just over the surface, I need to go deep down and really learn R language. Which I actually good. I am lazy from nature, but who isn't :-).


First week was OK, just to come through 2 quizzes. Course includes every week 1 questionnaire and 1 programming assignment in this week both covered as quiz. So I did not study so much and I did it almost for 100%. So I signed to Signature track and thought its piece of cake.

It started from second week. Quiz was good and warmed me up for next phase. But with next phase - programming assignment which contains 3 parts with 8 outputs - I spent over 8 hours of programming to solve problem. Solution was good just minor issue doesn't allows me to get points from 2nd part of it fully. So, I stuck on it. I finalize it in 2 AM in the morning and rest 2 hours I finalized rest of tasks.

If you want to try it (I hope it doesn't breaks any rules), data is available here: specdata.zip. And you need to implement for example (2nd part of assignment) function based on this skeleton:

complete <- function(directory, id = 1:332) {
        ## 'directory' is a character vector of length 1 indicating
        ## the location of the CSV files

        ## 'id' is an integer vector indicating the monitor ID numbers
        ## to be used
        
        ## Return a data frame of the form:
        ## id nobs
        ## 1  117
        ## 2  1041
        ## ...
        ## where 'id' is the monitor ID number and 'nobs' is the
        ## number of complete cases
}

And your task is to count number of completely observed cases (any of observed cases cannot be NA) in each data file. And for sure there is example output which you can compare yours with.

I have third week before me. I didn't have time to look on lecture videos yet. And there is really big programming assignment contains 3 parts and 10 outputs. So I need to catch the train and look at it today morning. Deadline is soon this Sunday.

Last week I hope will be much easier than 2nd and 3rd, ideally similar to first one. Because it is really difficult to go to work and then study and program during whole night :-).

Anyway I want to make it for 80 % and better and currently I have 3 quizzes done with 29 points and 1 programming assignment with 20 points. Total is 100, so I will do my best to get as much as possible, but I am pretty sure that I will do more than 80%.

Finally, I can recommended this course. You will learn R language with full hands on practice. If you are considering this, don't and go to study it. Yes, you need to have some experiences with programming in any language, but just basics. It is more about your programmer thinking (not knowledge of specific programming language, because you will start with R from scratch) and understand and ability to solve problem which you never saw. Of course, do it in short time!