Hello everyone. Edits to the project and this post
I went ahead and cleaned the data to the best of my ability. Any lesson with 1000 or 2000 at the front has that trimmed (i.e. 1000302 becomes 302) and any lessons that are length of four get the zero in index position 1 removed (i.e. 3002 becomes 302). It was really interesting to learn how to do this in Power BI. So interesting that I documented the steps.
Dataquest steps Data Cleaning.docx.pdf (15.9 KB)
I also made a video that I can’t upload but here’s the pdf of the updated version.
Dataquest Survey Report.pdf (1.1 MB)
So that makes some of the stuff in the rest of the post irrelevant, but I thought I’d leave it in. Feel free to DM if you have any questions.
End of edits.
Here is the last project for Analyzing Data with Microsoft Power BI, Building a BI App. It takes a look at Dataquest course/lesson net promoter scores and completion rates. Pretty interesting stuff and I am very happy with it. The dataset has some notable quality issues and I’ve taken this as far as I want until I can address them.
- There are no names for any of the courses or lessons. That really limits context. Are the popular courses for Python or R? Data science track, data analysis track, or other?
- Many of the entries are missing the lesson id and many of the lessons are missing the nps score, the completion rate, or both.
- Lastly, there are many lesson ids in the completion rate table that are not in the main course/lesson table. Are these trial classes that were offered? Or is the data corrupted (i.e. lesson 1001 isn’t a test version of lesson 101, but is actually supposed to be lesson 101)?
If any of these issues could be addressed it would make the project dramatically more interesting. Also, I think it could fix some of the small technical problems. Maybe someone from Dataquest can get back to me about the dataset?
I mention all this in the “Project Intro” page of the report. For what it’s worth, the initial page is “Intro” when opening the report online in Power BI Service. Lastly, I’m planning on doing a complete procedure document for how I did the project and a video showing the different pages, function of filters, etc. I’ll add them to this post when done, but it’ll be a couple weeks I think.
I’d appreciate any feedback, though I still don’t see a way to attach .pbix files to these posts. So you’ll have to simply look at the .pdf and images unless you want to give me an email address and I’ll gladly share the report with you.
Thank you.
Project Intro Page
Intro Page
Intro Page Showing Selection
NPS Page
Completion Rate Page
Completion Rate Page Showing Selection
Dataquest Report.pdf (1.4 MB)
Amazing job, thanks for sharing it with us! 