I'm doing Data Analyst nanodegree from Udacity. I'm confused between the difference even after going through the lecture a few times.
$\begingroup$
$\endgroup$
1
-
$\begingroup$ Could you give us a sentence or paragraph from a lecture with each example? It's hard to say exactly what someone meant without more context. Tidy data typically means well organized and not needing lots of preprocessing to get it into a format you can use, whereas good quality data might mean not containing errors or containing strong predictive information. $\endgroup$– ImranCommented Aug 18, 2018 at 3:09
Add a comment
|
1 Answer
$\begingroup$
$\endgroup$
Let me try to explain by intuitively. First let me take the easy one.
Data being tidy
As per definition Tidy means Arranged in Order, Neat, Uncluttered. All of these explain the physical aspects of the data representation. For example, data arranged in proper columns, with good headings, with relevance etc. You can think of this being syntactic in nature
Good Quality Data
This refers to actual data elements in the file. Like not having too many blank (missing) values. Every column having proper data types. Data without special (unreadable) characters. Properly encoded. Not having too much unstructured data. You can think this as the semantics of the data.
Hope this helps