Exploratory Data Analysis in Python (Pandas)

borderraux

Forums

Looking for a good source of functions used in EDA with Python (using Pandas library or any other). 
Basically my aim is to be able to derive quickly from a large set of data (usually over 20 000 records) the following information:
- what data is about
-main trends and patterns
Does anyone have any examples?

Brian Element Tue, 02/19/2019 - 11:06

Hello borderraux,

Unfortunately I don't have anything for you.  I keep trying to spend more time with Python but I have too many other things on the go.  Hopefully I will have more time in the future.  If you do find anything I hope you will share.

Brian

klmi Fri, 06/28/2019 - 03:56

From my point of view there are more books and tutorials on youtube about that subject than I have time to read/view. But you will need some basic Python skills because the language is developing fast. Often older code snippets need some modifications f.e.: print "Hello" doesn't work in newer versions because you need to set brackets: print("Hello").
Maybe www.packtpub.com is a good source to find eBooks regarding Python, data analysis and machine learning. When registering you will find some free books and also a daily free book or video tutorial. Another good source are books from O'Reilly. They sometimes offer free books too.

cmkenny Fri, 09/02/2022 - 05:24

Hi - I've probably come a bit late with this but I have found Datacamp.com an excellent tool for learning Python. I've been doing it for just over a year and have learned enough to start seeing benefits in my job and applying it to more complicated tasks (e.g. I am currently building a script to scrape number plates from a load of Excel files, send to the DVLA via an API, return CO2 emissions and estimate company vehicle emissions.  A year ago I would not have had a clue to where to even start with this).