These are chat archives for FreeCodeCamp/DataScience
discussion on how we can use statistical methods to measure and improve the efficacy of http://freeCodeCamp.com
@XpandGroup thanks for sharing!
@PunkDado welcome! Let us know if there's anything in particular you're interested in learning about :smile:
@vidushi2806 hello and welcome!
@willworth hello! Sounds like an awesome meet up. CSV is fairly standard, and so is JSON. They are generally interchangeable (i.e. you can put the same data into CSV and JSON), however, CSV is designed for tabular data (it is rectangle/square), versus JSON, which doesn't have to be and can be more flexible than CSV in terms of its schema or how it is structured.
erictleung sends brownie points to @xpandgroup and @punkdado and @vidushi2806 and @willworth :sparkles: :thumbsup: :sparkles:
Great there are lots of people willing to contribute! We could possibly enjoy the same shared success at last year.
Please feel free to suggest ideas either here on in this channel or in the issue page of the current project:
In 2016 we discussed advances of the project on this channel or through opened issues in the Github account where the project resided.
That year, @QuincyLarson suggested several questions for people to go, tagged as
Question as a guidance for what he thought were interesting questions to look at. This was not a compulsory list though: people could work on what they wanted, in teams or alone.
If you want to know how the issue list worked, check the issues list of last year.
We have been inviting FCC users to work those ideas also in Kaggle: the data will be likely the same cleaned file. If you have plans to work on Kaggle, we will be happy to help you here or in Kaggle to deliver a Top Quality and Informative chart; just let us know.
Between the most active users last year you could find @SamAI-Software and @krisgesling. They both and specially Sam worked a nice final product about the project that you can see here. This projected received support from Quincy and people at CodeNewbie.
There were other initiatives around the data. An important one to mention is this one, carried out by an external senior analyst that found the data in Kaggle.
Please let us know how to help you. I advice to have a look at the data now and see if there is something that @erictleung should also take in consideration.
Maybe I could collaborate with FCC using my professional marketing skills.
sounds great! I will contact you soon?
evaristoc sends brownie points to @xpandgroup :sparkles: :thumbsup: :sparkles:
@evaristoc make an issue to discuss possible contributions? Like analyses or such? Or are you talking about contributions to cleaning?
I've done the best I could with the time and have made a PR to add a single data set to the repository freeCodeCamp/2017-new-coder-survey#1
People interested in how I cleaned the data using the programming language R can be found here https://github.com/erictleung/2017-new-coder-survey. So if you have any questions or concerns with parts of the data, let me know.
@padf00t welcome! Two places I'd look at are R for Data Science (it goes through the whole process of data science from data viz to exploration) and the UCI Machine Learning Repository to find data sets to explore.
To get going with data science, you need to be curious and ask questions of the data set and see if you can answer those questions. Let us know if you have any other questions. Good luck! :+1:
padf00t sends brownie points to @erictleung :sparkles: :thumbsup: :sparkles: