Python Forum
Data Science and Machine Learning sub-forum
Poll: Test a Data Science forum?
You do not have permission to vote in this poll.
No opinion
0%
0 0%
Lets try it
50.00%
3 50.00%
We dont need it
50.00%
3 50.00%
Total 6 vote(s) 100%
* You voted for this item. [Show Results]

Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Data Science and Machine Learning sub-forum
#11
Data science is a specific subset of computer science. It tends to be heavier on math and statistics, and be extremely technical even for experienced programmers or computer scientists. Machine learning, neural networks, and AI are often considered domains within data science. They're all things that, personally, I'm not qualified to be very helpful with, and haven't had the time to dive into the topics.
Reply
#12
(Jan-12-2018, 09:12 PM)metulburr Wrote: i am not in that area really, what exactly is defined as data science? The use of the libraries: NumPy, SciPy, matplotlib, Pandas, SymPy??

Good question, and not that easy to answer. Data Science as a field itself has nothing to do with Python or its libraries. But its techniques and tools are implemented (also) in Python, and very well at that. So Python (along with the libraries you mentioned) is a very widespread tool among practicioners of D.S. and its related fields (I don't really know the exact hierarchy of those). After all it is the relatively recent advancement (or accessibility?) of high performance computing that makes D.S. practical.
As for defnition, I'd go with a quote from Wiki Data Science page, it looks like a good starting point to me.
Quote:Data science is a "concept to unify statistics, data analysis and their related methods" in order to "understand and analyze actual phenomena" with data.[3] It employs techniques and theories drawn from many fields within the broad areas of mathematics, statistics, information science, and computer science, in particular from the subdomains of machine learning, classification, cluster analysis, data mining, databases, and visualization.

Use of the libraries you mentioned doesn't necessarily mean the code will be about D.S., machine learning, statistics...(except Pandas is pretty sure to be). But the opposite is very likely to be true. If code is about D.S., at least one of those libraries will very probably to be used. Smile
Reply
#13
I voted for "We don't need it" for this reason. DS covers such a broad spectrum of topics, eventually we'd feel compelled to create sub-forums. For awhile we seemed to get a lot of posts centered on genetics, that seems to have died down a bit. Other times we get a run on Natural Learning (which I suppose could be another sub-forum of Machine Learning), then there is a rash of data mining questions and so on. As was pointed out, we already have members posting questions in the wrong forums. An example would be GUI question posted in the General forum. So even if you don't look a the GUI forum,you're still going to run across GUI questions. As a mod, I try and move the thread(s) to the proper forum provided no one has responded yet. Right now, that is a relatively easy task, adding more forums and sub-forums would just tend to complicate matters, especially if it's an area for which I have no knowledge of where it belongs.

So as a mod, I agree: Simple is better than complex.

DISCLAIMER:
The views and opinions expressed by Moderator sparkz_alot may not be those of User sparkz_alot.
If it ain't broke, I just haven't gotten to it yet.
OS: Windows 10, openSuse 42.3, freeBSD 11, Raspian "Stretch"
Python 3.6.5, IDE: PyCharm 2018 Community Edition
Reply
#14
Quote:I try and move the thread(s) to the proper forum provided no one has responded yet.
I move them regardless of how many posts. Responders will still get the link back to the proper post if they are subscribed. IF not they have other methods to finding it like "My discussions" user link, etc. I would more worry about the thread being in the proper location for Google SEO, and future searchers.

(Jan-13-2018, 02:26 PM)sparkz_alot Wrote: The views and opinions expressed by Moderator sparkz_alot may not be those of User sparkz_alot.
Thats kinda the same thing i am thinking. Im OK with splitting it, but i know its going to create more of a work-load for us.

Quote:DS covers such a broad spectrum of topics, eventually we'd feel compelled to create sub-forums.
I would assume that all topics considered data science would just get funneled to that one forum then.

The other questions i have is if we keep the data science forum. Are we suppose to look through gen coding and move as many threads to its new location or just leave them? Not sure how many.
Recommended Tutorials:
Reply
#15
That's exactly what interests me. I hope you will open a new subforum.
Reply
#16
For all of the questions we've answered to date, the current set of sub-forums has always, i believe, been adequate. We've always had machine learning, it has only recently been renamed to machine learning. We used it extensively in telecommunications, and in spectroscopy as well (my two fields).

That being said, perhaps this one exception deserves more thought, what with AI programming really exploding, and growing in use exponentially.
Reply
#17
its kinda at a stalemate right now.

you can still indulge in conversations pertaining to what interests you even though there is not a specific forum for it.
Recommended Tutorials:
Reply
#18
Since the new forum has been up, I believe this is the first request of this type, so it doesn't seem to be a pressing issue.
Reply


Possibly Related Threads…
Thread Author Replies Views Last Post
  Proposing "Data Science" sub-forum (again) micseydel 15 7,542 Dec-26-2018, 08:08 PM
Last Post: micseydel
  Does the forum need a forum category ? Yoriz 4 6,289 Sep-18-2016, 08:16 PM
Last Post: Kebap

Forum Jump:

User Panel Messages

Announcements
Announcement #1 8/1/2020
Announcement #2 8/2/2020
Announcement #3 8/6/2020