Any Data Engineers or Web Designers Interested in Working on UT Football Projects?

#27
#27
@DiderotsGhost This is exactly what I do at work. I'd also love to get involved with a football-related project. The only problem is I'm working for two startups right now and trying to build a python framework for SOA in my spare time. Definitely interested in talking, but I don't know how much time I could devote to it. At the very least, we should meet... always good to have connections.

Edit - Just noticed you said web designers. That's not really my bread and butter, but I do some of that. I'm an enterprise/solutions architect.
 
#28
#28
I just thought I'd let you know, while I would love to help, I still struggle with Microsoft Excel from time to time. I would probably just get in the way. It sounds like an awesome project though!
 
  • Like
Reactions: goldenvol
#29
#29
DiderotsGhost said:
I always thought you could PM people here with the redesign, but maybe I was wrong. I'm not seeing a way to do it either.
Click to expand...
Build some sort of composite score based on ranking of recruiting services and stats for both QBs and WRs. Then do the same only based on OL rankings b/c they don't have stats. Make sure to consider looking at past WRs and OL too for a few years before each QB since they may play together despite not being in the same class.
 
#33
#33
DiderotsGhost said:
In the real world, I'm a Data Scientist. I have a few Tennessee related projects I want to work on. Curious if anyone out there might be interested in helping?

(*) Data viz website. First one is a data visualization website for Tennessee. It's already built it out somewhat, but still messing around with D3 to try to make it work well. Nevertheless, my web design could probably use some work. I'm more of a Python data guy than a web designer. I also admit on a basic level, I hate web design.

(*) Predicting Best QBs. Second project is machine learning algorithm that would use high school stats to try to project how good a college QB would be. I've started working on this, but I'm struggling with ideas on how to automate some of the data collection; it's been very cumbersome thus far. My secret reason for building this is to see how a machine learning model would project our inexperienced QBs next season (Shrout, Maurer, Bailey, or even Hill); also to test out the idea that Bailey is underrated in the ratings services (an opinion many here have; I'm agnostic on it right now).

This is a passion project / hobby; don't really expect us to generate boatloads of money or anything, but maybe if we got things going, we could make a little ad revenue.

Let me know if you want to know more / have other ideas / have interest. I already have some samples of the D3 that can be shared for those that want to see; just not up on website yet.
Click to expand...
I have a few ideas on the qb thing but don’t completely understand how it works. Don’t want to make a fool of myself making uneducated suggestions. Needless to say I’d be interested in learning more
 
#34
#34
DiderotsGhost said:
In the real world, I'm a Data Scientist. I have a few Tennessee related projects I want to work on. Curious if anyone out there might be interested in helping?

(*) Data viz website. First one is a data visualization website for Tennessee. It's already built it out somewhat, but still messing around with D3 to try to make it work well. Nevertheless, my web design could probably use some work. I'm more of a Python data guy than a web designer. I also admit on a basic level, I hate web design.

(*) Predicting Best QBs. Second project is machine learning algorithm that would use high school stats to try to project how good a college QB would be. I've started working on this, but I'm struggling with ideas on how to automate some of the data collection; it's been very cumbersome thus far. My secret reason for building this is to see how a machine learning model would project our inexperienced QBs next season (Shrout, Maurer, Bailey, or even Hill); also to test out the idea that Bailey is underrated in the ratings services (an opinion many here have; I'm agnostic on it right now).

This is a passion project / hobby; don't really expect us to generate boatloads of money or anything, but maybe if we got things going, we could make a little ad revenue.

Let me know if you want to know more / have other ideas / have interest. I already have some samples of the D3 that can be shared for those that want to see; just not up on website yet.
Click to expand...
Meant to tell you I’m no engineer but I use a more in-depth system than the services to rate qbs if you’re interested. Don’t mind sharing or providing examples. Only takes a few min after watching real game tape. If the system works for your project it may at least provide a platform.
 
#36
#36
No but i can make sure that your poop goes the direction that is supposed to and not in your house and other various civil engineering duties.
 
#38
#38
I'm an R guy myself and have done some machine algorithm work, so I'm thinking less about how to get the data and more about what to do with it once you've got it. What metrics are you going to use to define success? W-L, efficiency, yards, touchdowns? You'd also need to categorize and account for the type of offense they ran in high school compared to what we're running (or other college campuses if it were to expand). You may have thought about this already and have it mapped out, but you'd need both high school and college stats to make for an effective algorithm, and the more data you pull in the better the algorithm gets. I can't help too much with the web scraping/API portions, but if it's in a database somewhere I can do a lot with it.

IF there's a way to get this to work and it shows accurate results, there could be mega $$ to be made. There's always going to be intangibles that can't be picked up in stats, but this could be also be used for coaches too. You could pull any quarterback that's played under Chaney and measure year to year growth in certain areas, and compare it that of other coaches if you wanted. My guess is that certain metrics (efficiency/completion percentage) won't change a ton between high school and college after taking offensive system into account, but you never know. It'd be extremely interesting to look at.

Random thought stream of possible variables you'd need to start to get a full picture:
High School:
- Years started
- Level of play (3A, 6A, etc)
- State (Higher competition at lower levels in states like Florida, Texas, etc.)
- Measurements (Height mostly, weight maybe)
- Stats (Yards, Touchdowns, interceptions, sacks, rushing yards, fumbles, anything that's available)
- Type of system
- Injuries?
-W-L Record
- 3rd Down stats
- Championships

College:
- College class (Fr, So, etc)
- Conference
- Individual school
- Stats & 3rd down stats
- Measurements
- Type of system/OC/Qb coach
- W-L Record
- Championships/Bowl wins
 
#39
#39
DiderotsGhost said:
In the real world, I'm a Data Scientist. I have a few Tennessee related projects I want to work on. Curious if anyone out there might be interested in helping?

(*) Data viz website. First one is a data visualization website for Tennessee. It's already built it out somewhat, but still messing around with D3 to try to make it work well. Nevertheless, my web design could probably use some work. I'm more of a Python data guy than a web designer. I also admit on a basic level, I hate web design.

(*) Predicting Best QBs. Second project is machine learning algorithm that would use high school stats to try to project how good a college QB would be. I've started working on this, but I'm struggling with ideas on how to automate some of the data collection; it's been very cumbersome thus far. My secret reason for building this is to see how a machine learning model would project our inexperienced QBs next season (Shrout, Maurer, Bailey, or even Hill); also to test out the idea that Bailey is underrated in the ratings services (an opinion many here have; I'm agnostic on it right now).

This is a passion project / hobby; don't really expect us to generate boatloads of money or anything, but maybe if we got things going, we could make a little ad revenue.

Let me know if you want to know more / have other ideas / have interest. I already have some samples of the D3 that can be shared for those that want to see; just not up on website yet.
Click to expand...
Please tell me what the difference in a Data Scientist and a Statistician is? By statistician, I mean someone that analyzes and manipulates data. I know that the knee jerk will be that this is the wrong definition but that is what an entire group of people were called where I work before THEY termed themselves Data Scientists.
 
#40
#40
82_VOL_83 said:
Please tell me what the difference in a Data Scientist and a Statistician is? By statistician, I mean someone that analyzes and manipulates data. I know that the knee jerk will be that this is the wrong definition but that is what an entire group of people were called where I work before THEY termed themselves Data Scientists.
Click to expand...

Data Scientists and Statisticians are similar. Biggest difference IMO is that Data Scientists are doing thing programmatically and there's often an engineering component.

For instance, you can be a Statistician who works in Excel or uses another commercial program like SPSS. A Data Scientist likely works in either Python, R, Scala, or even C++. Also a Data Scientist might build an app that automates a machine learning model, whereas a Statistician might not know how to do that.

If you search the web, you'll find some more pretentious answers out there, but to me, that's the gist of it. A Data Scientist is a Statistician who uses a programming language like Python or R, and can do some engineering.
 
  • Like
Reactions: VolFan_N_NC, DC_Vol and 82_VOL_83
#42
#42
jwilliams said:
@DiderotsGhost This is exactly what I do at work. I'd also love to get involved with a football-related project. The only problem is I'm working for two startups right now and trying to build a python framework for SOA in my spare time. Definitely interested in talking, but I don't know how much time I could devote to it. At the very least, we should meet... always good to have connections.

Edit - Just noticed you said web designers. That's not really my bread and butter, but I do some of that. I'm an enterprise/solutions architect.
Click to expand...

Totally understandable. That's my big problem is that I'm slammed with too many things :)

Though, I said web designers AND data engineers. Honestly, I'm finding collecting the data the most difficult part right now. Probably enough resources on college to do it. (If nothing else, I can copy and paste stats in a clean format and turn them into a csv file). High school stats are a giant mess, though.
 
#43
#43
DiderotsGhost said:
Totally understandable. That's my big problem is that I'm slammed with too many things :)

Though, I said web designers AND data engineers. Honestly, I'm finding collecting the data the most difficult part right now. Probably enough resources on college to do it. (If nothing else, I can copy and paste stats in a clean format and turn them into a csv file). High school stats are a giant mess, though.
Click to expand...

I can take a look at that... what is/are the best source(s) for the high school data?
 
#45
#45
I can help with this, well versed in SQL, Python, R. You can email me at sgrewal1988@gmail.com with more info. Quick idea: ESPN does a NBA projection for college players, and they separate players into predictive categories. They use All-Star, Starter, Role Player. They eventually added Superstar and Bust. You could do this for these Quarterbacks with % breakdowns for each. Who's the most likely All-Star in the 2017 NBA draft class?
 
  • Like
Reactions: VolFan_N_NC, DiderotsGhost and Willie Hutch
#46
#46
I have an interest in helping with this. I'm a web developer (currently doing mainly frontend stuff), a bit more on the junior / lower intermediate level

I haven't messed with d3 much, but use javascript/react daily and know bits of python (and some django if you're using that on the backend)

in the future, would you be putting this project on github or something for people to contribute to?

This seems like a cool thing to collaborate on with fellow vols/developers
 
  • Like
Reactions: DiderotsGhost
#47
#47
Threw some code together to scrape every statistic for every position in football from 04 - present. Running it now, seems to be working properly
 
  • Like
Reactions: DiderotsGhost
#49
#49
VolFan_N_NC said:
I’m always up for networking and helping out fellow Vols fans. My expertise is in IT so if you are ever looking for a new job I am always willing to help out.
Click to expand...

Maybe we should set up a group somewhere. Might be a cool way to exchange ideas. I was going to do a Github repo, which is good for sharing code, but not quite as good for communication.
 
New posts
You must log in or register to reply here.

VN Store



Back
Top