Research Artifacts for Machine Learning DSML Baseball Case Study

dc.contributor.author	Koseler, Kaan
dc.contributor.author	Stephan, Matthew
dc.date.accessioned	2018-04-12T19:34:52Z
dc.date.available	2018-04-12T19:34:52Z
dc.date.published	2018-04-12
dc.description.abstract	This entry contains all the artifacts created and data utilized in our research on developing a Machine Learning DSML, models, and software for a Baseball Case Study.	en_US
dc.identifier.uri	http://hdl.handle.net/2374.MIA/6234
dc.rights	Attribution 3.0 United States (CC BY 3.0 US)	*
dc.rights.uri	http://creativecommons.org/licenses/by/3.0/us/	*
dc.title	Research Artifacts for Machine Learning DSML Baseball Case Study	en_US
dc.type	Other	en_US

Files

Now showing 1 - 4 of 4

Name:: ML_DSML_Papyrus_Project.zip
Size:: 2.19 MB
Format:: Unknown data format
Description:: This file contains our metamodel, instance models, code generation engine, generated code, and a readme file. The .zip and folder as a whole is (can be opened as) a Papyrus project.

Name:: 2016_Training_COMBINED.csv
Size:: 38.08 MB
Format:: Unknown data format
Description:: The 2016 training data pulled from Baseball Savant. Play-by-play data for pitchers from the Yankees, Reds, Mets, and Blue Jays.

Name:: 2017_Test_COMBINED.csv
Size:: 41.51 MB
Format:: Unknown data format
Description:: The 2017 test data pulled from Baseball Savant. Play-by-play data for pitchers who were on the Yankees, Reds, Mets, and Blue Jays in 2016 (the year prior).

Name:: Data Analysis.ipynb
Size:: 896.94 KB
Format:: Unknown data format
Description:: The iPython notebook that was used to clean and analyze the 2016/2017 data.

Now showing 1 - 1 of 1