We want to build a Machine Learning Algorithm that given a randomly selected pitch thrown in an MLB game, it can appropriately identify what type of pitch was thrown. We are going to do this by collecting data from baseball.savant.mlb.com. We are going to gather a csv of every pitch that has been thrown through the 2023 season in order to build our algorithm.
Welcome! This is your shared repository for you and your group members for the Final Project. The directory structure will help make the deliverables clear and centralize your submission. Following the structure and keeping your repo up-to-date is important for us to able to effectively advise you. You may add additional structure, but please be sure to use the existing elements as defined here:
Upload your proposal pdf in the planning directory. Use the README in that directory to define, and update your timeline. Each week, you will provide a summary of progress on Monday evening (i.e. it should be available for viewing any time on Monday). For each week, define:
- What goals/tasks you accomplished from the previous week
- What goals you did not accomplish (and an explanation of the road block)
- Any items you need assistance with
In the paper/ directory, you will find the template for your final project paper. We recommend using the provided template for your final paper. If you would like to use OverLeaf or other IDE, please upload my provided files to ensure consistency. We must be able to compile your TeX files, so be sure to include all source material (including images) in your final submission, and please test compilation on the CS lab machines (the included Makefile should simplify this process).
If you choose not to use LaTeX for your paper, it is up to you to make sure your paper is well-formated and can produce a PDF format version. Both the "original" document and the PDF should be included in your repository.
In the presentation/ directory, place all files related to your project presentations. If you use GoogleDocs, you can share the document with the instructors by email, but please also download the slides here as a PDF.
DO NOT COMMIT LARGE DATA FILES TO YOUR REPO. Please discuss with us first efficient ways to manage your data sets. We will send instructions on how to submit your project data that is needed to replicate your results. Adding small toy example sets to your repo may be alright, but consult the instructors if in any doubt.