/Moneyball-Data-Analysis

Primary LanguageJupyter Notebook

Moneyball-Data-Analysis

This repository explores the moneyball theory & other baseball statistics to predict if a team makes the playoffs.

data folder:

  • contains data initialization steps, including loading dataset & adding more data via API.

extra folder:

  • contains attributes to obtain statistics from API and a jupyter icon.

linear model simulations folder:

  • contains models on moneyball statistics and another on more statistics.
  • explores variable weights and simulates models during different eras of baseball.

package folder:

  • contains modules and libraries used within the repository.

xgboost simulation

  • contains XGBoost model.
  • explores different accuracy metrics and simulates model during different eras of baseball.

how to use

  • set up the data with data_initialization.py.
  • run simulations