Skip to content

nachikethinge01/Data-Science-I-Project

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

30 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Data-Science-I-Project

A Machine Learning project to predict NBA players salaries based on their stats.

The goal was to create a model and predict what salary should be given to the NBA players based on their statistics in the NBA.

The project's main objective was to conduct an exploratory data analysis and develop models that are used in predicting how much salary a player might recieve. The analysis and the models support each other in ensuring that the prediction is nearly accurate. The data sets used in this project are a training data set, which has a model of 353 players, and testing data set with 89 players

Install

This project requires Python and the following Python libraries installed:

You will also need to have software installed to run and execute a Jupyter Notebook

Data Source:

https://www.kaggle.com/rikdifos/nba-players-salary-prediction/data?select=NBA_season1718_salary.csv https://www.kaggle.com/rikdifos/nba-players-salary-prediction/data?select=Players.csv

Analysis Steps:

  • Exploratory Data Analysis on R Studio
    • Used GGPlot2 to create creative charts analyzing trends in response and predictor variables.

Model Comparison and Conclusion:

Overall, the results we obtained are significant because this was the most important part of our analysis. To understand the efficiency of the models, we used the R-Squared method to understand how much of the data is explained by the model built. The R-Squared values we got for each of the models were:

  • Random Forest Regressor: 61.4%
  • K-Nearest Neighbor: 61.8%
  • Linear Regression: 40.4%

Presentation Slides: https://docs.google.com/presentation/d/1st9TtZXjxPKKNuk7RQ2SXQ-DgDUPvY5SCjUa3xwl6vo/edit?usp=sharing

About

A Machine Learning project to predict NBA players salaries based on their stats.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors