library(readxl)
library(tidyverse)
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.0     ✔ readr     2.1.4
## ✔ forcats   1.0.0     ✔ stringr   1.5.0
## ✔ ggplot2   3.4.1     ✔ tibble    3.1.8
## ✔ lubridate 1.9.2     ✔ tidyr     1.3.0
## ✔ purrr     1.0.1     
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
## ℹ Use the ]8;;http://conflicted.r-lib.org/conflicted package]8;; to force all conflicts to become errors
library(janitor)
## 
## Attaching package: 'janitor'
## 
## The following objects are masked from 'package:stats':
## 
##     chisq.test, fisher.test
library(ggplot2)
march_madness_rebounds_data <- read_excel("march madness rebounds data.xlsx") %>%
  clean_names()
march_madness_rebounds_data
## # A tibble: 340 × 8
##    team               year off_rebounds x3_poi…¹ assists turno…² made_…³ won_c…⁴
##    <chr>             <dbl>        <dbl>    <dbl>   <dbl>   <dbl> <chr>   <chr>  
##  1 Akron              2022          330    0.318     396     396 No      No     
##  2 Alabama            2022          432    0.309     467     467 No      No     
##  3 Arizona            2022          388    0.356     677     449 No      No     
##  4 Arkansas           2022          363    0.3       462     429 Yes     No     
##  5 Auburn             2022          416    0.32      480     384 No      No     
##  6 Baylor             2022          416    0.304     512     416 No      No     
##  7 Boise St.          2022          340    0.333     408     408 No      No     
##  8 Bryant             2022          403    0.296     434     434 No      No     
##  9 Cal St. Fullerton  2022          310    0.312     341     372 No      No     
## 10 Chattanooga        2022          374    0.348     442     374 No      No     
## # … with 330 more rows, and abbreviated variable names ¹​x3_point_percent,
## #   ²​turnovers, ³​made_elite_8, ⁴​won_championship
ggplot(march_madness_rebounds_data, aes(x = off_rebounds, y = x3_point_percent, shape = made_elite_8, color = won_championship)) + geom_point() +
  facet_wrap(~ year) +
  labs(title = "March Madness Teams and Their 3 Point % and Offensive Rebounds", 
       x = "Offensive Rebounds", y = "3 Point Percentage", color = "Championship Winner", shape = "Elite 8")

mme8 <- march_madness_rebounds_data %>%
  filter(made_elite_8 == "Yes")
mme8
## # A tibble: 40 × 8
##    team            year off_rebounds x3_point_…¹ assists turno…² made_…³ won_c…⁴
##    <chr>          <dbl>        <dbl>       <dbl>   <dbl>   <dbl> <chr>   <chr>  
##  1 Arkansas        2022          363       0.3       462     429 Yes     No     
##  2 Duke            2022          374       0.364     578     340 Yes     No     
##  3 Houston         2022          442       0.348     578     374 Yes     No     
##  4 Kansas          2022          377       0.353     524     425 Yes     Yes    
##  5 Miami FL        2022          264       0.35      462     330 Yes     No     
##  6 North Carolina  2022          363       0.364     495     396 Yes     No     
##  7 Saint Peter     2022          330       0.312     360     420 Yes     No     
##  8 Villanova       2022          330       0.36      396     330 Yes     No     
##  9 Arkansas        2021          334       0.339     419     368 Yes     No     
## 10 Baylor          2021          309       0.418     409     298 Yes     Yes    
## # … with 30 more rows, and abbreviated variable names ¹​x3_point_percent,
## #   ²​turnovers, ³​made_elite_8, ⁴​won_championship
ggplot(mme8, aes(x = off_rebounds, y = x3_point_percent, color = won_championship, shape = won_championship)) +
  geom_point() +
#facet_wrap(~ year) +
  labs(title = "March Madness Elite 8 and Their 3 Point % and Offensive Rebounds", 
       x = "Offensive Rebounds", y = "3 Point Percentage", color = "Championship Winner") +
  guides(shape = "none")

ggplot(march_madness_rebounds_data, aes(x = off_rebounds, y = x3_point_percent, size = made_elite_8, color = won_championship)) + geom_point() +
  labs(title = "March Madness Teams and Their 3 Point % and Offensive Rebounds", 
       x = "Offensive Rebounds", y = "3 Point Percentage", color = "Championship Winner", size = "Elite 8")
## Warning: Using size for a discrete variable is not advised.

ggplot(march_madness_rebounds_data, aes(x = assists, y = turnovers, shape = made_elite_8, color = won_championship)) + geom_point() +
  facet_wrap(~ year) +
  labs(title = "March Madness Teams and Their Turnovers and Assists", 
       x = "Assists", y = "Turnovers", color = "Championship Winner", shape = "Elite 8")

ggplot(mme8, aes(x = assists, y = turnovers, color = won_championship)) + geom_point() +
  facet_wrap(~ year) +
  labs(title = "Elite 8 Teams and Their Turnovers and Assists", 
       x = "Assists", y = "Turnovers", color = "Championship Winner")

ggplot(march_madness_rebounds_data, aes(x = assists, y = off_rebounds, size = made_elite_8, color = won_championship)) + geom_point() +
  #facet_wrap(~ year) +
  labs(title = "March Madness Teams and Their Offensive Rebounds and Assists", 
       x = "Assists", y = "Offensive Rebounds", color = "Championship Winner", shape = "Elite 8")
## Warning: Using size for a discrete variable is not advised.

ggplot(mme8, aes(x = assists, y = off_rebounds, color = won_championship)) + geom_point() +
  facet_wrap(~ year) +
  labs(title = "Elite 8 Teams and Their Offensive Rebounds and Assists", 
       x = "Assists", y = "Offensive Rebounds", color = "Championship Winner")