Assignment 7 - Jackson

Author

Introduction

I am going to be performing an analysis on seasonal NBA player data, provided by scraping the Basketball Reference website. This data records information about each player in the NBA from 2023-2025, along with that players individual statistics from each season they have played in that time period. Each row is a player (there are instances of a player getting traded and their statistics from each team they were on that season being totaled * Team label is 2TM) and a season and each column is a statistic or descriptive information specific to each player (ex: awards won that year, age, team played for in that season). You can learn more about this data at this link: NBA 2023-2025 Player Statistics

Research Questions

Question 1) Who are the top 3 players that have improved offensively (PTS, AST) from 2024 –> 2025

Question 2) Does a players position relate to total rebounds per game?

Question 3) How does age affect player offensive performance? (PTS, AST)

Question 4) Who are the best 10 all around players from 2025? (PTS, AST, REB)

Question 5) Which players are the biggest liabilities to their teams? (Top 5 in combined avg. turnovers and personal fouls)

These questions are interesting to me as the NBA playoffs are going on currently, and this information could impact how I bet on these games/individual players (I am over 21 and recommend you gamble responsibly)

How will I accomplish this?

I intend to answer these questions through first scraping the Basketball Reference website seasonal player data, then as needed, create separate tables and visualizations as needed for each question to display a clear answer to each question that I have posed.

Analysis

Question 1) Who are the top 3 players that have improved offensively (PTS, AST) from 2024 –> 2025

Above I created a column chart that shows the top 3 players in terms of improvement in combined PTS & AST from 2024 to 2025. Quientin Grimes is the most improved, with Toppin and Jerome significantly behind.

Question 2) Does a players position relate to total rebounds per game?

I created a bar chart as seen above that shows that as one would assume, Centers (which is typically played by the tallest player in the game) is the highest average in terms of rebounds per game. Then, Power Forwards who are around 1 fewer (on average) per game, and about another rebound fewer is Small Forwards. Point guards and Shooting Guards are both about the same, averaging just under a half fewer rebounds per game than Small Forwards. This shows that position does relate to average rebounds per game.

Question 3) How does age affect player offensive performance? (PTS, AST)

There is clearly one outlier in this visual, which is influenced by LeBron James specifically (aka 2nd best ever). Those who are in either in their late 20s and early 30s are not significantly different in terms of offensive production, but other than our LeBron outlier, age does impact a players ability to be of impact on the offensive side of the ball.

Question 4) Who are the best 10 all around players from 2025? (PTS, AST, REB)

The above column chart shows the top 10 players in PTS + AST + REB from 2025 in order from 1-10.

Question 5) Which players are the biggest liabilities to their teams? (Top 5 in combined avg. turnovers and personal fouls)

The listed players are the top 5 in combined personal fouls and turnovers per game. This is a negative influence on the team, however, all of these players are considered to be “stars” who elevate their team. This shows that these players are able to overcome their “negative” attributes, however, these players also are considered to not be overly successful (for the most part) in the playoffs, so maybe this is a part of why.

--- title: "Assignment 7 - Jackson" author: "BJ" toc: true # Generates an automatic table of contents. format: # Options related to formatting. html: # Options related to HTML output. code-tools: TRUE # Allow the code tools option showing in the output. embed-resources: TRUE # Embeds all components into a single HTML file. execute: # Options related to the execution of code chunks. warning: FALSE # FALSE: Code chunk sarnings are hidden by default. message: FALSE # FALSE: Code chunk messages are hidden by default. echo: FALSE # FALSE: Show no code in the output. --- ## Introduction I am going to be performing an analysis on seasonal NBA player data, provided by scraping the Basketball Reference website. This data records information about each player in the NBA from 2023-2025, along with that players individual statistics from each season they have played in that time period. Each row is a player (there are instances of a player getting traded and their statistics from each team they were on that season being totaled \* Team label is 2TM) and a season and each column is a statistic or descriptive information specific to each player (ex: awards won that year, age, team played for in that season). You can learn more about this data at this link: [NBA 2023-2025 Player Statistics](https://myxavier-my.sharepoint.com/:x:/g/personal/jacksonw6_xavier_edu/EfEJrfwPxr9BgPNZ3zSUGjsBEliGL6mFeqltfc2OBbX5CA?e=Yv6bFF) ## Research Questions **Question 1)** Who are the top 3 players that have improved offensively (PTS, AST) from 2024 –\> 2025 **Question 2)** Does a players position relate to total rebounds per game? **Question 3)** How does age affect player offensive performance? (PTS, AST) **Question 4)** Who are the best 10 all around players from 2025? (PTS, AST, REB) **Question 5)** Which players are the biggest liabilities to their teams? (Top 5 in combined avg. turnovers and personal fouls) These questions are interesting to me as the NBA playoffs are going on currently, and this information could impact how I bet on these games/individual players (I am over 21 and recommend you gamble responsibly) ## How will I accomplish this? I intend to answer these questions through first scraping the Basketball Reference website seasonal player data, then as needed, create separate tables and visualizations as needed for each question to display a clear answer to each question that I have posed. ```{r} library(tidyverse) # for all the tidy things library(skimr) # for better summary statistics ``` ```{r} all_season_stats <- read_csv("https://myxavier-my.sharepoint.com/:x:/g/personal/jacksonw6_xavier_edu/EfEJrfwPxr9BgPNZ3zSUGjsBEliGL6mFeqltfc2OBbX5CA?download=1") ``` ## Analysis **Question 1)** Who are the top 3 players that have improved offensively (PTS, AST) from 2024 –\> 2025 ```{r} # Calculate average PTS and AST for 2024 player_2024 <- all_season_stats %>% filter(Season == 2024) %>% group_by(Player) %>% summarise( PTS_2024 = PTS, na.rm = TRUE, AST_2024 = AST, na.rm = TRUE) # Calculate average PTS and AST for 2025 player_2025 <- all_season_stats %>% filter(Season == 2025) %>% group_by(Player) %>% summarise( PTS_2025 = PTS, na.rm = TRUE, AST_2025 = AST, na.rm = TRUE) # Merge the two data frames based on Player column player_improvement <- merge(player_2024, player_2025, by = "Player") # Calculate the total improvement in PTS and AST player_improvement <- player_improvement %>% mutate(total_improvement = (PTS_2025 + AST_2025) - (PTS_2024 + AST_2024)) %>% arrange(desc(total_improvement)) %>% slice(1:5) # Plot the top 5 improvements player_improvement %>% ggplot(aes(x = Player, y = total_improvement)) + geom_col() + labs(title = "Top 3 Player Improvements (PTS + AST, 2024 to 2025)", x = "Player", y = "Total Improvement") ``` Above I created a column chart that shows the top 3 players in terms of improvement in combined PTS & AST from 2024 to 2025. Quientin Grimes is the most improved, with Toppin and Jerome significantly behind. **Question 2)** Does a players position relate to total rebounds per game? ```{r} rebounding <- all_season_stats %>% group_by(Pos) %>% filter(!is.na(ORB), !is.na(DRB)) %>% summarise(Total_Reb = mean(ORB + DRB, na.rm = TRUE)) rebounding %>% ggplot(aes(x = Pos, y = Total_Reb)) + geom_bar(stat = "identity", na.rm = TRUE) + labs(title = "Average Total Rebounds Per Game by Position", x = "Position", y = "Average Total Rebounds Per Game") ``` I created a bar chart as seen above that shows that as one would assume, Centers (which is typically played by the tallest player in the game) is the highest average in terms of rebounds per game. Then, Power Forwards who are around 1 fewer (on average) per game, and about another rebound fewer is Small Forwards. Point guards and Shooting Guards are both about the same, averaging just under a half fewer rebounds per game than Small Forwards. This shows that position does relate to average rebounds per game. **Question 3)** How does age affect player offensive performance? (PTS, AST) ```{r} age_performance <- all_season_stats %>% group_by(Age) %>% filter(!is.na(PTS), !is.na(AST)) %>% summarise(Avg_PTS = mean(PTS, na.rm = TRUE), Avg_AST = mean(AST,na.rm = TRUE)) age_performance %>% ggplot(aes(x = Avg_AST, y = Avg_PTS, color = as.factor(Age))) + geom_point(na.rm = TRUE) + geom_text(aes(label = Age), vjust = -0.5, size = 3, na.rm = TRUE) + labs(title = "Age Impact on Offensive Performance", x = "Avg AST", y = "Avg PTS") ``` There is clearly one outlier in this visual, which is influenced by LeBron James specifically (aka 2nd best ever). Those who are in either in their late 20s and early 30s are not significantly different in terms of offensive production, but other than our LeBron outlier, age does impact a players ability to be of impact on the offensive side of the ball. **Question 4)** Who are the best 10 all around players from 2025? (PTS, AST, REB) ```{r} all_around <- all_season_stats %>% filter(Season == 2025) %>% group_by(Player) %>% filter(if("2TM" %in% Team) Team == "2TM" else TRUE) %>% ungroup() %>% mutate(Total_REB = ORB + DRB, All_Around_Score = PTS + AST + Total_REB) %>% arrange(desc(All_Around_Score)) %>% slice_head(n = 10) all_around %>% ggplot(aes(x = reorder(Player, All_Around_Score), y = All_Around_Score)) + geom_col() + coord_flip() + labs(title = "Top 10 All-Around Players", x = "Player", y = "PTS + AST + REB") ``` The above column chart shows the top 10 players in PTS + AST + REB from 2025 in order from 1-10. **Question 5)** Which players are the biggest liabilities to their teams? (Top 5 in combined avg. turnovers and personal fouls) ```{r} liabilities <- all_season_stats %>% filter(Season == 2025) %>% mutate(Liability_Comb = PF + TOV) %>% arrange(desc(Liability_Comb)) %>% slice_head(n = 5) liabilities %>% ggplot(aes(x = reorder(Player, Liability_Comb), y = Liability_Comb)) + geom_col() + coord_flip() + labs(title = "Top 5 Player Liabilities (Personal Fouls + Turnovers)", x = "Player", y = "Combined PF + TOV") ``` The listed players are the top 5 in combined personal fouls and turnovers per game. This is a negative influence on the team, however, all of these players are considered to be "stars" who elevate their team. This shows that these players are able to overcome their "negative" attributes, however, these players also are considered to not be overly successful (for the most part) in the playoffs, so maybe this is a part of why.