library(dplyr)
##
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
library(ggplot2)
data1 <- read.csv("C:\\Statistics\\nba.csv")
head(data1)
## bbrID Date Tm Opp TRB AST STL BLK PTS GmSc Season Playoffs Year
## 1 abdelal01 1993-03-16 BOS GSW 10 2 0 0 25 22.7 1992-93 false 1993
## 2 abdulma02 1991-04-02 DEN DAL 2 6 4 0 30 29.7 1990-91 false 1991
## 3 abdulta01 1998-04-19 SAC VAN 2 3 1 0 31 26.4 1997-98 false 1998
## 4 abdursh01 2001-11-23 ATL DET 12 5 2 1 50 46.0 2001-02 false 2002
## 5 abrinal01 2018-11-01 OKC CHO 2 0 0 0 25 17.1 2018-19 false 2019
## 6 achiupr01 2021-01-12 MIA PHI 13 3 0 1 17 16.9 2020-21 false 2021
## GameIndex GmScMovingZ GmScMovingZTop2Delta Date2 GmSc2 GmScMovingZ2
## 1 181 4.13 0.24 1991-12-04 18.6 3.89
## 2 64 3.82 0.64 1995-12-07 40.1 3.18
## 3 58 4.11 1.67 1998-01-14 16.9 2.44
## 4 386 4.06 0.84 2003-11-28 34.3 3.22
## 5 160 3.37 0.18 2018-11-30 16.6 3.19
## 6 8 2.58 0.05 2021-02-28 16.8 2.53
# Grouping the data by Team and summarizing points
group1 <- data1 %>%
group_by(Tm) %>%
summarise(mean_pts = mean(PTS, na.rm = TRUE))
# Grouping by Season and summarizing total rebounds
group2 <- data1 %>%
group_by(Season) %>%
summarise(mean_trb = mean(TRB, na.rm = TRUE))
# Grouping by Year and Playoffs status and summarizing assists
group3 <- data1 %>%
group_by(Year, Playoffs) %>%
summarise(mean_ast = mean(AST, na.rm = TRUE))
## `summarise()` has grouped output by 'Year'. You can override using the
## `.groups` argument.
# Visualization for Group 1 (Tm vs Points)
ggplot(group1, aes(x = Tm, y = mean_pts)) +
geom_bar(stat = "identity") +
theme_minimal() +
labs(title = "Average Points by Team", x = "Tm", y = "Average Points")
Note that the echo = FALSE
parameter was added to the
code chunk to prevent printing of the R code that generated the
plot.