Plot and Table Templates

Load Relevant Libraries

library(ggplot2)
library(ggthemes)
library(dplyr)
library(lubridate)
library(scales)
library(ggpubr)
library(stringr)
library(reshape2)
library(hexbin)
library(GGally)
library(DT)
library(forcats)

Set Global Image Options

knitr::opts_chunk$set(dpi = 200)

Set Colors

Hex_Dark_Red <- '#DE5246'

Hex_Google_Blue <- '#4285F4'
Hex_Google_Red <- '#EA4335'
Hex_Google_Yellow <- '#FBBC05'
Hex_Google_Green <- '#34A853'

Load 2018 Data

Golf_2018 <- 
    read.csv('./2018 Golf.csv', nrows = 105) %>% 
    mutate(
        Date = dmy(Date),
        Wind = as.numeric(gsub('mph', '', Wind)),
        Temp = as.numeric(gsub('°F', '', Temp)),
        FIR = NA,
        GIR = NA,
        Putts_Per_Hole = NA
    ) %>% 
    rename(
        'Hole_1' = 'Hole.1',
        'Hole_2' = 'Hole.2',
        'Hole_3' = 'Hole.3',
        'Hole_4' = 'Hole.4',
        'Hole_5' = 'Hole.5',
        'Hole_6' = 'Hole.6',
        'Hole_7' = 'Hole.7',
        'Hole_8' = 'Hole.8',
        'Hole_9' = 'Hole.9',
        'To_Par' = 'To.Par'
    ) %>% 
    select(
        -Partners,
        -Notes,
        -Fee.Avoided
    )

datatable(
    Golf_2018 %>% 
    select(
        Date,
        Course,
        Tee,
        Total,
        To_Par,
        Wind,
        Temp
    ) %>% 
    mutate(
        Date = format(Date, '%d %b %Y %H:%M:%S'),
        Wind = format(Wind, format = 'e', digits = 2, nsmall = 2),
        Temp = format(round(Temp, -1), nsmall = 1)
    )
    ,
    rownames = FALSE,
    selection = 'none',
    options = list(
        columnDefs = list(
            list(className = 'dt-left', targets = c(0:2)),
            list(className = 'dt-right', targets = c(3:6))
        )
    )
) %>%             
formatStyle(
    'Wind',
    backgroundColor = styleInterval(c(10, 20), c('#5cdb5c', '#ffff00', '#ff0021'))
) %>%
formatStyle(
    'Temp',
    backgroundColor = styleInterval(c(75, 85), c('#5cdb5c', '#ffff00', '#ff0021'))
)

Load 2019 Data

Golf_2019 <- 
    read.csv('./2019 Golf.csv', nrows = 143) %>% 
    mutate(
        Date = dmy(Date),
        Wind = as.numeric(gsub('mph', '', Wind)),
        Temp = as.numeric(gsub('°F', '', Temp))
    ) %>% 
    rename(
        'Hole_1' = 'Hole.1',
        'Hole_2' = 'Hole.2',
        'Hole_3' = 'Hole.3',
        'Hole_4' = 'Hole.4',
        'Hole_5' = 'Hole.5',
        'Hole_6' = 'Hole.6',
        'Hole_7' = 'Hole.7',
        'Hole_8' = 'Hole.8',
        'Hole_9' = 'Hole.9',
        'To_Par' = 'To.Par',
        'Putts_Per_Hole' = 'Putts.Per.Hole'
    ) %>%
    select(
        -Partners,
        -Notes,
        -Fee.Avoided,
        -Time,
        -X,
        -X.1,
        -X.2,
        -X.3,
        -X.4,
        -X.5,
        -X.6,
        -X.7
    )

Load 2020 Data

Golf_2020 <- 
    read.csv('./2020 Golf.csv', nrows = 177) %>%  
    mutate(
        Date = dmy(Date),
        Wind = as.numeric(gsub('mph', '', Wind)),
        Temp = as.numeric(gsub('°F', '', Temp))
    ) %>% 
    rename(
        'Hole_1' = 'Hole.1',
        'Hole_2' = 'Hole.2',
        'Hole_3' = 'Hole.3',
        'Hole_4' = 'Hole.4',
        'Hole_5' = 'Hole.5',
        'Hole_6' = 'Hole.6',
        'Hole_7' = 'Hole.7',
        'Hole_8' = 'Hole.8',
        'Hole_9' = 'Hole.9',
        'To_Par' = 'To.Par',
        'Putts_Per_Hole' = 'Putts.Per.Hole'
    ) %>%
    select(
        -Partners,
        -Notes,
        -Fee.Avoided,
        -Time
    )

Merge Data

Merged_Golf <-
    rbind(
        Golf_2018,
        Golf_2019,
        Golf_2020
    ) %>% 
    mutate(
        Week_Number = week(Date),
        Year = as.factor(year(Date)),
        Course = as.factor(Course),
        Weekday = weekdays(Date),
        Weekday = fct_relevel(
            Weekday,
            'Monday',
            'Tuesday',
            'Wednesday',
            'Thursday',
            'Friday',
            'Saturday',
            'Sunday'
        )
    )

Merged_Golf_Fargo <- 
    Merged_Golf %>% 
    filter(
        Course %in% c(
            'Rose Creek Front',
            'Rose Creek Back',
            'Edgewood Front',
            'Edgewood Back',
            'Osgood',
            'Prairiewood',
            'El Zagal'
        ),
        !is.na(To_Par)
    ) %>% 
    mutate(
        Course = fct_relevel(
            Course,
            'Rose Creek Front',
            'Rose Creek Back',
            'Edgewood Front',
            'Edgewood Back',
            'Osgood',
            'Prairiewood',
            'El Zagal'
        )
    )

Histograms

Histogram

Merged_Golf %>% 
filter(!is.na(GIR)) %>% 

ggplot(aes(x = GIR)) + 
geom_histogram(binwidth = 0.11, fill = Hex_Dark_Red, color = 'black') +
theme_bw() + 
xlab(paste('\n', 'GIRs (%)')) + 
ylab(paste('Count', '\n')) +
ggtitle('Histogram of GIRs')

Histogram with set breaks / labels

Hole_Scores <- 
  c(
    Merged_Golf$Hole_1,
    Merged_Golf$Hole_2,
    Merged_Golf$Hole_3,
    Merged_Golf$Hole_4,
    Merged_Golf$Hole_5,
    Merged_Golf$Hole_6,
    Merged_Golf$Hole_7,
    Merged_Golf$Hole_8,
    Merged_Golf$Hole_9
  )

Hole_Scores <- Hole_Scores[!is.na(Hole_Scores)]

Hole_Scores <- as.data.frame(Hole_Scores)

colnames(Hole_Scores) <- 'Scores'

Hole_Scores %>% 
  
ggplot(aes(x = Scores)) + 
geom_histogram(binwidth = 1, fill = Hex_Dark_Red, color = 'black') + 
scale_x_continuous(
  labels = c('1', '2', '3', '4', '5', '6', '7', '8', '9'), 
  breaks = c(1, 2, 3, 4, 5, 6, 7, 8, 9)
) +
theme_bw() + 
xlab(paste('\n', 'text')) + 
ylab(paste('text', '\n')) +
ggtitle(paste('text', '\n')) +
xlab(paste('\n', 'Score')) + 
ylab(paste('Count', '\n')) +
ggtitle('Histogram of Individual Hole Scores') 

Faceted histogram

Merged_Golf %>% 
filter(
    !is.na(To_Par)
) %>% 
  
ggplot(aes(x = To_Par)) +
geom_histogram(binwidth = 2, fill = Hex_Dark_Red, color = 'black') + 
facet_grid(. ~ Year) +
theme_bw() + 
xlab(paste('\n', 'Score (To Par)')) + 
ylab(paste('Number of 9-Hole Rounds', '\n')) +
ggtitle('Histogram of 9-Hole Round Scores Relative to Par')

Histogram of multiple variables

Merged_Golf %>% 
filter(!is.na(Total)) %>% 

ggplot(aes(x = To_Par, fill = Year)) +
geom_histogram(
    binwidth = 1,
    alpha = 0.5,
    position = 'identity'
) +
scale_fill_gdocs() +
theme_bw() +
xlab(paste('\n', 'Score (To Par)')) +
ylab(paste('Count', '\n')) +
ggtitle('Histogram of 9-Hole Round Scores')

Histogram of multiple variables stacked

Merged_Golf %>% 
filter(!is.na(Total)) %>%

ggplot(aes(x = To_Par, fill = Year)) +
geom_histogram(binwidth = 1, alpha = 0.7) + 
scale_fill_gdocs() +
theme_bw() + 
xlab(paste('\n', 'Score (To Par)')) + 
ylab(paste('Count', '\n')) +
ggtitle('Histogram of 9-Hole Round Scores')

Histogram with added stat lines

GIR_Mean <- mean(Merged_Golf$GIR, na.rm = TRUE)

Merged_Golf %>% 
filter(!is.na(GIR)) %>%

ggplot(aes(x = GIR)) + 
geom_histogram(binwidth = 0.11, fill = Hex_Dark_Red, color = 'black') +
theme_bw() + 
xlab(paste('\n', 'GIRs (%)')) + 
ylab(paste('Count', '\n')) +
ggtitle('Histogram of GIRs') +
geom_vline(aes(xintercept = GIR_Mean), color = Hex_Google_Blue, size = 1) +
labs(caption = paste('\n', 'Blue line: Sample mean'))

GIR_Mean <- mean(Merged_Golf$GIR, na.rm = TRUE)

GIR_SD <- sqrt(var(Merged_Golf$GIR, na.rm = TRUE))

Merged_Golf %>% 
filter(!is.na(GIR)) %>%

ggplot(aes(x = GIR)) + 
geom_histogram(binwidth = 0.11, aes(y = ..density..),fill = Hex_Dark_Red, color = 'black') +
theme_bw() +
xlab(paste('\n','GIRs (%)')) +
ylab(paste('Density', '\n')) +
ggtitle('Density of GIRs') + 
stat_function(fun = dnorm, args = list(mean = GIR_Mean, sd = GIR_SD), color = Hex_Google_Blue, size = 1.0) +
labs(caption = paste('\n', 'Blue line: Sample mean')) +
theme(plot.caption = element_text(hjust = 0))

Freq-Poly

Merged_Golf %>% 
filter(!is.na(Total)) %>%

ggplot(aes(x = To_Par, color = Year)) +
geom_freqpoly(binwidth = 1) +
scale_color_gdocs() +
theme_bw() +
xlab(paste('\n', 'Score (To Par)')) + 
ylab(paste('Count', '\n')) +
ggtitle('Frequency Plot of 9-Hole Round Scores') +
theme(plot.caption = element_text(hjust = 0))

Density Plots

Overlayed density plot

Merged_Golf %>% 
filter(!is.na(Total)) %>%

ggplot(aes(x = To_Par, fill = Year)) +
geom_density(alpha = 0.5) +
scale_fill_gdocs() +
theme_bw() + 
xlab(paste('\n', 'Score (To Par)')) + 
ylab(paste('Density', '\n')) +
ggtitle('Density Plot of 9-Hole Round Scores')

Merged_Golf %>% 
filter(!is.na(Total)) %>%

ggplot(aes(x = To_Par, color = Year)) +
geom_density(alpha = 1) +
scale_color_gdocs() +
theme_bw() + 
xlab(paste('\n', 'Score (To Par)')) + 
ylab(paste('Density', '\n')) +
ggtitle('Density Plot of 9-Hole Round Scores')

Faceted density plot

Merged_Golf_Fargo %>% 
filter(
    Year == 2020,
    Course %in% c(
        'Rose Creek Front',
        'Rose Creek Back',
        'Edgewood Front',
        'Edgewood Back'
    )
) %>% 

ggplot(aes(x = To_Par, fill = Course)) +
facet_grid(. ~ Course) +
geom_density(alpha = 0.7) +
xlim(0, 15) +
scale_fill_gdocs() +
theme_bw() +
xlab(paste('\n', 'Score (To Par)')) +
ylab(paste('Density', '\n')) +
ggtitle('Density Plot of Par 5 Course Scores (2020)') +
theme(
  legend.position = 'none'
)

Density plot with distribution lines

GIR_Mean <- mean(Merged_Golf$GIR, na.rm = TRUE)

GIR_SD <- sqrt(var(Merged_Golf$GIR, na.rm = TRUE))

Merged_Golf %>% 
filter(!is.na(GIR)) %>%

ggplot(aes(x = GIR)) + 
geom_density(fill = Hex_Dark_Red) +
theme_bw() +
xlab(paste('\n','GIRs (%)')) +
ylab(paste('Density', '\n')) +
ggtitle('Density of GIRs') + 
stat_function(fun = dnorm, args = list(mean = GIR_Mean, sd = GIR_SD), color = Hex_Google_Blue, size = 1.0) + 
labs(caption = paste('\n', 'Blue line: Sample mean')) +
theme(plot.caption = element_text(hjust = 0))

Bar Graph

Merged_Golf_Fargo %>% 

ggplot(aes(x = Course)) +
geom_bar(fill = Hex_Dark_Red, color = 'black') +
theme_bw() +
theme(
  axis.text.x = element_text(
    angle = 45, 
    vjust = 1, 
    size = 10, 
    hjust = 1
    )
) + 
xlab(paste('\n', 'Course')) + 
ylab(paste('Count', '\n')) +
ggtitle('Number of 9-Hole Rounds by Course')

Merged_Golf_Fargo %>% 
  
ggplot(aes(x = Course)) +
geom_bar(fill = Hex_Dark_Red, color = 'black') +
facet_grid(. ~ Year) +
theme_bw() +
theme(
  axis.text.x = element_text(
    angle = 45, 
    vjust = 1, 
    size = 8, 
    hjust = 1, 
    color = 'black'
  )
) + 
xlab(paste('\n', 'Course')) + 
ylab(paste('Count', '\n')) +
ggtitle('Number of 9-Hole Rounds by Course')

Scatter Plots

Faceted histogram with correlation stats

Merged_Golf %>% 
filter(!is.na(To_Par)) %>% 

ggplot(aes(x = Date, y = To_Par)) + 
geom_point(color = Hex_Dark_Red, size = 1.5) +
facet_grid(. ~ Year, scale = 'free_x') +
geom_smooth(method = 'lm', formula = y ~ x, se = TRUE, color = Hex_Google_Blue) +
stat_cor(
  method = 'pearson', 
  color = 'black',
  size = 4,
  label.x.npc = 0.97, 
  label.y.npc = 0.90, 
  hjust = 1
) +
theme(
  axis.text.x = element_text(
    size = 10, 
    color = 'black'
  )
) + 
theme_bw() + 
xlab(paste('\n', 'Month')) + 
ylab(paste('Score (To Par)', '\n')) +
ggtitle('9-Hole Scores Over Time')

Line / Time series

Merged_Golf_Fargo %>% 
filter(
  !is.na(To_Par), 
  Year == 2020
) %>% 

ggplot(aes(x = Date, y = To_Par)) + 
geom_point(color = Hex_Dark_Red, size = 2) +
stat_smooth(method = 'lm', formula = y ~ poly(x, 5), se = FALSE) +
theme_bw() + 
xlab(paste('\n', 'Month')) + 
ylab(paste('Score (To Par)', '\n')) +
ggtitle('9-Hole Scores Over Time (2020)')

Multiple Line / Time series

Merged_Golf %>% 
filter(
  !is.na(To_Par),
  !is.na(Week_Number)
) %>% 

ggplot(aes(x = Week_Number, y = To_Par, color = Year)) + 
geom_point(size = 2) +
stat_smooth(method = 'lm', formula = y ~ poly(x, 5), se = FALSE) +
scale_color_gdocs() +
theme_bw() +
xlab(paste('\n', 'Score (To Par)')) + 
ylab(paste('Week #', '\n')) +
ggtitle('Score Over Time')

Merged_Golf %>% 
filter(
  !is.na(To_Par),
  !is.na(Week_Number)
) %>% 

ggplot(aes(x = Week_Number, y = To_Par, color = Year)) + 
geom_point(size = 2, alpha = 0.3) +

stat_smooth(method = 'lm', formula = y ~ poly(x, 5), se = TRUE) +
scale_color_gdocs() +
theme_bw() +
xlab(paste('\n', 'Score (To Par)')) + 
ylab(paste('Week #', '\n')) +
ggtitle('Score Over Time')

Box Plots

Basic box plot

Merged_Golf %>% 
filter(!is.na(Total)) %>% 

ggplot(aes(y = To_Par, fill = Year)) +
geom_boxplot(alpha = 0.5) +
scale_fill_gdocs() +
theme_bw() +
ylab(paste('Score (To Par)', '\n')) +
ggtitle('Comparison of 9-Hole Round Scores') +
theme(
  axis.title.x=element_blank(),
  axis.text.x = element_blank(),
  axis.ticks.x = element_blank()
)

Box plot with specified order

Merged_Golf %>% 
filter(
  !is.na(To_Par),
  !is.na(Weekday),
  Year == 2020
) %>% 

ggplot(aes(Weekday, To_Par, fill = Weekday)) +
geom_boxplot(alpha = 0.5) +
scale_fill_gdocs() +
theme_bw() +
ylab(paste('Score (To Par)', '\n')) +
ggtitle('Comparison of Scores by Weekday (2020)') +
theme(
  axis.title.x=element_blank(),
  axis.text.x = element_blank(),
  axis.ticks.x = element_blank()
)

Violin

Merged_Golf %>% 
filter(!is.na(Total)) %>% 

ggplot(aes(x = Year, y = To_Par, fill = Year)) +
geom_violin(alpha = 0.5) +
scale_fill_gdocs() +
theme_bw() +
ylab(paste('Score (To Par)', '\n')) +
ggtitle('Comparison of 9-Hole Round Scores') +
theme(
  axis.title.x=element_blank(),
  axis.text.x = element_blank(),
  axis.ticks.x = element_blank()
)

Merged_Golf %>% 
filter(!is.na(Total)) %>%

ggplot(aes(x = Year, y = To_Par, fill = Year)) +
geom_violin(alpha = 0.5) +
scale_fill_gdocs() +
theme_bw() +
ylab(paste('Score (To Par)', '\n')) +
ggtitle('Comparison of 9-Hole Round Scores') +
theme(
  legend.position = 'none'
)

Merged_Golf %>% 
filter(!is.na(Total)) %>%

ggplot(aes(x = Year, y = To_Par, fill = Year)) +
geom_violin(width = 1.0, alpha = 0.5) +
geom_boxplot(width = 0.2, color = 'black', alpha = 1.0) +
scale_fill_gdocs() +
theme_bw() +
ylab(paste('Score (To Par)', '\n')) +
ggtitle('Comparison of 9-Hole Round Scores') +
theme(
  legend.position = 'none'
)

Dot Plot

Merged_Golf %>% 
filter(!is.na(Total)) %>%

ggplot(aes(x = Year, y = To_Par, fill = Year)) +
geom_dotplot(binaxis = 'y', stackdir = 'center', binwidth = 0.35) +
scale_fill_gdocs() +
theme_bw() +
ylab(paste('Score (To Par)', '\n')) +
ggtitle('Comparison of 9-Hole Round Scores') +
theme(
  axis.title.x=element_blank(),
  axis.text.x = element_blank(),
  axis.ticks.x = element_blank()
)

Jitter Plot

Merged_Golf %>% 
filter(!is.na(Total)) %>%

ggplot(aes(x = Year, y = To_Par)) +
geom_jitter(aes(color = Year), alpha = 0.5) +
scale_fill_gdocs() +
theme_bw() +
ylab(paste('Score (To Par)', '\n')) +
ggtitle('Comparison of 9-Hole Round Scores')

Correlation Matrix

mydata <- mtcars[, c(1,3,4,5,6,7)]
cormat <- round(cor(mydata),2)
melted_cormat <- melt(cormat)

melted_cormat %>% 
  
ggplot(aes(x=Var1, y=Var2, fill=value)) + 
geom_tile() 

# Get lower triangle of the correlation matrix
  get_lower_tri<-function(cormat){
    cormat[upper.tri(cormat)] <- NA
    return(cormat)
  }
  # Get upper triangle of the correlation matrix
  get_upper_tri <- function(cormat){
    cormat[lower.tri(cormat)]<- NA
    return(cormat)
  }

upper_tri <- get_upper_tri(cormat)
melted_cormat <- melt(upper_tri, na.rm = TRUE)

ggplot(data = melted_cormat, aes(Var2, Var1, fill = value))+
 geom_tile(color = "white")+
 scale_fill_gradient2(low = "blue", high = "red", mid = "white", 
   midpoint = 0, limit = c(-1,1), space = "Lab", 
   name="Pearson\nCorrelation") +
  theme_minimal()+ 
 theme(axis.text.x = element_text(angle = 45, vjust = 1, 
    size = 12, hjust = 1))+
 coord_fixed()

PairsPlot <- Merged_Golf[,c('To_Par', 'FIR', 'GIR')]

ggpairs(PairsPlot, lower = list(continuous = wrap("smooth", alpha = 0.5, size = 1))) +
        theme_bw() 

Heatmap

Merged_Golf %>% 
filter(
  !is.na(To_Par), 
  !is.na(GIR),
  Year != 2018
) %>% 

ggplot(aes(x = GIR, y = To_Par)) + 
 geom_hex(binwidth = c(0.1,1)) +
 xlim(0, 1) +
 theme_bw() +
 xlab(paste('\n', 'GIRs (%)')) + 
 ylab(paste('Score (To Par)', '\n')) +
 ggtitle(paste('Score vs GIRs', '\n')) +
 theme(plot.title = element_text(hjust = 0.5))

Merged_Golf %>% 
filter(
  !is.na(To_Par), 
  !is.na(GIR),
  Year != 2018
) %>%

ggplot(aes(x = GIR, y = To_Par)) + 
geom_hex(binwidth = c(0.1,1)) +
facet_grid(. ~ Year, scale = 'free_x') +
scale_fill_viridis_c() + 
xlim(0, 1) +
theme_bw() +
xlab(paste('\n', 'GIRs (%)')) + 
ylab(paste('Score (To Par)', '\n')) +
ggtitle(paste('Score vs GIRs', '\n')) +
theme(plot.title = element_text(hjust = 0.5))

## Warning: Removed 1 rows containing missing values (`geom_hex()`).

Q-Q Plot

Merged_Golf %>% 
filter(!is.na(GIR)) %>% 

ggplot(aes(sample = GIR)) + 
geom_qq(color = Hex_Dark_Red) +
stat_qq_line() +
theme_bw() + 
xlab(paste('\n', 'Theoretical')) + 
ylab(paste('Sample', '\n')) +
ggtitle(paste('GIR Q-Q Plot', '\n')) +
theme(plot.title = element_text(hjust = 0.5))