R, Python 분석과 프로그래밍의 친구 (by R Friend)

  (1) 순환문 진행상태를 막대(bar), 비율(percent), 추정 완료시간 출력하기

## 'progress' Package: Configurable progress bars

install.packages("progress")
library(progress)

pb <- progress_bar$new(total = 10000)
for (i in 1:10000) {
  pb$tick()
  Sys.sleep(1 / 1000) # Suspend execution of R expressions for a specified time interval
}

  (2) 순환문 진행상태를 현재까지 tick 개수(current), 총 tick 개수(total),

      현재까지 상세 소요 시간(elapsedfull) 출력하기

  (1) R ggplot2로 커널 밀도 곡선 그리기 (Kernel Density Curve by R ggplot2)

> library(MASS)

> library(ggplot2)

> 

> ggplot(Cars93, aes(x=Price)) + 

+   geom_density(fill = 'yellow') + 

+   geom_line(stat = "density") + 

+   expand_limits(y = 0) + 

+   ggtitle("Kernel Density Curve") 

(2) 커널 밀도 곡선의 최대 피크값의 좌표 구하기 

     (X, Y coordinates of the peak value in kernel density curve)

> density(Cars93$Price)

Call:

density.default(x = Cars93$Price)

Data: Cars93$Price (93 obs.); Bandwidth 'bw' = 3.011

       x                y            

 Min.   :-1.634   Min.   :1.608e-05  

 1st Qu.:16.508   1st Qu.:9.773e-04  

 Median :34.650   Median :5.329e-03  

 Mean   :34.650   Mean   :1.377e-02  

 3rd Qu.:52.792   3rd Qu.:2.078e-02  

 Max.   :70.934   Max.   :5.025e-02

> which.max(density(Cars93$Price)$y)

[1] 127

> x_coord_of_y_max = density(Cars93$Price)$x[127]

> x_coord_of_y_max

[1] 16.25942

 (3) 커널 밀도 곡선의 최대 피크값 위치에 수직선을 추가하기

     (adding a vertical line at peak value in kernel density plot)

> ggplot(Cars93, aes(x=Price)) + 

+   geom_density(fill = 'yellow') + 

+   geom_line(stat = "density") + 

+   expand_limits(y = 0) + 

+   ggtitle("Kernel Density Curve w/ Vertical Line at Peak Point") +

+   geom_vline(xintercept = x_coord_of_y_max, color='blue', size=2, linetype="dotted")

  (4) 여러개 그룹의 커널 밀도 곡선을 겹쳐 그린 경우 최대 peak 값 찾고 수직선 그리기

> ggplot(Cars93, aes(x=Price, colour = Type)) + 

+   geom_density(fill = NA) + 

+   geom_line(stat = "density") + 

+   expand_limits(y = 0) + 

+   ggtitle("Kernel Density Curve by Car Types")

> density(Cars93[Cars93$Type=='Van', ]$Price)

Call:

density.default(x = Cars93[Cars93$Type == "Van", ]$Price)

Data: Cars93[Cars93$Type == "Van", ]$Price (9 obs.); Bandwidth 'bw' = 0.303

       x               y            

 Min.   :15.39   Min.   :0.0000072  

 1st Qu.:17.45   1st Qu.:0.0040424  

 Median :19.50   Median :0.0495649  

 Mean   :19.50   Mean   :0.1215343  

 3rd Qu.:21.55   3rd Qu.:0.1807290  

 Max.   :23.61   Max.   :0.5321582  

> which.max(density(Cars93[Cars93$Type=='Van', 'Price'])$y)

[1] 238

> x_coord_of_y_max = density(Cars93[Cars93$Type=='Van','Price'])$x[238]

> x_coord_of_y_max

[1] 19.20249

> ggplot(Cars93, aes(x=Price, colour = Type)) + 

+   geom_density(fill = NA) + 

+   geom_line(stat = "density") + 

+   expand_limits(y = 0) + 

+   ggtitle("Kernel Density Curve w/ Vertical Line at Peak Point") +

+   theme_bw() +

+   geom_vline(xintercept = x_coord_of_y_max, color='red', size=1, linetype="dashed")

#----------------

# histogram with variable size of bin width and different colors per bins using ggplot2

#----------------

# sample data frame

mydf <- data.frame(var = c(1100, 10000, 100000, 190000, 110000, 220000, 550000, 701000, 790000))

# numeric notation for large numbers

options(scipen = 30)

library("ggplot2")

# fill color with different colors per bins

mydf$group <- ifelse(mydf$var < 10000, 1, 

                          ifelse(mydf$var < 100000, 2, 

                                 ifelse(mydf$var < 200000, 3, 

                                        ifelse(mydf$var < 500000, 4, 5))))

# breaks of bin

bins <- c(1000, 10000, 100000, 200000, 500000, 800000)

# draw histogram with variable size of bin width and different colors per bins

ggplot(mydf, aes(x= var)) +

  geom_histogram(data=subset(mydf, group==1), breaks = c(1000, 10000), fill="black") +

  geom_histogram(data=subset(mydf, group==2), breaks = c(10000, 100000), fill="yellow") +

  geom_histogram(data=subset(mydf, group==3), breaks = c(100000, 200000), fill="green") +

  geom_histogram(data=subset(mydf, group==4), breaks = c(200000, 500000), fill="blue") +

  geom_histogram(data=subset(mydf, group==5), breaks = c(500000, 800000), fill="red") +

  scale_x_continuous(breaks = bins, limits = c(1000, 800000)) +

  xlab("variable 1") + 

  ylab("count") +

  ggtitle("Histogram with different size of bin width and colors") + 

  theme(plot.title = element_text(hjust = 0.5, size = 14))

#=========================================
# Dual y-axes plot using ggplot2 sec.axis
#=========================================

rm(list=ls()) # clear all

# make a DataFrame
data_val <- matrix(
  c(-4.2922960, 0.00000000000389755, 0.00000000268579,
  -3.9102123, 0.00000000000939471, 0.00000003082191,
  -3.5281286, 0.00000000002264455, 0.00000027610486,
  -3.1460449, 0.00000000005458189, 0.00000193070482,
  -2.7639612, 0.00000000013156254, 0.00001053865139,
  -2.3818776, 0.00000000031711433, 0.00004490363779,
  -1.9997939, 0.00000000076436268, 0.00014935003987,
  -1.6177102, 0.00000000184239690, 0.00038775418083,
  -1.2356265, 0.00000000444085801, 0.00078584150863,
  -0.8535428, 0.00000001070411038, 0.00124319933681,
  -0.4714591, 0.00000002580086522, 0.00153523161114,
  -0.0893754, 0.00000006218962756, 0.00147990680737,
  0.2927083, 0.00000014989999897, 0.00111358189390,
  0.6747920, 0.00000036131440584, 0.00065408965954,
  1.0568757, 0.00000087090114242, 0.00029990225777,
  1.4389594, 0.00000209919260108, 0.00010733701573,
  1.8210431, 0.00000505982314747, 0.00002998793957,
  2.2031268, 0.00001219600184343, 0.00000653989939,
  2.5852105, 0.00002939662278856, 0.00000111332724,
  3.5852105, 0.00029392734366929, 0.00000000000000,
  4.5852105, 0.00293538878457633, 0.00000000000000,
  5.5852105, 0.02896916461589227, 0.00000000000000,
  6.5852105, 0.25470155892952129, 0.00000000000000,
  7.5852105, 0.94711869936516890, 0.00000000000000,
  8.5852105, 0.99999999999982903, 0.00000000000000,
  9.5852105, 1.00000000000000000, 0.0000000000000),
  nrow=26,
  byrow=TRUE)

# convert a matrix into a dataframe
df <- data.frame(data_val)

# column name
colnames(df) <- c("x", "y1", "y2")

> head(df)
          x           y1           y2
1 -4.292296 3.897550e-12 2.685790e-09
2 -3.910212 9.394710e-12 3.082191e-08
3 -3.528129 2.264455e-11 2.761049e-07
4 -3.146045 5.458189e-11 1.930705e-06
5 -2.763961 1.315625e-10 1.053865e-05
6 -2.381878 3.171143e-10 4.490364e-05

> # max ratio b/w 2 axes
> summary(df)
       x                 y1                  y2          
Min.   :-4.2923   Min.   :0.0000000   Min.   :0.000e+00 
1st Qu.:-1.9043   1st Qu.:0.0000000   1st Qu.:7.000e-10 
Median : 0.4838   Median :0.0000003   Median :8.539e-06 
Mean   : 1.1492   Mean   :0.1243873   Mean   :3.020e-04 
3rd Qu.: 3.3352   3rd Qu.:0.0002278   3rd Qu.:3.658e-04 
Max.   : 9.5852   Max.   :1.0000000   Max.   :1.535e-03 
> max_ratio <- max(df$y1)/max(df$y2); max_ratio
[1] 651.367

> # Dual y-axes plot using ggplot2 sec.axis
> library(ggplot2)
> 
> g <- ggplot(df, aes(x = x))
>   g <- g + geom_line(aes(y = y1), colour = "red", size = 2)
>   
>   # adding the relative result5.data.A, 
>   # transformed to match roughly the range of the B
>   g <- g + geom_bar(aes(y = y2*max_ratio), 
>                         fill = "blue", 
>                         stat = "identity")
>   
>   # adding secondary axis
>   g <- g + scale_y_continuous(sec.axis = sec_axis(~.*max_ratio, name="y2*651"))
>   
> g

> # adding text
>   g <- g + annotate("text", x = -2, y = 0.75, colour="black", label="y2*651")
>   g <- g + annotate("text", x = 5, y = 0.5, colour="black", label="y1")
>   
> # adding arrow
> library(grid)
>   g <- g + annotate("segment", x = -1.8, y = 0.75, 
+                     xend = -1, yend = 0.6, colour="blue", arrow=arrow())
>   g <- g + annotate("segment", x = 5.2, y = 0.5, 
+                     xend = 6.7, yend = 0.4, colour="red", arrow=arrow())
> g

# KRUG's plot quiz, as of 18th NOV. 2017

library(ggplot2)

#install.packages("dplyr")

library(dplyr)

str(mtcars)

# making 'model' variable

mtcars$model <- rownames(mtcars)

# ordering by cyl, hp

mtcars_ord <- arrange(mtcars[,c('model', 'cyl', 'hp')], cyl, desc(hp))

# marking an inflection point within cluster : threshold >= 40

mtcars_cyl <- c(4, 6, 8)

mtcars_ord_2 <- data.frame()

for (i in 1:length(mtcars_cyl)) {

  mtcars_tmp <- subset(mtcars_ord, subset = (cyl == mtcars_cyl[i]))

  for (j in 1:nrow(mtcars_tmp)) {

    if (j != nrow(mtcars_tmp) & mtcars_tmp$hp[j] - mtcars_tmp$hp[j+1] >= 40) {

      mtcars_tmp$hp_outlier[j] = '1_outlier'

    } else {

      mtcars_tmp$hp_outlier[j] = '2_normal'

    }

  }

  mtcars_ord_2 <- rbind(mtcars_ord_2, mtcars_tmp)

  rm(mtcars_tmp)

}

# converting cyl variable type from numeric to factor

mtcars_ord_2$cyl_cd <- paste0("cyl :", mtcars_ord_2$cyl)

model_order <- mtcars_ord_2$model[order(mtcars_ord_2$cyl_cd, 

                                        mtcars_ord_2$hp, 

                                        decreasing = FALSE)]

mtcars_ord_2$model <- factor(mtcars_ord_2$model, levels = model_order)

# drawing cleveland dot plot

ggplot(mtcars_ord_2, aes(x = hp, y = model)) +

  geom_point(size = 2, aes(colour = hp_outlier)) +

  scale_colour_manual(values = c("red", "black")) + 

  theme_bw() +

  facet_grid(. ~ cyl_cd, scales = "free_y", space = "free_y") +

  xlim(0, max(mtcars_ord_2$hp)) +

  geom_hline(yintercept = nrow(mtcars_ord_2[mtcars_ord_2$cyl == 4,]) + 0.5, 

             colour = "black", linetype = "dashed", size = 0.5) +

  geom_hline(yintercept = nrow(mtcars_ord_2) - 

               nrow(mtcars_ord_2[mtcars_ord_2$cyl == 8,]) + 0.5, 

             colour = "black", linetype = "dashed", size = 0.5) +

  theme(legend.position = 'none')

library(data.table)
library(dplyr)
library(ggplot2)

mtcars %>%
mutate(car.name=rownames(.)) %>%
arrange(cyl, hp) %>%
mutate(order.key=1:n()) -> data

data %>%
ggplot(aes(x=hp, y=reorder(car.name, order.key))) +
geom_point(
colour=case_when(
data$car.name %in% c('Ferrari Dino','Maserati Bora') ~ 'red', 
TRUE ~ 'black')) +
geom_hline(yintercept = 11.5, linetype='dashed') +
geom_hline(yintercept = 18.5, linetype='dashed') +
facet_wrap(~ cyl, labeller = label_both) +
scale_x_continuous(limits=c(0,max(data$hp))) +
theme_bw() +
theme(axis.title.y=element_blank())

#==========================

# Rssizing the plot

#==========================

install.packages("ggplot2")

library(ggplot2)

# X, Y coordinate and segments(A, B category) data set

my.df <- data.frame(XCoord = c(1, 1, 1, 2, 2, 2, 3, 3, 4, 4), 

                    YCoord = c(1, 2, 4, 1, 3, 4, 2, 4, 1, 4), 

                    Seg = c("A", "A", "A", "A", "B", "A", "B", "B", "B", "B"))

# Original plot

ggplot(my.df, aes(x=XCoord, y=YCoord, fill=Seg)) +

  geom_tile(colour="gray80") +

  scale_fill_manual(values = c("black", "white")) +

  ggtitle("Original Heatmap by X4*Y4 size")

# Resized plot using coord_fixed(ratio = number)

ggplot(my.df, aes(x=XCoord, y=YCoord, fill=Seg)) +

  geom_tile(colour="gray80") +

  scale_fill_manual(values = c("black", "white")) +

  coord_fixed(ratio = 2) +

  ggtitle("Heatmap : Resized X:Y axis size with 1:2 ratio")

# Resized plot using coord_fixed(ratio = number)

ggplot(my.df, aes(x=XCoord, y=YCoord, fill=Seg)) +

  geom_tile(colour="gray80") +

  scale_fill_manual(values = c("black", "white")) +

  coord_fixed(ratio = 0.5) +

  ggtitle("Heatmap : Resized X:Y axis size with 2:1 ratio")

#==============
# Image resize using EBImage package

# installing EBImage package
source("http://bioconductor.org/biocLite.R")
biocLite("EBImage")


# resizing image using EBImage package's resize() function

library("EBImage")

x <- readImage(system.file("images", "sample-color.png", package="EBImage"))


# width and height of the original image
dim(x)[1:2]


# scale to a specific width and height
y <- resize(x, w = 200, h = 100)


# scale by 50%; the height is determined automatically so that
# the aspect ratio is preserved
y <- resize(x, dim(x)[1]/2)


# show the scaled image
display(y)


# extract the pixel array
z <- imageData(y)


# or
z <- as.array(y)

> ##======================================================

> ## adding multiple vertical lines at time-series plot using R ggplot2

> ##======================================================

> 

> # making time series data

> dt <- c("20170609100000", "20170609100100", "20170609100200", 

+         "20170609100300", "20170609100400", "20170609100500")

> val <- c(5.2, 3.4, 3.9, 6.3, 4.7, 5.6)

> 

> dt_val <- data.frame(dt, val)

> dt_val <- transform(dt_val, 

+                     dt = as.POSIXct(dt, 

+                                     format = '%Y%m%d%H%M%S', 

+                                     origin = "1970-01-01", 

+                                     tz = "UTC"))

> 

> dt_val

                   dt val

1 2017-06-09 10:00:00 5.2

2 2017-06-09 10:01:00 3.4

3 2017-06-09 10:02:00 3.9

4 2017-06-09 10:03:00 6.3

5 2017-06-09 10:04:00 4.7

6 2017-06-09 10:05:00 5.6

> # making time series plot

> library(ggplot2)

> 

> ggplot(dt_val, aes(x = dt, y = val)) +

+   geom_line(size=1, color = "blue") + 

+   ggtitle("Time-series plot")

> # To add vertical line at time series plot

> # Error in Ops.POSIXt((x - from[1]), diff(from)) : '/' not defined for "POSIXt" objects

> ggplot(dt_val, aes(x = dt, y = val)) +

+   geom_line(size = 1, color = "blue") +

+   geom_vline(xintercept = dt_val$dt[3], color =  "red", linetype = 2) +

+   ggtitle("Adding vertical line at time-series plot using geom_vline()")

Error in Ops.POSIXt((x - from[1]), diff(from)) : 

  '/' not defined for "POSIXt" objects

> # Use as.numeric() function at xintercept

> ggplot(dt_val, aes(x = dt, y = val)) +

+   geom_line(size = 1, color = "blue") +

+   geom_vline(xintercept = as.numeric(dt_val$dt[3]), color = "red", linetype = 2) + # as.numeric() transformation

+   ggtitle("Adding vertical line at time-series plot using geom_vline() and as.numeric() transformation")

> # adding "Multiple" vertical lines

> ggplot(dt_val, aes(x = dt, y = val)) +

+   geom_line(size = 1, color = "blue") +

+   geom_vline(xintercept = as.numeric(dt_val$dt[c(3,5)]), color = "red", linetype = 2) +

+   ggtitle("Adding multiple vertical lines at time-series plot using geom_vline()")

HOW_BACKTRACE environmental variable.

> # adding multiple vertical lines with another data frame

> dt_2 <- c("20170609100150", "20170609100430")

> val_2 <- c("yes", "yes")

> dt_val_2 <- data.frame(dt_2, val_2)

> dt_val_2 <- transform(dt_val_2, 

+                       dt_2 = as.POSIXct(dt_2, 

+                                         format = '%Y%m%d%H%M%S', 

+                                         origin = "1970-01-01", 

+                                         tz = "UTC"))

> dt_val_2

                 dt_2 val_2

1 2017-06-09 10:01:50   yes

2 2017-06-09 10:04:30   yes

> # time series plot with multiple vertical lines from another data frame

> ggplot(dt_val, aes(x = dt, y = val)) +

+   geom_line(size = 1, color = "blue") +

+   geom_vline(xintercept = as.numeric(dt_val_2$dt_2), color = "red", linetype = 2) +

+   ggtitle("Time-seires plot with multiple vertical line from another dataframe")

HOW_BACKTRACE environmental variable.

> # time series plot with multiple vertical lines from another data frame(2)

> ggplot(dt_val, aes(x = dt, y = val)) +

+   geom_line(size = 1, color = "blue") +

+   geom_vline(data = dt_val_2, xintercept = as.numeric(dt_val_2$dt_2), color = "red", linetype = 2) +

+   ggtitle("Time-series plot with multiple vertical lines from another dataframe 2")

##---------------------------------

## gantt chart by timevis package

##---------------------------------

# reference : https://github.com/daattali/timevis

# install timevis package

install.packages("timevis")

# minimum view of timeline without any data at system time

library(timevis)

timevis()

# adding data to timevis() by DataFrame

data <- data.frame(

  id      = c(1:4),

  content = c("Item_First"  , "Item_Second"  ,"Ranged_First", "Ranged_Second"),

  start   = c("2017-05-26", "2017-05-27 01:30:00", "2017-05-27 05:00:00", "2017-05-30"),

  end     = c(NA          , NA                   , "2017-05-28 15:00:00", "2017-05-31 03:10:00")

)

# view of Gantt chart

timevis(data)

> # checking data type

> sapply(data, class)

       id      content      start        end 

"integer"  "factor"  "factor"  "factor"

# hide the zoom buttons, options for editable, height

timevis(data, 

            showZoom = FALSE, 

            options = list(editable = TRUE, 

                                  height = "300px"))

# %>% operator, set editable Options, add Item, set Selected Item

timevis() %>%

  setItems(data.frame(

    id = 1:2,

    content = c("one", "two"),

    start = c("2017-05-28", "2017-05-30")

  )) %>%

  setOptions(list(editable = TRUE)) %>%

  addItem(list(id = 3, content = "three", start = "2017-05-29")) %>%

  setSelection("1") 

# using the groups feature to group together multiple items into different buckets

timevis(

  data = data.frame(

    start = c(Sys.Date(), Sys.Date(), Sys.Date() + 1, Sys.Date() + 2),

    content = c("one", "two", "three", "four"), 

    group = c(1, 2, 1, 2)),

  groups = data.frame(id = 1:2, content = c("Group_1", "Group_2"))

)

# RShiny

library(shiny)

data <- data.frame(

  id = 1:3,

  start = c("2015-04-04", "2015-04-05 11:00:00", "2015-04-06 15:00:00"),

  end = c("2015-04-08", NA, NA),

  content = c("<h2>Vacation!!!</h2>", "Acupuncture", "Massage"),

  style = c("color: red;", NA, NA)

)

ui <- fluidPage(

  timevisOutput("appts"),

  div("Selected items:", textOutput("selected", inline = TRUE)),

  div("Visible window:", textOutput("window", inline = TRUE)),

  tableOutput("table")

)

server <- function(input, output) {

  output$appts <- renderTimevis(

    timevis(

      data,

      options = list(editable = TRUE, multiselect = TRUE, align = "center")

    )

  )

  output$selected <- renderText(

    paste(input$appts_selected, collapse = " ")

  )

  output$window <- renderText(

    paste(input$appts_window[1], "to", input$appts_window[2])

  )

  output$table <- renderTable(

    input$appts_data

  )

}

shinyApp(ui, server)

##---------------------------

# ggplot2 : legend 

##---------------------------

library(MASS)

library(ggplot2)

# Boxplot of MPG.highway per Car Type

mpg <- ggplot(Cars93, aes(x = Type, y = MPG.highway, fill = Type)) +

  geom_boxplot() +

  theme_bw() +

  ggtitle("MPG.highway per Car Type")

mpg

 (1) 범례 위치 바꾸기 (changing the position of legend) : theme(legend.position = "bottom")

# (1) Changing the legend position

# (1-1) outside the plot by using theme(legend.position = "right", "bottom", "left", "top")

# bottom

mpg + theme(legend.position = "bottom")

# left

mpg + theme(legend.position = "left")

# top

mpg + theme(legend.position = "top") 

# (1-2) inside the plot by using the location vector c(x coordinate, y coordinate) 

mpg + theme(legend.position = c(0.9, 0.8)) # coordinate value : between 0 and 1

 (2) 범례 글자 크기 및 색깔 바꾸기 (changing the size and color of the legend)

      : theme(legend.title = element_text(color, size, face))

      : theme(legend.text = element_text(color, size, face))

# (2) Changing the legend title and label size and color

mpg + 

  theme(legend.title = element_text(color = "blue", size = 12, face = "bold")) + # legend title

  theme(legend.text = element_text(color = "blue", size = 8, face = "italic")) # legend label

 (3) 범례 항목 순서 바꾸기 (changing the order of legend label)

      : factor(Type, levels = ("Compact", "Small", "Midsize", "Large", "Sporty", "Van")

> # (3) Changing the order of legend labels

> # checking the levels and class of 'Type' variable

> attributes(Cars93$Type)

$levels

[1] "Compact" "Large"   "Midsize" "Small"   "Sporty"  "Van"    

$class

[1] "factor"

> 

> # changing the level's order of factor 'Type'

> Cars93 <- transform(Cars93, 

+                  Type = factor(Type, levels = c("Compact", "Small", "Midsize", 

+                                                                    "Large", "Sporty", "Van")))

> 

> attributes(Cars93$Type)

$levels

[1] "Compact" "Small"   "Midsize" "Large"   "Sporty"  "Van"    

$class

[1] "factor"

> 

> mpg_legend_order_change <- ggplot(Cars93, aes(x = Type, y = MPG.highway, fill = Type)) +

+   geom_boxplot() +

+   theme_bw() +

+   ggtitle("Changing the order of legend labels by Car Size")

> 

> mpg_legend_order_change

 (4) 범례 없애기 (removing the legend) 

        : theme(legend.title = element_blank())

        : theme(legend.position = 'none')

# (4) Removing the legend title and labels

mpg + 

  theme(legend.title = element_blank()) +   # remove legend title

  theme(legend.position = 'none')                # remove legend labels

> library(ggplot2)

> library(MASS)

> str(Cars93)

'data.frame': 93 obs. of  27 variables:

 $ Manufacturer      : Factor w/ 32 levels "Acura","Audi",..: 1 1 2 2 3 4 4 4 4 5 ...

 $ Model             : Factor w/ 93 levels "100","190E","240",..: 49 56 9 1 6 24 54 74 73 35 ...

 $ Type              : Factor w/ 6 levels "Compact","Large",..: 4 3 1 3 3 3 2 2 3 2 ...

 $ Min.Price         : num  12.9 29.2 25.9 30.8 23.7 14.2 19.9 22.6 26.3 33 ...

 $ Price             : num  15.9 33.9 29.1 37.7 30 15.7 20.8 23.7 26.3 34.7 ...

 $ Max.Price         : num  18.8 38.7 32.3 44.6 36.2 17.3 21.7 24.9 26.3 36.3 ...

 $ MPG.city          : int  25 18 20 19 22 22 19 16 19 16 ...

 $ MPG.highway       : int  31 25 26 26 30 31 28 25 27 25 ...

 $ AirBags           : Factor w/ 3 levels "Driver & Passenger",..: 3 1 2 1 2 2 2 2 2 2 ...

 $ DriveTrain        : Factor w/ 3 levels "4WD","Front",..: 2 2 2 2 3 2 2 3 2 2 ...

 $ Cylinders         : Factor w/ 6 levels "3","4","5","6",..: 2 4 4 4 2 2 4 4 4 5 ...

 $ EngineSize        : num  1.8 3.2 2.8 2.8 3.5 2.2 3.8 5.7 3.8 4.9 ...

 $ Horsepower        : int  140 200 172 172 208 110 170 180 170 200 ...

 $ RPM               : int  6300 5500 5500 5500 5700 5200 4800 4000 4800 4100 ...

 $ Rev.per.mile      : int  2890 2335 2280 2535 2545 2565 1570 1320 1690 1510 ...

 $ Man.trans.avail   : Factor w/ 2 levels "No","Yes": 2 2 2 2 2 1 1 1 1 1 ...

 $ Fuel.tank.capacity: num  13.2 18 16.9 21.1 21.1 16.4 18 23 18.8 18 ...

 $ Passengers        : int  5 5 5 6 4 6 6 6 5 6 ...

 $ Length            : int  177 195 180 193 186 189 200 216 198 206 ...

 $ Wheelbase         : int  102 115 102 106 109 105 111 116 108 114 ...

 $ Width             : int  68 71 67 70 69 69 74 78 73 73 ...

 $ Turn.circle       : int  37 38 37 37 39 41 42 45 41 43 ...

 $ Rear.seat.room    : num  26.5 30 28 31 27 28 30.5 30.5 26.5 35 ...

 $ Luggage.room      : int  11 15 14 17 13 16 17 21 14 18 ...

 $ Weight            : int  2705 3560 3375 3405 3640 2880 3470 4105 3495 3620 ...

 $ Origin            : Factor w/ 2 levels "USA","non-USA": 2 2 2 2 2 1 1 1 1 1 ...

 $ Make              : Factor w/ 93 levels "Acura Integra",..: 1 2 4 3 5 6 7 9 8 10 ...

  (1) ggplot 그래프 배경을 흰색으로 바꾸기 : theme_bw() 

# box-plot by default

ggplot(Cars93, aes(x=Type, y=MPG.highway)) +

  geom_boxplot()

# box-plot with white background

ggplot(Cars93, aes(x=Type, y=MPG.highway)) +

  geom_boxplot() +

  theme_bw() # white background 

 (2) ggplot x축 라벨 각도를 90도 돌리기 : theme(axis.text.x=element_text(angle=90, hjust=1))

# box-plot with axis label's angle of 90 degrees

ggplot(Cars93, aes(x=Type, y=MPG.highway)) +

  geom_boxplot() +

  theme_bw() +

  theme(axis.text.x=element_text(angle=90, hjust=1))

# box-plot with x axis label's angle of 45 degrees

ggplot(Cars93, aes(x=Type, y=MPG.highway)) +

  geom_boxplot() +

  theme_bw() +

  theme(axis.text.x=element_text(angle=45, hjust=1))

# box-plot with y axis label's angle of 45 degrees

ggplot(Cars93, aes(x=Type, y=MPG.highway)) +

  geom_boxplot() +

  theme_bw() +

  theme(axis.text.y=element_text(angle=45, hjust=1))

 (3) ggplot x축과 y축의 위치를 바꾸기 : coord_flip()

# box-plot with the label at vertical axis

ggplot(Cars93, aes(x=Type, y=MPG.highway)) +

  geom_boxplot() +

  theme_bw() +

  coord_flip()