第 1 週補充教材

5 種 data types：

• 向量 (vector)
• factor
• list
• data.frame
• matrix

3 種 element types：

• 數值： 實數 double, 整數 integer
• 字串： ” ”
• 邏輯值： TRUE, FALSE, 邏輯表達式 <, >, <=, >=, ==, !, &, | 的結果

邏輯運算

mtcars |> head()

m = mtcars$mpg
s = m |> summary()
m[m < s[2]]

[1] 14.3 15.2 10.4 10.4 14.7 15.2 13.3 15.0

m[m >= s[5]]

[1] 22.8 24.4 22.8 32.4 30.4 33.9 27.3 26.0 30.4

m[m < s[2] | m >= s[5]]

 [1] 22.8 14.3 24.4 22.8 15.2 10.4 10.4 14.7 32.4 30.4 33.9 15.2 13.3 27.3 26.0
[16] 30.4 15.0

m[m < s[5] & m >= s[2]]

 [1] 21.0 21.0 21.4 18.7 18.1 19.2 17.8 16.4 17.3 21.5 15.5 19.2 15.8 19.7 21.4

m[m < s[2]] |> mean()

[1] 13.5625

m[m >= s[5]] |> median()

[1] 27.3

m[m < s[2] | m >= s[5]] |> min()

[1] 10.4

m[m < s[2] | m >= s[5]] |> max()

[1] 33.9

m |> min()

[1] 10.4

m |> max()

[1] 33.9

m[m < s[5] & m >= s[2]] |> median()

[1] 19.2

列的操作

• mtcars 的倒數第 12 列
• 1 到 173 的前 1/4 與後 1/4 各包含哪些數字
• flights 的前 1/4 列的最後一列
• flights 的後 1/4 列的第一列

mtcars |> tail(12) |> head(1)

n = 1:173 |> summary()
1:n[2]

 [1]  1  2  3  4  5  6  7  8  9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25
[26] 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44

n[5]:173

 [1] 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148
[20] 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167
[39] 168 169 170 171 172 173

n1 = 1:nrow(flights) |> summary()
n1[2]*2

 1st Qu. 
168389.5 

flights[as.integer(n1[2]),]

flights[as.integer(n1[5]),]

部分樣本的分組直方圖

• mpg 資料檔中 manufacturer 樣本最多的 3 家名稱 n
• 挑出這 3 家的樣本，製作

mpg$manufacturer |> table()

      audi  chevrolet      dodge       ford      honda    hyundai       jeep 
        18         19         37         25          9         14          8 
land rover    lincoln    mercury     nissan    pontiac     subaru     toyota 
         4          3          4         13          5         14         34 
volkswagen 
        27 

a = mpg$manufacturer |> table() |> sort()
n = a |> tail(3) |> names()
m = mpg[mpg$manufacturer %in% n,]

barplot(table(m$class,m$manufacturer),beside = T)

m |> ggplot() + 
  geom_bar(aes(manufacturer, fill = class), position = "dodge")

分組統計量及直方圖

f = flights[flights$hour >= 5,]

tapply(f$arr_time,f$hour,median,na.rm = T) |>
  enframe() |> 
  ggplot() + geom_col(aes(name,value))

tapply(flights$distance,flights$origin,median,na.rm = T) |>
  enframe() |> 
  ggplot() + geom_col(aes(name,value))

flights$carrier |> table()

   9E    AA    AS    B6    DL    EV    F9    FL    HA    MQ    OO    UA    US 
18460 32729   714 54635 48110 54173   685  3260   342 26397    32 58665 20536 
   VX    WN    YV 
 5162 12275   601 

tapply(flights$arr_delay,flights$carrier,mean,na.rm = T) |>
  enframe() |> 
  ggplot() + geom_col(aes(name,value))

tapply(airquality$Temp,airquality$Month,mean) |>
  enframe() |> 
  ggplot() + geom_col(aes(name,value))

tapply(airquality$Ozone,airquality$Month,mean,na.rm = T) |>
  enframe() |> 
  ggplot() + geom_col(aes(name,value))

tapply(airquality$Solar.R,airquality$Month,mean,na.rm = T) |>
  enframe() |> 
  ggplot() + geom_col(aes(name,value))

tapply(airquality$Wind,airquality$Month,mean,na.rm = T) |>
  enframe() |> 
  ggplot() + geom_col(aes(name,value))

airquality |> ggplot() + geom_point(aes(Month,Temp))

airquality |> ggplot() + geom_point(aes(Month,Wind))

airquality |> na.omit() |> 
  ggplot() + geom_point(aes(Month,Ozone))

airquality |> na.omit() |> 
  ggplot() + geom_point(aes(Month,Solar.R))

特殊向量：

seq(11,15)

[1] 11 12 13 14 15

seq(11,25, by = 3)

[1] 11 14 17 20 23

seq(11,15, length.out = 7)

[1] 11.00000 11.66667 12.33333 13.00000 13.66667 14.33333 15.00000

seq(11,15, l = 7)

[1] 11.00000 11.66667 12.33333 13.00000 13.66667 14.33333 15.00000

x = 1:3
rep(x, times = 3)

[1] 1 2 3 1 2 3 1 2 3

rep(x, 3)

[1] 1 2 3 1 2 3 1 2 3

rep(x, each = 4)

 [1] 1 1 1 1 2 2 2 2 3 3 3 3

rep(x, 2, each = 4)

 [1] 1 1 1 1 2 2 2 2 3 3 3 3 1 1 1 1 2 2 2 2 3 3 3 3

rep(x, length = 7)

[1] 1 2 3 1 2 3 1

rep(x, c(4,2,6))

 [1] 1 1 1 1 2 2 3 3 3 3 3 3