直譯式語言

#這是註解
3 + 3
## [1] 6
demo(graphics)
## 
## 
##  demo(graphics)
##  ---- ~~~~~~~~
## 
## > #  Copyright (C) 1997-2009 The R Core Team
## > 
## > require(datasets)
## 
## > require(grDevices); require(graphics)
## 
## > ## Here is some code which illustrates some of the differences between
## > ## R and S graphics capabilities.  Note that colors are generally specified
## > ## by a character string name (taken from the X11 rgb.txt file) and that line
## > ## textures are given similarly.  The parameter "bg" sets the background
## > ## parameter for the plot and there is also an "fg" parameter which sets
## > ## the foreground color.
## > 
## > 
## > x <- stats::rnorm(50)
## 
## > opar <- par(bg = "white")
## 
## > plot(x, ann = FALSE, type = "n")

plot of chunk unnamed-chunk-1

## 
## > abline(h = 0, col = gray(.90))
## 
## > lines(x, col = "green4", lty = "dotted")
## 
## > points(x, bg = "limegreen", pch = 21)
## 
## > title(main = "Simple Use of Color In a Plot",
## +       xlab = "Just a Whisper of a Label",
## +       col.main = "blue", col.lab = gray(.8),
## +       cex.main = 1.2, cex.lab = 1.0, font.main = 4, font.lab = 3)
## 
## > ## A little color wheel.    This code just plots equally spaced hues in
## > ## a pie chart.    If you have a cheap SVGA monitor (like me) you will
## > ## probably find that numerically equispaced does not mean visually
## > ## equispaced.  On my display at home, these colors tend to cluster at
## > ## the RGB primaries.  On the other hand on the SGI Indy at work the
## > ## effect is near perfect.
## > 
## > par(bg = "gray")
## 
## > pie(rep(1,24), col = rainbow(24), radius = 0.9)

plot of chunk unnamed-chunk-1

## 
## > title(main = "A Sample Color Wheel", cex.main = 1.4, font.main = 3)
## 
## > title(xlab = "(Use this as a test of monitor linearity)",
## +       cex.lab = 0.8, font.lab = 3)
## 
## > ## We have already confessed to having these.  This is just showing off X11
## > ## color names (and the example (from the postscript manual) is pretty "cute".
## > 
## > pie.sales <- c(0.12, 0.3, 0.26, 0.16, 0.04, 0.12)
## 
## > names(pie.sales) <- c("Blueberry", "Cherry",
## +              "Apple", "Boston Cream", "Other", "Vanilla Cream")
## 
## > pie(pie.sales,
## +     col = c("purple","violetred1","green3","cornsilk","cyan","white"))

plot of chunk unnamed-chunk-1

## 
## > title(main = "January Pie Sales", cex.main = 1.8, font.main = 1)
## 
## > title(xlab = "(Don't try this at home kids)", cex.lab = 0.8, font.lab = 3)
## 
## > ## Boxplots:  I couldn't resist the capability for filling the "box".
## > ## The use of color seems like a useful addition, it focuses attention
## > ## on the central bulk of the data.
## > 
## > par(bg="cornsilk")
## 
## > n <- 10
## 
## > g <- gl(n, 100, n*100)
## 
## > x <- rnorm(n*100) + sqrt(as.numeric(g))
## 
## > boxplot(split(x,g), col="lavender", notch=TRUE)

plot of chunk unnamed-chunk-1

## 
## > title(main="Notched Boxplots", xlab="Group", font.main=4, font.lab=1)
## 
## > ## An example showing how to fill between curves.
## > 
## > par(bg="white")
## 
## > n <- 100
## 
## > x <- c(0,cumsum(rnorm(n)))
## 
## > y <- c(0,cumsum(rnorm(n)))
## 
## > xx <- c(0:n, n:0)
## 
## > yy <- c(x, rev(y))
## 
## > plot(xx, yy, type="n", xlab="Time", ylab="Distance")

plot of chunk unnamed-chunk-1

## 
## > polygon(xx, yy, col="gray")
## 
## > title("Distance Between Brownian Motions")
## 
## > ## Colored plot margins, axis labels and titles.    You do need to be
## > ## careful with these kinds of effects.    It's easy to go completely
## > ## over the top and you can end up with your lunch all over the keyboard.
## > ## On the other hand, my market research clients love it.
## > 
## > x <- c(0.00, 0.40, 0.86, 0.85, 0.69, 0.48, 0.54, 1.09, 1.11, 1.73, 2.05, 2.02)
## 
## > par(bg="lightgray")
## 
## > plot(x, type="n", axes=FALSE, ann=FALSE)

plot of chunk unnamed-chunk-1

## 
## > usr <- par("usr")
## 
## > rect(usr[1], usr[3], usr[2], usr[4], col="cornsilk", border="black")
## 
## > lines(x, col="blue")
## 
## > points(x, pch=21, bg="lightcyan", cex=1.25)
## 
## > axis(2, col.axis="blue", las=1)
## 
## > axis(1, at=1:12, lab=month.abb, col.axis="blue")
## 
## > box()
## 
## > title(main= "The Level of Interest in R", font.main=4, col.main="red")
## 
## > title(xlab= "1996", col.lab="red")
## 
## > ## A filled histogram, showing how to change the font used for the
## > ## main title without changing the other annotation.
## > 
## > par(bg="cornsilk")
## 
## > x <- rnorm(1000)
## 
## > hist(x, xlim=range(-4, 4, x), col="lavender", main="")

plot of chunk unnamed-chunk-1

## 
## > title(main="1000 Normal Random Variates", font.main=3)
## 
## > ## A scatterplot matrix
## > ## The good old Iris data (yet again)
## > 
## > pairs(iris[1:4], main="Edgar Anderson's Iris Data", font.main=4, pch=19)

plot of chunk unnamed-chunk-1

## 
## > pairs(iris[1:4], main="Edgar Anderson's Iris Data", pch=21,
## +       bg = c("red", "green3", "blue")[unclass(iris$Species)])

plot of chunk unnamed-chunk-1

## 
## > ## Contour plotting
## > ## This produces a topographic map of one of Auckland's many volcanic "peaks".
## > 
## > x <- 10*1:nrow(volcano)
## 
## > y <- 10*1:ncol(volcano)
## 
## > lev <- pretty(range(volcano), 10)
## 
## > par(bg = "lightcyan")
## 
## > pin <- par("pin")
## 
## > xdelta <- diff(range(x))
## 
## > ydelta <- diff(range(y))
## 
## > xscale <- pin[1]/xdelta
## 
## > yscale <- pin[2]/ydelta
## 
## > scale <- min(xscale, yscale)
## 
## > xadd <- 0.5*(pin[1]/scale - xdelta)
## 
## > yadd <- 0.5*(pin[2]/scale - ydelta)
## 
## > plot(numeric(0), numeric(0),
## +      xlim = range(x)+c(-1,1)*xadd, ylim = range(y)+c(-1,1)*yadd,
## +      type = "n", ann = FALSE)

plot of chunk unnamed-chunk-1

## 
## > usr <- par("usr")
## 
## > rect(usr[1], usr[3], usr[2], usr[4], col="green3")
## 
## > contour(x, y, volcano, levels = lev, col="yellow", lty="solid", add=TRUE)
## 
## > box()
## 
## > title("A Topographic Map of Maunga Whau", font= 4)
## 
## > title(xlab = "Meters North", ylab = "Meters West", font= 3)
## 
## > mtext("10 Meter Contour Spacing", side=3, line=0.35, outer=FALSE,
## +       at = mean(par("usr")[1:2]), cex=0.7, font=3)
## 
## > ## Conditioning plots
## > 
## > par(bg="cornsilk")
## 
## > coplot(lat ~ long | depth, data = quakes, pch = 21, bg = "green3")

plot of chunk unnamed-chunk-1

## 
## > par(opar)

數學運算

# 數字相加
3 + 8
## [1] 11
# 數字相減
3 - 8
## [1] -5
# 數字相乘
5 * 5
## [1] 25
# 數字相除
11 / 2
## [1] 5.5
# 指數
2^10
## [1] 1024
# 取餘數
11%%2
## [1] 1

設定變數

# 指定變數
a = 3
a
## [1] 3
# 變數相加
b = 5
c = a + b
c
## [1] 8

基礎資料型態

# 數值型態
numer = 17.8
# 字串型態
char = "Hello World"
# 布林邏輯
logic = TRUE

# 使用class 檢查資料型態
class(logic)
## [1] "logical"

不同型態資料做運算

card_length = 3
card_width = "5 inches"

#重新將card_width 指到5
card_width = 5
card_length * card_width
## [1] 15

向量 (Vector)

# 不同型態的向量
height_vec = c(180,169,173)
name_vec = c("Brian", "Toby", "Sherry")

向量的運算

x=c(1,2,3,7)
y=c(2,3,5,1)

x+y 
## [1] 3 5 8 8
x*y
## [1]  2  6 15  7
x-y
## [1] -1 -1 -2  6
x/y
## [1] 0.5000 0.6667 0.6000 7.0000

將向量作加總

# 透過sum 將向量資料作加總
x = c(1,2,3,7) 
sum(x)
## [1] 13

指定名稱

height_vec = c(180,169,173)
height_vec
## [1] 180 169 173
names(height_vec) = c("Brian", "Toby", "Sherry")
height_vec
##  Brian   Toby Sherry 
##    180    169    173
name_vec = c("Brian", "Toby", "Sherry")
names(height_vec) = name_vec

判斷向量內容是否符合條件

height_vec > 175
##  Brian   Toby Sherry 
##   TRUE  FALSE  FALSE
height_vec < 175
##  Brian   Toby Sherry 
##  FALSE   TRUE   TRUE
height_vec >= 175
##  Brian   Toby Sherry 
##   TRUE  FALSE  FALSE
height_vec <= 175
##  Brian   Toby Sherry 
##  FALSE   TRUE   TRUE
height_vec == 180
##  Brian   Toby Sherry 
##   TRUE  FALSE  FALSE
height_vec != 180
##  Brian   Toby Sherry 
##  FALSE   TRUE   TRUE

自動產生向量

x = 1:20
x
##  [1]  1  2  3  4  5  6  7  8  9 10 11 12 13 14 15 16 17 18 19 20
y = seq(1,20)
y
##  [1]  1  2  3  4  5  6  7  8  9 10 11 12 13 14 15 16 17 18 19 20

seq()

seq(1,20,2)
##  [1]  1  3  5  7  9 11 13 15 17 19
seq(1,3.5, by =0.5)
## [1] 1.0 1.5 2.0 2.5 3.0 3.5
seq(1,10,length=2)
## [1]  1 10

rep()

rep(c(5,8),3)
## [1] 5 8 5 8 5 8
rep(c(1,2), each=2)
## [1] 1 1 2 2
rep_len(c(1,2), 5)
## [1] 1 2 1 2 1

產生初始向量

vector("numeric", length = 10)
##  [1] 0 0 0 0 0 0 0 0 0 0
vector("character", length = 10) 
##  [1] "" "" "" "" "" "" "" "" "" ""
vector("logical", length = 10) 
##  [1] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE

產生陣列

matrix(1:9, byrow=TRUE, nrow=3)
##      [,1] [,2] [,3]
## [1,]    1    2    3
## [2,]    4    5    6
## [3,]    7    8    9
matrix(1:9, nrow=3)
##      [,1] [,2] [,3]
## [1,]    1    4    7
## [2,]    2    5    8
## [3,]    3    6    9

建立陣列

kevin = c(85,73)
marry = c(72,64)
jerry = c(59,66)

mat = matrix(c(kevin, marry, jerry), nrow=3, byrow= TRUE)

新增欄位與列的名稱

colnames(mat) = c('first', 'second')
rownames(mat) = c('kevin', 'marry', 'jerry')
mat2 = matrix(c(kevin, marry, jerry), nrow=3, byrow=TRUE, 
dimnames=list(c('kevin', 'marry', 'jerry'),c('first', 'second')))

取矩陣維度、列與欄數

dim(mat2)
## [1] 3 2
nrow(mat2)
## [1] 3
ncol(mat2)
## [1] 2

依欄或列取矩陣資料

#取第一列
mat2[1,] 
##  first second 
##     85     73
#取第一行
mat2[,1]
## kevin marry jerry 
##    85    72    59
#取第二、三列
mat2[2:3,]
##       first second
## marry    72     64
## jerry    59     66
#取第二列第一行的元素
mat2[2,1]
## [1] 72

新增列與行

mat3 = rbind(mat2, c(78,63))
rownames(mat3)[nrow(mat3)] = 'sam'
mat3
##       first second
## kevin    85     73
## marry    72     64
## jerry    59     66
## sam      78     63
mat4 = cbind(mat2,c(82,77,70))
colnames(mat4)[ncol(mat4)] = 'third'
mat4
##       first second third
## kevin    85     73    82
## marry    72     64    77
## jerry    59     66    70

使用rowSums 及colSums

rowSums(mat2)
## kevin marry jerry 
##   158   136   125
colSums(mat2)
##  first second 
##    216    203

矩陣運算

#矩陣宣告
m1 = matrix(1:4, byrow=TRUE, nrow=2)
m2 = matrix(5:8, byrow=TRUE, nrow=2)

#矩陣運算
m1 + m2
##      [,1] [,2]
## [1,]    6    8
## [2,]   10   12
m1 - m2
##      [,1] [,2]
## [1,]   -4   -4
## [2,]   -4   -4
m1 * m2
##      [,1] [,2]
## [1,]    5   12
## [2,]   21   32
m1 / m2
##        [,1]   [,2]
## [1,] 0.2000 0.3333
## [2,] 0.4286 0.5000

矩陣乘積

# m1 X m2 
m1 %*% m2
##      [,1] [,2]
## [1,]   19   22
## [2,]   43   50

矩陣轉置

#t()
t(m1)
##      [,1] [,2]
## [1,]    1    3
## [2,]    2    4
t(m2)
##      [,1] [,2]
## [1,]    5    7
## [2,]    6    8

將資料轉換為類別資料(Factor)

weather= c("sunny","rainy", "cloudy", "rainy", "cloudy")
weather_category = factor(weather)
weather_category
## [1] sunny  rainy  cloudy rainy  cloudy
## Levels: cloudy rainy sunny

有順序的階層

temperature = c("Low", "High", "High", "Medium", "Low", "Medium")
temperature_category = factor(temperature, order = TRUE, levels = c("Low", "Medium", "High"))
temperature_category
## [1] Low    High   High   Medium Low    Medium
## Levels: Low < Medium < High
temperature_category[3] > temperature_category[1]
## [1] TRUE
temperature_category[4] > temperature_category[3]
## [1] FALSE

觀看類別

levels(weather_category)
## [1] "cloudy" "rainy"  "sunny"
levels(temperature_category)
## [1] "Low"    "Medium" "High"

快速轉換類別名稱

weather= c("s","r", "c", "r", "c")
weather_factor = factor(weather)
levels(weather_factor) = c("cloudy","rainy","sunny")
weather_factor
## [1] sunny  rainy  cloudy rainy  cloudy
## Levels: cloudy rainy sunny

建立data frame

df = data.frame(a=c(1,2,3,4,5),b=c(2,3,4,5,6))
df
##   a b
## 1 1 2
## 2 2 3
## 3 3 4
## 4 4 5
## 5 5 6

使用R 內建的資料集

#表列資料集
data()

#使用資料集
data(iris)

#觀察讀取到的資料集型態
class(iris)
## [1] "data.frame"

觀看資料集的前幾筆資料與後幾筆資料

#觀看前幾筆資料
head(iris)
##   Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## 1          5.1         3.5          1.4         0.2  setosa
## 2          4.9         3.0          1.4         0.2  setosa
## 3          4.7         3.2          1.3         0.2  setosa
## 4          4.6         3.1          1.5         0.2  setosa
## 5          5.0         3.6          1.4         0.2  setosa
## 6          5.4         3.9          1.7         0.4  setosa
head(iris, 10)
##    Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## 1           5.1         3.5          1.4         0.2  setosa
## 2           4.9         3.0          1.4         0.2  setosa
## 3           4.7         3.2          1.3         0.2  setosa
## 4           4.6         3.1          1.5         0.2  setosa
## 5           5.0         3.6          1.4         0.2  setosa
## 6           5.4         3.9          1.7         0.4  setosa
## 7           4.6         3.4          1.4         0.3  setosa
## 8           5.0         3.4          1.5         0.2  setosa
## 9           4.4         2.9          1.4         0.2  setosa
## 10          4.9         3.1          1.5         0.1  setosa
#觀看後幾筆資料
tail(iris)
##     Sepal.Length Sepal.Width Petal.Length Petal.Width   Species
## 145          6.7         3.3          5.7         2.5 virginica
## 146          6.7         3.0          5.2         2.3 virginica
## 147          6.3         2.5          5.0         1.9 virginica
## 148          6.5         3.0          5.2         2.0 virginica
## 149          6.2         3.4          5.4         2.3 virginica
## 150          5.9         3.0          5.1         1.8 virginica
tail(iris, 10)
##     Sepal.Length Sepal.Width Petal.Length Petal.Width   Species
## 141          6.7         3.1          5.6         2.4 virginica
## 142          6.9         3.1          5.1         2.3 virginica
## 143          5.8         2.7          5.1         1.9 virginica
## 144          6.8         3.2          5.9         2.3 virginica
## 145          6.7         3.3          5.7         2.5 virginica
## 146          6.7         3.0          5.2         2.3 virginica
## 147          6.3         2.5          5.0         1.9 virginica
## 148          6.5         3.0          5.2         2.0 virginica
## 149          6.2         3.4          5.4         2.3 virginica
## 150          5.9         3.0          5.1         1.8 virginica

檢視資料的架構

str(iris)
## 'data.frame':    150 obs. of  5 variables:
##  $ Sepal.Length: num  5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...
##  $ Sepal.Width : num  3.5 3 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 ...
##  $ Petal.Length: num  1.4 1.4 1.3 1.5 1.4 1.7 1.4 1.5 1.4 1.5 ...
##  $ Petal.Width : num  0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
##  $ Species     : Factor w/ 3 levels "setosa","versicolor",..: 1 1 1 1 1 1 1 1 1 1 ...

取得指定列與行的部分資料集

#取前三列資料
iris[1:3,]
##   Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## 1          5.1         3.5          1.4         0.2  setosa
## 2          4.9         3.0          1.4         0.2  setosa
## 3          4.7         3.2          1.3         0.2  setosa
#取前三列第一行的資料
iris[1:3,1]
## [1] 5.1 4.9 4.7
#也可以用欄位名稱取值
iris[1:3,"Sepal.Length"]
## [1] 5.1 4.9 4.7
#取前兩行資料
head(iris[,1:2])
##   Sepal.Length Sepal.Width
## 1          5.1         3.5
## 2          4.9         3.0
## 3          4.7         3.2
## 4          4.6         3.1
## 5          5.0         3.6
## 6          5.4         3.9
#取特定欄位向量值
iris$"Sepal.Length"
##   [1] 5.1 4.9 4.7 4.6 5.0 5.4 4.6 5.0 4.4 4.9 5.4 4.8 4.8 4.3 5.8 5.7 5.4
##  [18] 5.1 5.7 5.1 5.4 5.1 4.6 5.1 4.8 5.0 5.0 5.2 5.2 4.7 4.8 5.4 5.2 5.5
##  [35] 4.9 5.0 5.5 4.9 4.4 5.1 5.0 4.5 4.4 5.0 5.1 4.8 5.1 4.6 5.3 5.0 7.0
##  [52] 6.4 6.9 5.5 6.5 5.7 6.3 4.9 6.6 5.2 5.0 5.9 6.0 6.1 5.6 6.7 5.6 5.8
##  [69] 6.2 5.6 5.9 6.1 6.3 6.1 6.4 6.6 6.8 6.7 6.0 5.7 5.5 5.5 5.8 6.0 5.4
##  [86] 6.0 6.7 6.3 5.6 5.5 5.5 6.1 5.8 5.0 5.6 5.7 5.7 6.2 5.1 5.7 6.3 5.8
## [103] 7.1 6.3 6.5 7.6 4.9 7.3 6.7 7.2 6.5 6.4 6.8 5.7 5.8 6.4 6.5 7.7 7.7
## [120] 6.0 6.9 5.6 7.7 6.3 6.7 7.2 6.2 6.1 6.4 7.2 7.4 7.9 6.4 6.3 6.1 7.7
## [137] 6.3 6.4 6.0 6.9 6.7 6.9 5.8 6.8 6.7 6.7 6.3 6.5 6.2 5.9

資料篩選

#取前五筆包含length 及 width 的資料
Five.Sepal.iris = iris[1:5, c("Sepal.Length", "Sepal.Width")]

#可以用條件做篩選
setosa.data = iris[iris$Species=="setosa",1:5]

#使用which 做資料篩選
which(iris$Species=="setosa")
##  [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] 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46
## [47] 47 48 49 50

使用subset 做資料篩選

#使用subset 取欄位
Sepal.data = subset(iris, select=c("Sepal.Length", "Sepal.Width"))

#以Species 做篩選條件
setosa.data = subset(iris, Species =="setosa")

#可以做篩選條件的組合 
example.data= subset(iris, Petal.Length <=1.4 & Petal.Width >= 0.2, select=Species )

資料合併

#以Merge 做資料合併
flower.type = data.frame(Species = "setosa", Flower = "iris")
merge(flower.type, iris[1:3,], by ="Species")
##   Species Flower Sepal.Length Sepal.Width Petal.Length Petal.Width
## 1  setosa   iris          5.1         3.5          1.4         0.2
## 2  setosa   iris          4.9         3.0          1.4         0.2
## 3  setosa   iris          4.7         3.2          1.3         0.2

資料排序

#用order做資料排序
iris[order(iris$Sepal.Length, decreasing = TRUE),]
##     Sepal.Length Sepal.Width Petal.Length Petal.Width    Species
## 132          7.9         3.8          6.4         2.0  virginica
## 118          7.7         3.8          6.7         2.2  virginica
## 119          7.7         2.6          6.9         2.3  virginica
## 123          7.7         2.8          6.7         2.0  virginica
## 136          7.7         3.0          6.1         2.3  virginica
## 106          7.6         3.0          6.6         2.1  virginica
## 131          7.4         2.8          6.1         1.9  virginica
## 108          7.3         2.9          6.3         1.8  virginica
## 110          7.2         3.6          6.1         2.5  virginica
## 126          7.2         3.2          6.0         1.8  virginica
## 130          7.2         3.0          5.8         1.6  virginica
## 103          7.1         3.0          5.9         2.1  virginica
## 51           7.0         3.2          4.7         1.4 versicolor
## 53           6.9         3.1          4.9         1.5 versicolor
## 121          6.9         3.2          5.7         2.3  virginica
## 140          6.9         3.1          5.4         2.1  virginica
## 142          6.9         3.1          5.1         2.3  virginica
## 77           6.8         2.8          4.8         1.4 versicolor
## 113          6.8         3.0          5.5         2.1  virginica
## 144          6.8         3.2          5.9         2.3  virginica
## 66           6.7         3.1          4.4         1.4 versicolor
## 78           6.7         3.0          5.0         1.7 versicolor
## 87           6.7         3.1          4.7         1.5 versicolor
## 109          6.7         2.5          5.8         1.8  virginica
## 125          6.7         3.3          5.7         2.1  virginica
## 141          6.7         3.1          5.6         2.4  virginica
## 145          6.7         3.3          5.7         2.5  virginica
## 146          6.7         3.0          5.2         2.3  virginica
## 59           6.6         2.9          4.6         1.3 versicolor
## 76           6.6         3.0          4.4         1.4 versicolor
## 55           6.5         2.8          4.6         1.5 versicolor
## 105          6.5         3.0          5.8         2.2  virginica
## 111          6.5         3.2          5.1         2.0  virginica
## 117          6.5         3.0          5.5         1.8  virginica
## 148          6.5         3.0          5.2         2.0  virginica
## 52           6.4         3.2          4.5         1.5 versicolor
## 75           6.4         2.9          4.3         1.3 versicolor
## 112          6.4         2.7          5.3         1.9  virginica
## 116          6.4         3.2          5.3         2.3  virginica
## 129          6.4         2.8          5.6         2.1  virginica
## 133          6.4         2.8          5.6         2.2  virginica
## 138          6.4         3.1          5.5         1.8  virginica
## 57           6.3         3.3          4.7         1.6 versicolor
## 73           6.3         2.5          4.9         1.5 versicolor
## 88           6.3         2.3          4.4         1.3 versicolor
## 101          6.3         3.3          6.0         2.5  virginica
## 104          6.3         2.9          5.6         1.8  virginica
## 124          6.3         2.7          4.9         1.8  virginica
## 134          6.3         2.8          5.1         1.5  virginica
## 137          6.3         3.4          5.6         2.4  virginica
## 147          6.3         2.5          5.0         1.9  virginica
## 69           6.2         2.2          4.5         1.5 versicolor
## 98           6.2         2.9          4.3         1.3 versicolor
## 127          6.2         2.8          4.8         1.8  virginica
## 149          6.2         3.4          5.4         2.3  virginica
## 64           6.1         2.9          4.7         1.4 versicolor
## 72           6.1         2.8          4.0         1.3 versicolor
## 74           6.1         2.8          4.7         1.2 versicolor
## 92           6.1         3.0          4.6         1.4 versicolor
## 128          6.1         3.0          4.9         1.8  virginica
## 135          6.1         2.6          5.6         1.4  virginica
## 63           6.0         2.2          4.0         1.0 versicolor
## 79           6.0         2.9          4.5         1.5 versicolor
## 84           6.0         2.7          5.1         1.6 versicolor
## 86           6.0         3.4          4.5         1.6 versicolor
## 120          6.0         2.2          5.0         1.5  virginica
## 139          6.0         3.0          4.8         1.8  virginica
## 62           5.9         3.0          4.2         1.5 versicolor
## 71           5.9         3.2          4.8         1.8 versicolor
## 150          5.9         3.0          5.1         1.8  virginica
## 15           5.8         4.0          1.2         0.2     setosa
## 68           5.8         2.7          4.1         1.0 versicolor
## 83           5.8         2.7          3.9         1.2 versicolor
## 93           5.8         2.6          4.0         1.2 versicolor
## 102          5.8         2.7          5.1         1.9  virginica
## 115          5.8         2.8          5.1         2.4  virginica
## 143          5.8         2.7          5.1         1.9  virginica
## 16           5.7         4.4          1.5         0.4     setosa
## 19           5.7         3.8          1.7         0.3     setosa
## 56           5.7         2.8          4.5         1.3 versicolor
## 80           5.7         2.6          3.5         1.0 versicolor
## 96           5.7         3.0          4.2         1.2 versicolor
## 97           5.7         2.9          4.2         1.3 versicolor
## 100          5.7         2.8          4.1         1.3 versicolor
## 114          5.7         2.5          5.0         2.0  virginica
## 65           5.6         2.9          3.6         1.3 versicolor
## 67           5.6         3.0          4.5         1.5 versicolor
## 70           5.6         2.5          3.9         1.1 versicolor
## 89           5.6         3.0          4.1         1.3 versicolor
## 95           5.6         2.7          4.2         1.3 versicolor
## 122          5.6         2.8          4.9         2.0  virginica
## 34           5.5         4.2          1.4         0.2     setosa
## 37           5.5         3.5          1.3         0.2     setosa
## 54           5.5         2.3          4.0         1.3 versicolor
## 81           5.5         2.4          3.8         1.1 versicolor
## 82           5.5         2.4          3.7         1.0 versicolor
## 90           5.5         2.5          4.0         1.3 versicolor
## 91           5.5         2.6          4.4         1.2 versicolor
## 6            5.4         3.9          1.7         0.4     setosa
## 11           5.4         3.7          1.5         0.2     setosa
## 17           5.4         3.9          1.3         0.4     setosa
## 21           5.4         3.4          1.7         0.2     setosa
## 32           5.4         3.4          1.5         0.4     setosa
## 85           5.4         3.0          4.5         1.5 versicolor
## 49           5.3         3.7          1.5         0.2     setosa
## 28           5.2         3.5          1.5         0.2     setosa
## 29           5.2         3.4          1.4         0.2     setosa
## 33           5.2         4.1          1.5         0.1     setosa
## 60           5.2         2.7          3.9         1.4 versicolor
## 1            5.1         3.5          1.4         0.2     setosa
## 18           5.1         3.5          1.4         0.3     setosa
## 20           5.1         3.8          1.5         0.3     setosa
## 22           5.1         3.7          1.5         0.4     setosa
## 24           5.1         3.3          1.7         0.5     setosa
## 40           5.1         3.4          1.5         0.2     setosa
## 45           5.1         3.8          1.9         0.4     setosa
## 47           5.1         3.8          1.6         0.2     setosa
## 99           5.1         2.5          3.0         1.1 versicolor
## 5            5.0         3.6          1.4         0.2     setosa
## 8            5.0         3.4          1.5         0.2     setosa
## 26           5.0         3.0          1.6         0.2     setosa
## 27           5.0         3.4          1.6         0.4     setosa
## 36           5.0         3.2          1.2         0.2     setosa
## 41           5.0         3.5          1.3         0.3     setosa
## 44           5.0         3.5          1.6         0.6     setosa
## 50           5.0         3.3          1.4         0.2     setosa
## 61           5.0         2.0          3.5         1.0 versicolor
## 94           5.0         2.3          3.3         1.0 versicolor
## 2            4.9         3.0          1.4         0.2     setosa
## 10           4.9         3.1          1.5         0.1     setosa
## 35           4.9         3.1          1.5         0.2     setosa
## 38           4.9         3.6          1.4         0.1     setosa
## 58           4.9         2.4          3.3         1.0 versicolor
## 107          4.9         2.5          4.5         1.7  virginica
## 12           4.8         3.4          1.6         0.2     setosa
## 13           4.8         3.0          1.4         0.1     setosa
## 25           4.8         3.4          1.9         0.2     setosa
## 31           4.8         3.1          1.6         0.2     setosa
## 46           4.8         3.0          1.4         0.3     setosa
## 3            4.7         3.2          1.3         0.2     setosa
## 30           4.7         3.2          1.6         0.2     setosa
## 4            4.6         3.1          1.5         0.2     setosa
## 7            4.6         3.4          1.4         0.3     setosa
## 23           4.6         3.6          1.0         0.2     setosa
## 48           4.6         3.2          1.4         0.2     setosa
## 42           4.5         2.3          1.3         0.3     setosa
## 9            4.4         2.9          1.4         0.2     setosa
## 39           4.4         3.0          1.3         0.2     setosa
## 43           4.4         3.2          1.3         0.2     setosa
## 14           4.3         3.0          1.1         0.1     setosa

plyr

library(plyr)
head(iris)
##   Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## 1          5.1         3.5          1.4         0.2  setosa
## 2          4.9         3.0          1.4         0.2  setosa
## 3          4.7         3.2          1.3         0.2  setosa
## 4          4.6         3.1          1.5         0.2  setosa
## 5          5.0         3.6          1.4         0.2  setosa
## 6          5.4         3.9          1.7         0.4  setosa
ddply(iris, c("Species"), function(df) mean(df$Sepal.Length))
##      Species    V1
## 1     setosa 5.006
## 2 versicolor 5.936
## 3  virginica 6.588

Reshape 與Aggregate

#install.packages("reshape")
library(reshape)
## 
## Attaching package: 'reshape'
## 
## The following objects are masked from 'package:plyr':
## 
##     rename, round_any
iris.melt <- melt(iris,id='Species')
cast(Species~variable,data=iris.melt,mean,
     subset=Species %in% c('setosa','versicolor'),
     margins='grand_row') 
##      Species Sepal.Length Sepal.Width Petal.Length Petal.Width
## 1     setosa        5.006       3.428        1.462       0.246
## 2 versicolor        5.936       2.770        4.260       1.326
## 3      (all)        5.471       3.099        2.861       0.786
aggregate(x=iris[,1:4],by=list(iris$Species),FUN=mean)
##      Group.1 Sepal.Length Sepal.Width Petal.Length Petal.Width
## 1     setosa        5.006       3.428        1.462       0.246
## 2 versicolor        5.936       2.770        4.260       1.326
## 3  virginica        6.588       2.974        5.552       2.026

清單(Lists)

item = list(thing="hat", size=8.25) 
item
## $thing
## [1] "hat"
## 
## $size
## [1] 8.25
test = list(name="Toby", score = c(87,57,72)) 
test$score
## [1] 87 57 72
test$score[2]
## [1] 57

清單(Lists)

flower= list(title="iris dataset", data=iris)
str(flower)
## List of 2
##  $ title: chr "iris dataset"
##  $ data :'data.frame':   150 obs. of  5 variables:
##   ..$ Sepal.Length: num [1:150] 5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...
##   ..$ Sepal.Width : num [1:150] 3.5 3 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 ...
##   ..$ Petal.Length: num [1:150] 1.4 1.4 1.3 1.5 1.4 1.7 1.4 1.5 1.4 1.5 ...
##   ..$ Petal.Width : num [1:150] 0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
##   ..$ Species     : Factor w/ 3 levels "setosa","versicolor",..: 1 1 1 1 1 1 1 1 1 1 ...
flower$data[1,"Sepal.Width"]
## [1] 3.5

讀取資料

#read.table 
test.data = read.table(header = TRUE, text = "
a b
1 2
3 4
")
#觀看資料屬性
class(test.data)
## [1] "data.frame"

寫入資料

#table
write.table(test.data, file = "test.txt" , sep = " ")

#csv
write.csv(test.data, file = "test.csv")

IF…ELSE…

x = 5;
if(x > 3){ 
    print("x > 3");
}else{
    print("x <= 3");
}
## [1] "x > 3"

IF…ELSE IF…ELSE

x = 5;
if(x > 3){ 
    print("x > 3");
} else if(x ==3){
    print("x == 3");
}else{
    print("x < 3");
}
## [1] "x > 3"

FOR 迴圈

#For 迴圈
for(i in 1:10){
     print (i);
}
## [1] 1
## [1] 2
## [1] 3
## [1] 4
## [1] 5
## [1] 6
## [1] 7
## [1] 8
## [1] 9
## [1] 10
#1~100的總和
sum = 0
for(i in 1:100){
     sum = sum + i;
}
sum
## [1] 5050

三種FOR 迴圈

x <- c("sunny","rainy", "cloudy", "rainy", "cloudy")

for(i in 1:length(x)) {
 print(x[i])
}
## [1] "sunny"
## [1] "rainy"
## [1] "cloudy"
## [1] "rainy"
## [1] "cloudy"
for(i in seq_along(x)) {
 print(x[i])
}
## [1] "sunny"
## [1] "rainy"
## [1] "cloudy"
## [1] "rainy"
## [1] "cloudy"
for(letter in x) {
 print(letter)
}
## [1] "sunny"
## [1] "rainy"
## [1] "cloudy"
## [1] "rainy"
## [1] "cloudy"

兩層for 迴圈

mat = matrix(1:9, byrow=TRUE, nrow=3)
for(i in seq_len(nrow(mat))) {
 for(j in seq_len(ncol(mat))) {
 print(mat[i, j])
 } 
}
## [1] 1
## [1] 2
## [1] 3
## [1] 4
## [1] 5
## [1] 6
## [1] 7
## [1] 8
## [1] 9

使用while 迴圈

sum = 0;
cnt = 0;
while(cnt <= 100){
    sum = sum + cnt;
    cnt = cnt + 1;
}
sum
## [1] 5050

使用Repeat

sum = 0;
cnt = 0;
repeat{
  cnt = cnt + 1;
    if(cnt > 100) break;
    sum = sum + cnt;
}
sum;    
## [1] 5050

Lazy Function

f = function(a, b) {
   a * 2
}
f(3)
## [1] 6
f = function(a, b) {
     print(a+ b)
}
#f(3)