R_basic1

what is R? - https://zh.wikipedia.org/wiki/R%E8%AF%AD%E8%A8%80

R vs Python? - https://www.datacamp.com/community/tutorials/r-or-python-for-data-analysis

most popular programming language for analytics - http://www.kdnuggets.com/polls/2015/r-vs-python.html - http://www.kdnuggets.com/2016/06/r-python-top-analytics-data-mining-data-science-software.html

Kaggle - https://www.kaggle.com/

UCI dataset - https://archive.ics.uci.edu/ml/datasets.html

R intro

RDemo

#使用範例資料
data(anscombe)
#使用資料中x1,y1變數畫出點散布圖
plot(y1 ~ x1, data = anscombe)
#建立回歸模型並assign到lmfit變數中
lmfit <- lm(y1~x1, data=anscombe) 
#在點散佈圖上加上迴歸線
abline(lmfit, col="red")

Basic type

• numeric: 1,2,1.2
• integer: 1L,2L,3L
• character: “string”
• logical: TRUE,FALSE,T,F
• complex: 1+4i

Basic Objects

(由相同資料型態組成)

atomic:

• vector
• matrix
• factor

(可以有混合的資料型態)

recursive:

• dataframe
• list

R basic command

#文件查詢
help(package="base")
?base::sum
?sum
help.search("sum")
??sum

#範例演釋
demo()
#使用內建資料集
data()
#看現有變數
ls()

## [1] "anscombe" "lmfit"

#移除變數
rm()

x = c(1,2,3)
#查看資料型態
class(x)

## [1] "numeric"

#查看資料結構
str(x)

##  num [1:3] 1 2 3

Basic computing

3+8

## [1] 11

3-8

## [1] -5

3*8

## [1] 24

3/8

## [1] 0.375

1/0

## [1] Inf

11%%2

## [1] 1

3<4

## [1] TRUE

2==5

## [1] FALSE

T == TRUE

## [1] TRUE

Assignment

a = 3
a <- 3 # ( alt + - )
assign("a",3)

a / 2

## [1] 1.5

a = a / 2
a

## [1] 1.5

Vector

• R語言最基本的物件

character(5)  ## character vector of length 5

## [1] "" "" "" "" ""

numeric(5)

## [1] 0 0 0 0 0

logical(5)

## [1] FALSE FALSE FALSE FALSE FALSE

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] 0.5000000 0.6666667 0.6000000 7.0000000

x = c(1,2,3,7)
x + 10

## [1] 11 12 13 17

x + c(10)

## [1] 11 12 13 17

x + c(1,2)

## [1] 2 4 4 9

x + c(1,2,1,2)

## [1] 2 4 4 9

x == c(1,99,3,4)

## [1]  TRUE FALSE  TRUE FALSE

c(1,2,3)

## [1] 1 2 3

c(2,T,3+0i,"one")

## [1] "2"    "TRUE" "3+0i" "one"

c(2,T,3+0i)

## [1] 2+0i 1+0i 3+0i

c(c(1,2,3,4),c(5))

## [1] 1 2 3 4 5

x = c(1,2,3,4,NA)
is.na(x)

## [1] FALSE FALSE FALSE FALSE  TRUE

sum(x)

## [1] NA

sum(x, na.rm=T)

## [1] 10

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
height_vec > 175

##  Brian   Toby Sherry 
##   TRUE  FALSE  FALSE

height_vec / 100

##  Brian   Toby Sherry 
##   1.80   1.69   1.73

height_vec > 175 | height_vec < 170

##  Brian   Toby Sherry 
##   TRUE   TRUE  FALSE

height_vec < 175 & height_vec > 170

##  Brian   Toby Sherry 
##  FALSE  FALSE   TRUE

#R 的index從1開始
height_vec[c(1)] #index

## Brian 
##   180

height_vec['Brian'] #element name

## Brian 
##   180

height_vec[height_vec > 175] #condition (boolean vector)

## Brian 
##   180

seq() & rep() & paste()

1:20

##  [1]  1  2  3  4  5  6  7  8  9 10 11 12 13 14 15 16 17 18 19 20

seq(1,20)

##  [1]  1  2  3  4  5  6  7  8  9 10 11 12 13 14 15 16 17 18 19 20

20:1

##  [1] 20 19 18 17 16 15 14 13 12 11 10  9  8  7  6  5  4  3  2  1

?seq
seq(from=1,to=20,by=2)

##  [1]  1  3  5  7  9 11 13 15 17 19

seq(from=1,to=20,length=2)

## [1]  1 20

rep(1,5)

## [1] 1 1 1 1 1

?rep
rep(x=c(1,2), times=5)

##  [1] 1 2 1 2 1 2 1 2 1 2

rep(x=c(1,2), times=c(1,2))

## [1] 1 2 2

rep(x=c(1,2), each=5)

##  [1] 1 1 1 1 1 2 2 2 2 2

rep_len(x=c(1,2),length.out = 5)

## [1] 1 2 1 2 1

paste("the","big","bang","theory")

## [1] "the big bang theory"

paste("big","bang",sep="-")

## [1] "big-bang"

length(paste("the","big","bang","theory"))

## [1] 1

paste("big","bang",sep="")

## [1] "bigbang"

paste("big","bang",sep=";")

## [1] "big;bang"

paste(c("big","bang"),1:2)

## [1] "big 1"  "bang 2"

paste(c("big","bang"),1:2,collapse = "+" )

## [1] "big 1+bang 2"

length(paste(c("big","bang"),1:4,collapse = "+" ))

## [1] 1

Matrix

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

kevin = c(85,73)
marry = c(72,64)
jerry = c(59,66)
mat = matrix(c(kevin, marry, jerry), nrow=3, byrow= TRUE)
colnames(mat) = c('first', 'second')
rownames(mat) = c('kevin', 'marry', 'jerry')
mat

##       first second
## kevin    85     73
## marry    72     64
## jerry    59     66

#取得矩陣維度
dim(mat)

## [1] 3 2

#取得矩陣列數
nrow(mat)

## [1] 3

#取得矩陣欄數
ncol(mat)

## [1] 2

#矩陣轉置(transpose)
t(mat)

##        kevin marry jerry
## first     85    72    59
## second    73    64    66

#取第一列
mat[1,]

##  first second 
##     85     73

#取第一行
mat[,1]

## kevin marry jerry 
##    85    72    59

#取第一、二列
mat[1:2,]

##       first second
## kevin    85     73
## marry    72     64

#取kevin和jerry成績
mat[c('kevin','jerry'),]

##       first second
## kevin    85     73
## jerry    59     66

#取kevin和jerry成績的第一次考試成績
mat[c('kevin','jerry'),'first']

## kevin jerry 
##    85    59

#取得第一次考試成績不及格的人
mat[mat[,1] < 60,'first']

## [1] 59

rowSums(mat)

## kevin marry jerry 
##   158   136   125

colSums(mat)

##  first second 
##    216    203

rowMeans(mat)

## kevin marry jerry 
##  79.0  68.0  62.5

colMeans(mat)

##    first   second 
## 72.00000 67.66667

#新增列與行
mat2 = rbind(mat, c(78,63))
rownames(mat2)[nrow(mat2)] = 'sam'
mat2

##       first second
## kevin    85     73
## marry    72     64
## jerry    59     66
## sam      78     63

mat3 = cbind(mat2,c(82,77,70,64))
colnames(mat3)[ncol(mat3)] = 'third'
mat3

##       first second third
## kevin    85     73    82
## marry    72     64    77
## jerry    59     66    70
## sam      78     63    64

rowMeans(mat3)

##    kevin    marry    jerry      sam 
## 80.00000 71.00000 65.00000 68.33333

colMeans(mat3)

##  first second  third 
##  73.50  66.50  73.25

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

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,] 0.2000000 0.3333333
## [2,] 0.4285714 0.5000000

m1 %*% m2

##      [,1] [,2]
## [1,]   19   22
## [2,]   43   50

Factor

# syntax
weather= c("sunny","rainy", "cloudy", "rainy", "cloudy")
weather_category = factor(weather)
weather_category

## [1] sunny  rainy  cloudy rainy  cloudy
## Levels: cloudy rainy sunny

class(weather)

## [1] "character"

class(weather_category)

## [1] "factor"

# order
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

# change levels name
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

Dataframe

name <- c("Joe", "Bob", "Vicky")
age <- c(28, 26, 34)
gender <- c("Male","Male","Female")
df <- data.frame(name, age, gender)
class(df)

## [1] "data.frame"

str(df)

## 'data.frame':    3 obs. of  3 variables:
##  $ name  : Factor w/ 3 levels "Bob","Joe","Vicky": 2 1 3
##  $ age   : num  28 26 34
##  $ gender: Factor w/ 2 levels "Female","Male": 2 2 1

data(iris)
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

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

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

#取前三列Sepal.Length欄位的資料
iris[1:3,"Sepal.Length"]

## [1] 5.1 4.9 4.7

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

iris$"Sepal.Length"[1:3]

## [1] 5.1 4.9 4.7

#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]
str(setosa.data)

## 'data.frame':    50 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 ...

#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

#merge進行資料合併
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

df1 = data.frame(CustomerId = c(1:6), Product = c(rep("Toaster", 3), rep("Radio", 3)))
df2 = data.frame(CustomerId = c(2, 4, 6), State = c(rep("Alabama", 2), rep("Ohio", 1)))

#Inner join:
merge(x = df1, y= df2, by="CustomerId")

##   CustomerId Product   State
## 1          2 Toaster Alabama
## 2          4   Radio Alabama
## 3          6   Radio    Ohio

#Outer join: 
merge(x = df1, y = df2, by = "CustomerId", all = TRUE)

##   CustomerId Product   State
## 1          1 Toaster    <NA>
## 2          2 Toaster Alabama
## 3          3 Toaster    <NA>
## 4          4   Radio Alabama
## 5          5   Radio    <NA>
## 6          6   Radio    Ohio

#Left outer: 
merge(x = df1, y = df2, by = "CustomerId", all.x = TRUE)

##   CustomerId Product   State
## 1          1 Toaster    <NA>
## 2          2 Toaster Alabama
## 3          3 Toaster    <NA>
## 4          4   Radio Alabama
## 5          5   Radio    <NA>
## 6          6   Radio    Ohio

#Right outer: 
merge(x = df1, y = df2, by = "CustomerId", all.y = TRUE)

##   CustomerId Product   State
## 1          2 Toaster Alabama
## 2          4   Radio Alabama
## 3          6   Radio    Ohio

#Cross join: 
merge(x = df1, y = df2, by = NULL)

##    CustomerId.x Product CustomerId.y   State
## 1             1 Toaster            2 Alabama
## 2             2 Toaster            2 Alabama
## 3             3 Toaster            2 Alabama
## 4             4   Radio            2 Alabama
## 5             5   Radio            2 Alabama
## 6             6   Radio            2 Alabama
## 7             1 Toaster            4 Alabama
## 8             2 Toaster            4 Alabama
## 9             3 Toaster            4 Alabama
## 10            4   Radio            4 Alabama
## 11            5   Radio            4 Alabama
## 12            6   Radio            4 Alabama
## 13            1 Toaster            6    Ohio
## 14            2 Toaster            6    Ohio
## 15            3 Toaster            6    Ohio
## 16            4   Radio            6    Ohio
## 17            5   Radio            6    Ohio
## 18            6   Radio            6    Ohio

#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

sort(iris$Sepal.Length, decreasing = TRUE)

##   [1] 7.9 7.7 7.7 7.7 7.7 7.6 7.4 7.3 7.2 7.2 7.2 7.1 7.0 6.9 6.9 6.9 6.9
##  [18] 6.8 6.8 6.8 6.7 6.7 6.7 6.7 6.7 6.7 6.7 6.7 6.6 6.6 6.5 6.5 6.5 6.5
##  [35] 6.5 6.4 6.4 6.4 6.4 6.4 6.4 6.4 6.3 6.3 6.3 6.3 6.3 6.3 6.3 6.3 6.3
##  [52] 6.2 6.2 6.2 6.2 6.1 6.1 6.1 6.1 6.1 6.1 6.0 6.0 6.0 6.0 6.0 6.0 5.9
##  [69] 5.9 5.9 5.8 5.8 5.8 5.8 5.8 5.8 5.8 5.7 5.7 5.7 5.7 5.7 5.7 5.7 5.7
##  [86] 5.6 5.6 5.6 5.6 5.6 5.6 5.5 5.5 5.5 5.5 5.5 5.5 5.5 5.4 5.4 5.4 5.4
## [103] 5.4 5.4 5.3 5.2 5.2 5.2 5.2 5.1 5.1 5.1 5.1 5.1 5.1 5.1 5.1 5.1 5.0
## [120] 5.0 5.0 5.0 5.0 5.0 5.0 5.0 5.0 5.0 4.9 4.9 4.9 4.9 4.9 4.9 4.8 4.8
## [137] 4.8 4.8 4.8 4.7 4.7 4.6 4.6 4.6 4.6 4.5 4.4 4.4 4.4 4.3

#資料轉換
iris$Species_new = ifelse(iris$Species == c("setosa"), "IsSetosa","Notsetosa")
iris$Species_new

##   [1] "IsSetosa"  "IsSetosa"  "IsSetosa"  "IsSetosa"  "IsSetosa" 
##   [6] "IsSetosa"  "IsSetosa"  "IsSetosa"  "IsSetosa"  "IsSetosa" 
##  [11] "IsSetosa"  "IsSetosa"  "IsSetosa"  "IsSetosa"  "IsSetosa" 
##  [16] "IsSetosa"  "IsSetosa"  "IsSetosa"  "IsSetosa"  "IsSetosa" 
##  [21] "IsSetosa"  "IsSetosa"  "IsSetosa"  "IsSetosa"  "IsSetosa" 
##  [26] "IsSetosa"  "IsSetosa"  "IsSetosa"  "IsSetosa"  "IsSetosa" 
##  [31] "IsSetosa"  "IsSetosa"  "IsSetosa"  "IsSetosa"  "IsSetosa" 
##  [36] "IsSetosa"  "IsSetosa"  "IsSetosa"  "IsSetosa"  "IsSetosa" 
##  [41] "IsSetosa"  "IsSetosa"  "IsSetosa"  "IsSetosa"  "IsSetosa" 
##  [46] "IsSetosa"  "IsSetosa"  "IsSetosa"  "IsSetosa"  "IsSetosa" 
##  [51] "Notsetosa" "Notsetosa" "Notsetosa" "Notsetosa" "Notsetosa"
##  [56] "Notsetosa" "Notsetosa" "Notsetosa" "Notsetosa" "Notsetosa"
##  [61] "Notsetosa" "Notsetosa" "Notsetosa" "Notsetosa" "Notsetosa"
##  [66] "Notsetosa" "Notsetosa" "Notsetosa" "Notsetosa" "Notsetosa"
##  [71] "Notsetosa" "Notsetosa" "Notsetosa" "Notsetosa" "Notsetosa"
##  [76] "Notsetosa" "Notsetosa" "Notsetosa" "Notsetosa" "Notsetosa"
##  [81] "Notsetosa" "Notsetosa" "Notsetosa" "Notsetosa" "Notsetosa"
##  [86] "Notsetosa" "Notsetosa" "Notsetosa" "Notsetosa" "Notsetosa"
##  [91] "Notsetosa" "Notsetosa" "Notsetosa" "Notsetosa" "Notsetosa"
##  [96] "Notsetosa" "Notsetosa" "Notsetosa" "Notsetosa" "Notsetosa"
## [101] "Notsetosa" "Notsetosa" "Notsetosa" "Notsetosa" "Notsetosa"
## [106] "Notsetosa" "Notsetosa" "Notsetosa" "Notsetosa" "Notsetosa"
## [111] "Notsetosa" "Notsetosa" "Notsetosa" "Notsetosa" "Notsetosa"
## [116] "Notsetosa" "Notsetosa" "Notsetosa" "Notsetosa" "Notsetosa"
## [121] "Notsetosa" "Notsetosa" "Notsetosa" "Notsetosa" "Notsetosa"
## [126] "Notsetosa" "Notsetosa" "Notsetosa" "Notsetosa" "Notsetosa"
## [131] "Notsetosa" "Notsetosa" "Notsetosa" "Notsetosa" "Notsetosa"
## [136] "Notsetosa" "Notsetosa" "Notsetosa" "Notsetosa" "Notsetosa"
## [141] "Notsetosa" "Notsetosa" "Notsetosa" "Notsetosa" "Notsetosa"
## [146] "Notsetosa" "Notsetosa" "Notsetosa" "Notsetosa" "Notsetosa"

File read and write

# getwd()
setwd('~/lecture/riii')
# setwd("__your_working_directory_path__")
tw2330 = read.csv("data/2330.csv", header=TRUE)
test.data = read.table("data/match.txt" ,header = FALSE, sep="|")

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

List

item= list(thing='hat',size=8.25)
item$thing

## [1] "hat"

item$size

## [1] 8.25