R Demo
data("anscombe")
View(anscombe)
fit <- lm(y1 ~ x1, data = anscombe)
plot(y1 ~ x1, data = anscombe)
abline(fit, col = 'red')
數學運算
3 + 8
## [1] 11
3 - 8
## [1] -5
3 * 8
## [1] 24
3 / 8
## [1] 0.375
2 ^ 10
## [1] 1024
11 %% 2
## [1] 1
a <- 3
b = 2
c <- a+b
numer <- 17.8
class(numer)
## [1] "numeric"
char <- 'hello world'
class(char)
## [1] "character"
logic <- TRUE
class(logic)
## [1] "logical"
a <- 3
class(a)
## [1] "numeric"
a <- "hello world"
class(a)
## [1] "character"
card_length <- 3
card_width <- '5 inches'
#card_length * card_width
card_width <- 5
card_length * card_width
## [1] 15
RRP <- 35.99
Exchange <- 31.74
NTD <- RRP * Exchange
NTD
## [1] 1142.323
向量
name1 <- 'david'
name2 <- 'sherry'
name3 <- 'brian'
c()
## NULL
height_vec <- c(180,169,173)
name_vec <- c('Brian','Toby','Sherry')
height_vec
## [1] 180 169 173
height_vec[1]
## [1] 180
height_vec[2]
## [1] 169
height_vec[3]
## [1] 173
height_vec[c(1,3)]
## [1] 180 173
h_vec <- c(180,169,173, 'Joe')
h_vec
## [1] "180" "169" "173" "Joe"
class(h_vec)
## [1] "character"
x <- c(1,2,3,4)
y <- c(2,3,4,5)
x + y
## [1] 3 5 7 9
x - y
## [1] -1 -1 -1 -1
x * y
## [1] 2 6 12 20
x / y
## [1] 0.5000000 0.6666667 0.7500000 0.8000000
x + 3
## [1] 4 5 6 7
x + c(3)
## [1] 4 5 6 7
x + c(3,3,3,3)
## [1] 4 5 6 7
a <- 3
a <- c(3)
x + c(1,2)
## [1] 2 4 4 6
x + c(1,2,1,2)
## [1] 2 4 4 6
a <- c(1,2,3)
a <- c(1,2,3,4,5,6,7,8,9)
a <- 1:20
a
## [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
y <- seq(from = 1,to = 20)
a <- c(4,5,6,7,8)
seq_along(a)
## [1] 1 2 3 4 5
help(seq)
## starting httpd help server ... done
seq(0, 1, length.out = 11)
## [1] 0.0 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 1.0
seq(1, 9, by = 2)
## [1] 1 3 5 7 9
seq(1, 9, length.out = 3)
## [1] 1 5 9
help(seq)
?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
seq(1,10, length.out =2)
## [1] 1 10
seq(1,10, len =2)
## [1] 1 10
x <- c(1,2,3,5,7)
sum(x)
## [1] 18
sum(3,5)
## [1] 8
sum(3,5,7)
## [1] 15
?sum
x <- c(1,2,3,5,7, NA)
sum(x)
## [1] NA
sum(x, na.rm=TRUE)
## [1] 18
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
height_vec > 175
## Brian Toby Sherry
## TRUE FALSE FALSE
height_vec[height_vec > 175]
## Brian
## 180
height_vec < 175
## Brian Toby Sherry
## FALSE TRUE TRUE
height_vec[height_vec < 175]
## Toby Sherry
## 169 173
height_vec == 180
## Brian Toby Sherry
## TRUE FALSE FALSE
height_vec[height_vec == 180]
## Brian
## 180
height_vec != 180
## Brian Toby Sherry
## FALSE TRUE TRUE
height_vec[height_vec != 180]
## Toby Sherry
## 169 173
height_vec > 170 & height_vec < 180
## Brian Toby Sherry
## FALSE FALSE TRUE
height_vec >= 180 | height_vec < 170
## Brian Toby Sherry
## TRUE TRUE FALSE
height_vec > 175
## Brian Toby Sherry
## TRUE FALSE FALSE
which(height_vec > 175)
## Brian
## 1
height_vec[which(height_vec > 175)]
## Brian
## 180
height_vec[c(1)]
## Brian
## 180
計算BMI
height_vec <- c(180,169,173)
weight_vec <- c(73,87,43)
names_vec <- c('Brian', 'Toby', 'Sherry')
bmi_vec <- weight_vec / (height_vec / 100) ^ 2
bmi_vec[1]
## [1] 22.53086
names(bmi_vec) <- names_vec
bmi_vec[1]
## Brian
## 22.53086
bmi_vec['Brian']
## Brian
## 22.53086
bmi_vec[c('Brian')]
## Brian
## 22.53086
bmi_vec < 18.5
## Brian Toby Sherry
## FALSE FALSE TRUE
bmi_vec >= 24
## Brian Toby Sherry
## FALSE TRUE FALSE
(bmi_vec < 18.5) | (bmi_vec >= 24)
## Brian Toby Sherry
## FALSE TRUE TRUE
bmi_vec[(bmi_vec < 18.5) | (bmi_vec >= 24) ]
## Toby Sherry
## 30.46112 14.36734
?names
names(bmi_vec[(bmi_vec < 18.5) | (bmi_vec >= 24) ])
## [1] "Toby" "Sherry"
矩陣
kevin <- c(85,73)
marry <- c(72,64)
jerry <- c(59,66)
c(kevin, marry, jerry)
## [1] 85 73 72 64 59 66
mat <- matrix(
c(kevin, marry, jerry),
nrow =3,
byrow=TRUE)
matrix(1:9, nrow=3)
## [,1] [,2] [,3]
## [1,] 1 4 7
## [2,] 2 5 8
## [3,] 3 6 9
matrix(1:9, nrow=3, byrow=TRUE)
## [,1] [,2] [,3]
## [1,] 1 2 3
## [2,] 4 5 6
## [3,] 7 8 9
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
mat <- matrix(
c(kevin, marry, jerry),
nrow=3,
byrow=TRUE,
dimnames=list(
c('kevin', 'marry', 'jerry')
,c('first', 'second')))
dim(mat)
## [1] 3 2
nrow(mat)
## [1] 3
ncol(mat)
## [1] 2
mat[1,]
## first second
## 85 73
mat[,1]
## kevin marry jerry
## 85 72 59
mat[2:3,]
## first second
## marry 72 64
## jerry 59 66
mat[,1:2]
## first second
## kevin 85 73
## marry 72 64
## jerry 59 66
mat[c('kevin', 'marry'),'first']
## kevin marry
## 85 72
mat[c('kevin', 'marry'),c('first', 'second')]
## first second
## kevin 85 73
## marry 72 64
mat[c('kevin', 'marry'),c(1,2)]
## first second
## kevin 85 73
## marry 72 64
mat[c('kevin', 'marry'),c(TRUE,FALSE)]
## kevin marry
## 85 72
mat2 <- rbind(mat, c(78,63))
rownames(mat2)
## [1] "kevin" "marry" "jerry" ""
rownames(mat2)[4] <- 'sam'
mat2
## first second
## kevin 85 73
## marry 72 64
## jerry 59 66
## sam 78 63
mat
## first second
## kevin 85 73
## marry 72 64
## jerry 59 66
mat3 <- cbind(mat,c(82,77,70))
mat3
## first second
## kevin 85 73 82
## marry 72 64 77
## jerry 59 66 70
colnames(mat3)
## [1] "first" "second" ""
colnames(mat3)[3] <- 'third'
mat3
## first second third
## kevin 85 73 82
## marry 72 64 77
## jerry 59 66 70
m1 <- matrix(1:4, byrow=TRUE, nrow=2)
m2 <- matrix(5:8, byrow=TRUE, nrow=2)
m2
## [,1] [,2]
## [1,] 5 6
## [2,] 7 8
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
rowSums(mat)
## kevin marry jerry
## 158 136 125
colSums(mat)
## first second
## 216 203
m1 %*% m2
## [,1] [,2]
## [1,] 19 22
## [2,] 43 50
# 9 X 9
# 9 X 1 %*% 1 X 9 => 9 X 9
matrix(1:9, nrow = 9) %*% matrix(1:9, nrow = 1)
## [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9]
## [1,] 1 2 3 4 5 6 7 8 9
## [2,] 2 4 6 8 10 12 14 16 18
## [3,] 3 6 9 12 15 18 21 24 27
## [4,] 4 8 12 16 20 24 28 32 36
## [5,] 5 10 15 20 25 30 35 40 45
## [6,] 6 12 18 24 30 36 42 48 54
## [7,] 7 14 21 28 35 42 49 56 63
## [8,] 8 16 24 32 40 48 56 64 72
## [9,] 9 18 27 36 45 54 63 72 81
kevin <- c(85,73)
marry <- c(72,64)
jerry <- c(59,66)
mat <- matrix(c(kevin, marry, jerry), nrow=3, byrow= TRUE)
# method 1
mat[,1] * 0.4 + mat[,2] * 0.6
## [1] 77.8 67.2 63.2
# method 2
# 3 X 2 %*% 2 X 1 = 3 X 1
mat %*% matrix(c(0.4,0.6), nrow= 2)
## [,1]
## [1,] 77.8
## [2,] 67.2
## [3,] 63.2
階層
weather <- c("sunny","rainy"
, "cloudy", "rainy", "cloudy")
class(weather)
## [1] "character"
weather_category <- factor(weather)
weather_category
## [1] sunny rainy cloudy rainy cloudy
## Levels: cloudy rainy sunny
levels(weather_category)
## [1] "cloudy" "rainy" "sunny"
temperature <- c("Low", "High", "High", "Medium", "Low", "Medium")
temperature_category <- factor(temperature, order = TRUE, levels=c("Low", "Medium", "High"))
temperature_category[1]
## [1] Low
## Levels: Low < Medium < High
temperature_category[2]
## [1] High
## Levels: Low < Medium < High
temperature_category[2] > temperature_category[1]
## [1] TRUE
temperature_category[4]
## [1] Medium
## Levels: Low < Medium < High
temperature_category[3]
## [1] High
## Levels: Low < Medium < High
temperature_category[4] > temperature_category[3]
## [1] FALSE
levels(temperature_category)
## [1] "Low" "Medium" "High"
Data Frame
height <- c(180,169,173)
height
## [1] 180 169 173
class(height)
## [1] "numeric"
height <- c(height, 165 )
height
## [1] 180 169 173 165
class(height)
## [1] "numeric"
height <- c(height, 'hello' )
height
## [1] "180" "169" "173" "165" "hello"
class(height)
## [1] "character"
days <- c('mon','tue','wed','thu','fri')
temp <- c(22.2,21,23,24.3,25)
rain <- c(TRUE, TRUE, FALSE, FALSE, TRUE)
m <- matrix(c(days, temp, rain), nrow = 5)
class(m)
## [1] "matrix"
m
## [,1] [,2] [,3]
## [1,] "mon" "22.2" "TRUE"
## [2,] "tue" "21" "TRUE"
## [3,] "wed" "23" "FALSE"
## [4,] "thu" "24.3" "FALSE"
## [5,] "fri" "25" "TRUE"
mean(temp)
## [1] 23.1
#mean(m[,2])
df <- data.frame(days,temp,rain)
class(df)
## [1] "data.frame"
View(df)
str(df)
## 'data.frame': 5 obs. of 3 variables:
## $ days: Factor w/ 5 levels "fri","mon","thu",..: 2 4 5 3 1
## $ temp: num 22.2 21 23 24.3 25
## $ rain: logi TRUE TRUE FALSE FALSE TRUE
summary(df)
## days temp rain
## fri:1 Min. :21.0 Mode :logical
## mon:1 1st Qu.:22.2 FALSE:2
## thu:1 Median :23.0 TRUE :3
## tue:1 Mean :23.1
## wed:1 3rd Qu.:24.3
## Max. :25.0
data()
data(iris)
View(iris)
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 ...
class(iris)
## [1] "data.frame"
?head
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, 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
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,3)
## Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## 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
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
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[1:3,1]
## [1] 5.1 4.9 4.7
iris[1:3,'Sepal.Length']
## [1] 5.1 4.9 4.7
head(iris$Species)
## [1] setosa setosa setosa setosa setosa setosa
## Levels: setosa versicolor virginica
#iris$Species == 'setosa'
#which(iris$Species == 'setosa')
head(iris[iris$Species == 'setosa', c('Sepal.Length', 'Sepal.Width')])
## 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
head(iris[iris$Species == 'setosa', c(1,2)])
## Sepal.Length Sepal.Width
## 1 5.1 3.5
## 2 4.9 3.0
## 3 4.7 3.2
## 4 4.6 3.1
## 5 5.0 3.6
## 6 5.4 3.9
head(iris[iris$Species == 'setosa', 1:4])
## Sepal.Length Sepal.Width Petal.Length Petal.Width
## 1 5.1 3.5 1.4 0.2
## 2 4.9 3.0 1.4 0.2
## 3 4.7 3.2 1.3 0.2
## 4 4.6 3.1 1.5 0.2
## 5 5.0 3.6 1.4 0.2
## 6 5.4 3.9 1.7 0.4
head(iris[iris$Species == 'setosa', -5])
## Sepal.Length Sepal.Width Petal.Length Petal.Width
## 1 5.1 3.5 1.4 0.2
## 2 4.9 3.0 1.4 0.2
## 3 4.7 3.2 1.3 0.2
## 4 4.6 3.1 1.5 0.2
## 5 5.0 3.6 1.4 0.2
## 6 5.4 3.9 1.7 0.4
head(sort(iris$Sepal.Length))
## [1] 4.3 4.4 4.4 4.4 4.5 4.6
head(sort(iris$Sepal.Length, decreasing = TRUE))
## [1] 7.9 7.7 7.7 7.7 7.7 7.6
a <- c(70,50,60,80,90)
sort(a)
## [1] 50 60 70 80 90
order(a)
## [1] 2 3 1 4 5
order(a, decreasing = TRUE)
## [1] 5 4 1 3 2
a[order(a)]
## [1] 50 60 70 80 90
head(iris[order(iris$Sepal.Length), ])
## Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## 14 4.3 3.0 1.1 0.1 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
## 42 4.5 2.3 1.3 0.3 setosa
## 4 4.6 3.1 1.5 0.2 setosa
head(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
tw2330 <- read.csv('https://raw.githubusercontent.com/ywchiu/rtibame/master/Data/2330.TW.csv', na.strings = 'null')
class(tw2330)
## [1] "data.frame"
str(tw2330)
## 'data.frame': 1231 obs. of 7 variables:
## $ Date : Factor w/ 1231 levels "2013-08-12","2013-08-13",..: 1 2 3 4 5 6 7 8 9 10 ...
## $ Open : num 96.4 96 96 96.4 95.4 ...
## $ High : num 96.7 97.4 97.3 96.4 97.5 ...
## $ Low : num 95.6 96 95.8 95.3 95.2 ...
## $ Close : num 96 97.2 96.8 96 96.5 ...
## $ Adj.Close: num 81.8 82.8 82.4 81.8 82.2 ...
## $ Volume : int 33389000 34361000 41618000 42647000 37509000 49081000 41635000 60185000 44276000 18663000 ...
summary(tw2330)
## Date Open High Low
## 2013-08-12: 1 Min. : 93.0 Min. : 94.9 Min. : 92.9
## 2013-08-13: 1 1st Qu.:127.5 1st Qu.:128.5 1st Qu.:125.5
## 2013-08-14: 1 Median :149.0 Median :149.5 Median :147.5
## 2013-08-15: 1 Mean :164.3 Mean :165.4 Mean :163.0
## 2013-08-16: 1 3rd Qu.:204.0 3rd Qu.:205.0 3rd Qu.:203.0
## 2013-08-19: 1 Max. :263.0 Max. :266.0 Max. :262.5
## (Other) :1225 NA's :6 NA's :6 NA's :6
## Close Adj.Close Volume
## Min. : 94.4 Min. : 80.4 Min. : 0
## 1st Qu.:127.5 1st Qu.:112.8 1st Qu.: 21840151
## Median :148.5 Median :131.9 Median : 29134000
## Mean :164.3 Mean :151.0 Mean : 32469195
## 3rd Qu.:204.0 3rd Qu.:190.5 3rd Qu.: 39253000
## Max. :266.0 Max. :256.6 Max. :157081000
## NA's :6 NA's :6 NA's :6
head(tw2330[order(tw2330$Close),])
## Date Open High Low Close Adj.Close Volume
## 7 2013-08-20 95.2 95.4 94.4 94.4 80.39552 41635000
## 8 2013-08-22 93.0 94.9 92.9 94.5 80.48069 60185000
## 6 2013-08-19 95.5 96.1 95.3 95.5 81.33234 49081000
## 11 2013-08-27 96.0 96.8 95.6 95.6 81.41750 22435000
## 1 2013-08-12 96.4 96.7 95.6 96.0 81.75816 33389000
## 4 2013-08-15 96.4 96.4 95.3 96.0 81.75816 42647000
head(tw2330[order(tw2330$Close, decreasing = TRUE),])
## Date Open High Low Close Adj.Close Volume
## 1100 2018-01-23 262.5 266.0 262.5 266.0 256.6461 33527444
## 1099 2018-01-22 257.5 262.0 257.0 261.5 252.3044 43400509
## 1107 2018-02-01 257.5 261.0 257.0 259.5 250.3747 30559457
## 1108 2018-02-02 259.0 260.0 255.0 259.5 250.3747 25707560
## 1128 2018-03-13 255.5 259.0 255.0 259.0 249.8923 33756883
## 1104 2018-01-29 259.0 261.5 255.0 258.5 249.4099 30071234
plot(Close ~ Date, data = tw2330)
清單
list()
## list()
phone <- list(thing="iphone X" , height=5.65, width=2.79 )
phone$thing
## [1] "iphone X"
phone$height
## [1] 5.65
student <- list(name="Toby", score = c(87,57,72))
student$score
## [1] 87 57 72
(student$score ^ (1/2) ) * 10
## [1] 93.27379 75.49834 84.85281
li <- list(c(3,5,12), c(2,4,5,8,10))
li
## [[1]]
## [1] 3 5 12
##
## [[2]]
## [1] 2 4 5 8 10
li[[1]]
## [1] 3 5 12
li[[2]]
## [1] 2 4 5 8 10
student <- list(name="Toby", score = c(87,57,72))
student$name
## [1] "Toby"
student[[1]]
## [1] "Toby"
li <- list(c(3,5,12), c(2,4,5,8,10))
li
## [[1]]
## [1] 3 5 12
##
## [[2]]
## [1] 2 4 5 8 10
sum(li[[1]])
## [1] 20
sum(li[[2]])
## [1] 29
lapply(li, sum)
## [[1]]
## [1] 20
##
## [[2]]
## [1] 29
lapply(li, mean)
## [[1]]
## [1] 6.666667
##
## [[2]]
## [1] 5.8
lapply(li, min)
## [[1]]
## [1] 3
##
## [[2]]
## [1] 2
lapply(li, max)
## [[1]]
## [1] 12
##
## [[2]]
## [1] 10
流程控制
x <- 2
if(x > 3){
print('x > 3')
}else{
print('x <= 3')
}
## [1] "x <= 3"
x <-3
if(x > 3){
print('x > 3')
}else if (x == 3){
print('x == 3')
}else{
print('x < 3')
}
## [1] "x == 3"
1:10
## [1] 1 2 3 4 5 6 7 8 9 10
for(qoo in 1:10){
print(qoo)
}
## [1] 1
## [1] 2
## [1] 3
## [1] 4
## [1] 5
## [1] 6
## [1] 7
## [1] 8
## [1] 9
## [1] 10
## Bad Method
s <- 0
for(i in 1:100){
s <- s + i
}
s
## [1] 5050
## Good Method
sum(1:100)
## [1] 5050
x <- c("sunny","rainy"
, "cloudy", "rainy", "cloudy")
for(weather in x){
print(weather)
}
## [1] "sunny"
## [1] "rainy"
## [1] "cloudy"
## [1] "rainy"
## [1] "cloudy"
length(x)
## [1] 5
for(i in 1:length(x)) {
print(x[i])
}
## [1] "sunny"
## [1] "rainy"
## [1] "cloudy"
## [1] "rainy"
## [1] "cloudy"
seq_along(x)
## [1] 1 2 3 4 5
for(i in seq_along(x)) {
print(x[i])
}
## [1] "sunny"
## [1] "rainy"
## [1] "cloudy"
## [1] "rainy"
## [1] "cloudy"
cnt <- 0
s <- 0
while(cnt <= 100){
s <- s + cnt
cnt <- cnt + 1
}
s
## [1] 5050
cnt
## [1] 101
url <- 'https://tw.appledaily.com/new/realtime/'
paste(url, 1)
## [1] "https://tw.appledaily.com/new/realtime/ 1"
?paste
paste(url, 1, sep='')
## [1] "https://tw.appledaily.com/new/realtime/1"
paste0(url, 1)
## [1] "https://tw.appledaily.com/new/realtime/1"
for(i in 1:10){
print(paste(url,i, sep=''))
}
## [1] "https://tw.appledaily.com/new/realtime/1"
## [1] "https://tw.appledaily.com/new/realtime/2"
## [1] "https://tw.appledaily.com/new/realtime/3"
## [1] "https://tw.appledaily.com/new/realtime/4"
## [1] "https://tw.appledaily.com/new/realtime/5"
## [1] "https://tw.appledaily.com/new/realtime/6"
## [1] "https://tw.appledaily.com/new/realtime/7"
## [1] "https://tw.appledaily.com/new/realtime/8"
## [1] "https://tw.appledaily.com/new/realtime/9"
## [1] "https://tw.appledaily.com/new/realtime/10"
for(i in 1:10){
print(paste0(url,i))
}
## [1] "https://tw.appledaily.com/new/realtime/1"
## [1] "https://tw.appledaily.com/new/realtime/2"
## [1] "https://tw.appledaily.com/new/realtime/3"
## [1] "https://tw.appledaily.com/new/realtime/4"
## [1] "https://tw.appledaily.com/new/realtime/5"
## [1] "https://tw.appledaily.com/new/realtime/6"
## [1] "https://tw.appledaily.com/new/realtime/7"
## [1] "https://tw.appledaily.com/new/realtime/8"
## [1] "https://tw.appledaily.com/new/realtime/9"
## [1] "https://tw.appledaily.com/new/realtime/10"
函數
addNum <- function(a,b){
a + b
}
addNum(a = 3,b = 2)
## [1] 5
addNum(3,2)
## [1] 5
#addNum(3)
addNum <- function(a,b=2){
a + b
}
addNum(3,2)
## [1] 5
addNum(3)
## [1] 5
addNum <- function(a,b=2){
return(a + b)
}
addNum(3,2)
## [1] 5
f <- function(a, b) {
a * 2
}
f(3)
## [1] 6
f <- function(a, b) {
a + b
}
#f(3)
f <- function(a, b) {
a * 3 + b
}
f(2,3)
## [1] 9
f(b=2,a=3)
## [1] 11
f <- function(abb, bcc) {
abb * 3 + bcc
}
f(b=2,a=3)
## [1] 11
撰寫函式計算文章詞頻
stopwords <- c("a", "about", "above", "above", "across", "after", "afterwards", "again", "against", "all", "almost", "alone", "along", "already", "also","although","always","am","among", "amongst", "amoungst", "amount", "an", "and", "another", "any","anyhow","anyone","anything","anyway", "anywhere", "are", "around", "as", "at", "back","be","became", "because","become","becomes", "becoming", "been", "before", "beforehand", "behind", "being", "below", "beside", "besides", "between", "beyond", "bill", "both", "bottom","but", "by", "call", "can", "cannot", "cant", "co", "con", "could", "couldnt", "cry", "de", "describe", "detail", "do", "done", "down", "due", "during", "each", "eg", "eight", "either", "eleven","else", "elsewhere", "empty", "enough", "etc", "even", "ever", "every", "everyone", "everything", "everywhere", "except", "few", "fifteen", "fify", "fill", "find", "fire", "first", "five", "for", "former", "formerly", "forty", "found", "four", "from", "front", "full", "further", "get", "give", "go", "had", "has", "hasnt", "have", "he", "hence", "her", "here", "hereafter", "hereby", "herein", "hereupon", "hers", "herself", "him", "himself", "his", "how", "however", "hundred", "ie", "if", "in", "inc", "indeed", "interest", "into", "is", "it", "its", "itself", "keep", "last", "latter", "latterly", "least", "less", "ltd", "made", "many", "may", "me", "meanwhile", "might", "mill", "mine", "more", "moreover", "most", "mostly", "move", "much", "must", "my", "myself", "name", "namely", "neither", "never", "nevertheless", "next", "nine", "no", "nobody", "none", "noone", "nor", "not", "nothing", "now", "nowhere", "of", "off", "often", "on", "once", "one", "only", "onto", "or", "other", "others", "otherwise", "our", "ours", "ourselves", "out", "over", "own","part", "per", "perhaps", "please", "put", "rather", "re", "same", "see", "seem", "seemed", "seeming", "seems", "serious", "several", "she", "should", "show", "side", "since", "sincere", "six", "sixty", "so", "some", "somehow", "someone", "something", "sometime", "sometimes", "somewhere", "still", "such", "system", "take", "ten", "than", "that", "the", "their", "them", "themselves", "then", "thence", "there", "thereafter", "thereby", "therefore", "therein", "thereupon", "these", "they", "thickv", "thin", "third", "this", "those", "though", "three", "through", "throughout", "thru", "thus", "to", "together", "too", "top", "toward", "towards", "twelve", "twenty", "two", "un", "under", "until", "up", "upon", "us", "very", "via", "was", "we", "well", "were", "what", "whatever", "when", "whence", "whenever", "where", "whereafter", "whereas", "whereby", "wherein", "whereupon", "wherever", "whether", "which", "while", "whither", "who", "whoever", "whole", "whom", "whose", "why", "will", "with", "within", "without", "would", "yet", "you", "your", "yours", "yourself", "yourselves", "the")
## read articles
f <- file('https://raw.githubusercontent.com/ywchiu/rtibame/master/Data/trump.txt')
article <- readLines(f)
## Warning in readLines(f): 於 'https://raw.githubusercontent.com/ywchiu/
## rtibame/master/Data/trump.txt' 找到不完整的最後一列
close(f)
## split the words by delimiter
?strsplit()
article.split <- strsplit(tolower(article), split = ' ')
class(article.split)
## [1] "list"
## unlist the list
article.vec <- unlist(article.split)
## using table to count words
tb <- table(article.vec)
## filter out stopwords and words with charater length below 2
sort(tb[(! names(tb) %in% stopwords) & (nchar(names(tb)) >= 2)], decreasing = TRUE)[1:10]
## article.vec
## american america again. country great new people
## 11 10 8 6 6 6 6
## make president right
## 5 5 5
## Using table to count
a <- c(3,3,2,1,2,2,2,3)
?table
table(a)
## a
## 1 2 3
## 1 4 3
## Generate a word count function
wordcount <- function(article){
article.split <- strsplit(tolower(article), split = ' |,|\\.')
article.vec <- unlist(article.split)
tb <- table(article.vec)
sort(tb[(! names(tb) %in% stopwords) & (nchar(names(tb)) >= 2)], decreasing = TRUE)
}
#wordcount(article)
#install.packages('wordcloud2')
library(wordcloud2)
?wordcloud2
wordcloud2(wordcount(article), shape = 'star')
strsplit
a = 'hi, my name is David.'
?strsplit
strsplit(a, split = ' |,|\\.')
## [[1]]
## [1] "hi" "" "my" "name" "is" "David"
# ' |,|\\.' , split the string by " " OR "," OR "."