练习dplyr包的常用方法
library(dplyr)
test <- iris[c(1:2,51:52,101:102),]
##--------------------dplyr五个基础函数---------------------#
#1、mutate()新增列
mutate(test, new = Sepal.Length * Sepal.Width)
#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 7.0 3.2 4.7 1.4 versicolor
#4 6.4 3.2 4.5 1.5 versicolor
#5 6.3 3.3 6.0 2.5 virginica
#6 5.8 2.7 5.1 1.9 virginica
#new
#1 17.85
#2 14.70
#3 22.40
#4 20.48
#5 20.79
#6 15.66
#2、select()按列筛选
select(test,1)
#Sepal.Length
#1 5.1
#2 4.9
#51 7.0
#52 6.4
#101 6.3
#102 5.8
select(test,c(1,5))
#Sepal.Length Species
#1 5.1 setosa
#2 4.9 setosa
#51 7.0 versicolor
#52 6.4 versicolor
#101 6.3 virginica
#102 5.8 virginica
select(test,Sepal.Length)
#Sepal.Length
#1 5.1
#2 4.9
#51 7.0
#52 6.4
#101 6.3
#102 5.8
select(test, Petal.Length, Petal.Width)
#Petal.Length Petal.Width
#1 1.4 0.2
#2 1.4 0.2
#51 4.7 1.4
#52 4.5 1.5
#101 6.0 2.5
#102 5.1 1.9
vars <- c("Petal.Length", "Petal.Width")
select(test, one_of(vars))
#Petal.Length Petal.Width
#1 1.4 0.2
#2 1.4 0.2
#51 4.7 1.4
#52 4.5 1.5
#101 6.0 2.5
#102 5.1 1.9
#3、filter()筛选行
filter(test, Species == "setosa")
#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
filter(test, Species == "setosa"&Sepal.Length >5)
#Sepal.Length Sepal.Width Petal.Length Petal.Width Species
#1 5.1 3.5 1.4 0.2 setosa
filter(test, Species %in% c("setosa","versicolor"))
#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 7.0 3.2 4.7 1.4 versicolor
#4 6.4 3.2 4.5 1.5 versicolor
#4、arrange(),按某1列或某几列对整个表格进行排序
arrange(test, Sepal.Length) ##默认排序为从小到大
arrange(test, desc(Sepal.Length)) ##使用desc进行从大到小排序
#Sepal.Length Sepal.Width Petal.Length Petal.Width Species
#1 7.0 3.2 4.7 1.4 versicolor
#2 6.4 3.2 4.5 1.5 versicolor
#3 6.3 3.3 6.0 2.5 virginica
#4 5.8 2.7 5.1 1.9 virginica
#5 5.1 3.5 1.4 0.2 setosa
#6 4.9 3.0 1.4 0.2 setosa
#5、summarise()汇总
summarise(test, mean(Sepal.Length), sd(Sepal.Length))
#mean(Sepal.Length) sd(Sepal.Length)
#1 5.916667 0.8084965
###（先按照species分组，再计算每组sepal.length的平均值与标准差）
group_by(test,Species)
# A tibble: 6 x 5
# Groups: Species [3]
#Sepal.Length Sepal.Width Petal.Length Petal.Width Species
#* <dbl> <dbl> <dbl> <dbl> <fct>
# 1 5.1 3.5 1.4 0.2 setosa
#2 4.9 3 1.4 0.2 setosa
#3 7 3.2 4.7 1.4 versicolor
#4 6.4 3.2 4.5 1.5 versicolor
#5 6.3 3.3 6 2.5 virginica
#6 5.8 2.7 5.1 1.9 virginica
summarise(group_by(test, Species), mean(Sepal.Length), sd(Sepal.Length))
#A tibble: 3 x 3
#Species `mean(Sepal.Length)` `sd(Sepal.Length)`
#<fct> <dbl> <dbl>
# 1 setosa 5 0.141
#2 versicolor 6.7 0.424
#3 virginica 6.05 0.354
#-----------------------dplyr使用功能--------------------------#
#（1）
test %>%
group_by(Species) %>%
summarise(mean(Sepal.Length), sd(Sepal.Length))
#A tibble: 3 x 3
#Species `mean(Sepal.Length)` `sd(Sepal.Length)`
#<fct> <dbl> <dbl>
# 1 setosa 5 0.141
#2 versicolor 6.7 0.424
#3 virginica 6.05 0.354
#（2）
count(test,Species)
#Species n
#<fct> <int>
# 1 setosa 2
#2 versicolor 2
#3 virginica 2
##-----------------------------dplyr处理关系数据--------------------#
##不能引入factor
options(stringsAsFactors = F)
test1 <- data.frame(x = c('b','e','f','x'),
z = c("A","B","C",'D'),
stringsAsFactors = F)
test1
# x z
#1 b A
#2 e B
#3 f C
#4 x D
test2 <- data.frame(x = c('a','b','c','d','e','f'),
y = c(1,2,3,4,5,6),
stringsAsFactors = F)
test2
# x y
#1 a 1
#2 b 2
#3 c 3
#4 d 4
#5 e 5
#6 f 6
#（1）inner_join (交集)
inner_join(test1, test2, by = "x")
# x z y
#1 b A 2
#2 e B 5
#3 f C 6
#（2）left_join (以左侧集合为主，右侧没有的以缺失值表示)
left_join(test1,test2,by = "x")
# x z y
#1 b A 2
#2 e B 5
#3 f C 6
#4 x D NA
#（3）full_join (并集)
full_join(test1,test2,by = "x")
# x z y
#1 b A 2
#2 e B 5
#3 f C 6
#4 x D NA
#5 a <NA> 1
#6 c <NA> 3
#7 d <NA> 4
#（4）semi_join 返回能够与y匹配的x表记录
semi_join(x = test1, y = test2, by = "x")
# x z
#1 b A
#2 e B
#3 f C
#（5） anti_join 返回无法与y表匹配的x表记录
anti_join(x = test2, y = test1, by = "x")
# x y
#1 a 1
#2 c 3
#3 d 4
#(6) 其他
test1 <- data.frame(x = c(1,2,3,4), y = c(10,20,30,40))
test1
# x y
# 1 1 10
# 2 2 20
# 3 3 30
# 4 4 40
test2 <- data.frame(x = c(5,6), y = c(50,60))
test2
# x y
#1 5 50
#2 6 60
test3 <- data.frame(z = c(100,200,300,400))
test3
#z
#1 100
#2 200
#3 300
#4 400
bind_rows(test1, test2) ##两集合列数相同
# x y
#1 1 10
#2 2 20
#3 3 30
#4 4 40
#5 5 50
#6 6 60
bind_cols(test1, test3) ##两集合行数相同
# x y z
#1 1 10 100
#2 2 20 200
#3 3 30 300
#4 4 40 400
内容来源--微信公众号生信星球
