Day 6 - Alex 2020-07-08

1.mutate(),新增列

mutate(test, new = Sepal.Length * Sepal.Width)

2.select(),按列筛选

(1)按列号筛选

select(test,1)
select(test,c(1,5))
select(test,Sepal.Length)

(2)按列名筛选

select(test, Petal.Length, Petal.Width)

vars <- c("Petal.Length", "Petal.Width")
select(test, one_of(vars))

3.filter()筛选行

filter(test, Species == "setosa")
filter(test, Species == "setosa"&Sepal.Length > 5 )
filter(test, Species %in% c("setosa","versicolor"))

4.arrange(),按某1列或某几列对整个表格进行排序

arrange(test, Sepal.Length)#默认从小到大排序
arrange(test, desc(Sepal.Length))#用desc从大到小

5.summarise()：汇总

summarise(test, mean(Sepal.Length), sd(Sepal.Length))# 计算Sepal.Length的平均值和标准差
group_by(test, Species)
summarise(group_by(test, Species),mean(Sepal.Length), sd(Sepal.Length))
----------------------------------分割线----------------------------------

dplyr两个实用技能

1：管道操作 %>% (cmd/ctr + shift + M)

test %>% 
  group_by(Species) %>% 
  summarise(mean(Sepal.Length), sd(Sepal.Length))

2：count统计某列的unique值

count(test,Species)
----------------------------------dplyr处理关系数据----------------------------------
即将2个表进行连接，注意：不要引入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.內连inner_join,取交集

inner_join(test1, test2, by = "x")
##   x z y
## 1 b A 2
## 2 e B 5
## 3 f C 6

2.左连left_join

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
left_join(test2, test1, by = 'x')
##   x y    z
## 1 a 1 
## 2 b 2    A
## 3 c 3 
## 4 d 4 
## 5 e 5    B
## 6 f 6    C

3.全连full_join

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 
## 6 c 
## 7 d

4.半连接：返回能够与y表匹配的x表所有记录semi_join

semi_join(x = test1, y = test2, by = 'x')
##   x z
## 1 b A
## 2 e B
## 3 f C

5.反连接：返回无法与y表匹配的x表的所记录anti_join

anti_join(x = test2, y = test1, by = 'x')
##   x y
## 1 a 1
## 2 c 3
## 3 d 4

6.简单合并

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)
##   x  y
## 1 1 10
## 2 2 20
## 3 3 30
## 4 4 40
## 5 5 50
## 6 6 60
bind_cols(test1, test3)
##   x  y   z
## 1 1 10 100
## 2 2 20 200
## 3 3 30 300
## 4 4 40 400