tidyr包常用函数操作

如何把蹂躏数据框

library(dplyr)
library(tidyr)
tdata <- mtcars[1:10, 1:3]
tdata <- data.frame(name = rownames(tdata), tdata)
knitr::kable(tdata)

	name	mpg	cyl	disp
Mazda RX4	Mazda RX4	21.0	6	160.0
Mazda RX4 Wag	Mazda RX4 Wag	21.0	6	160.0
Datsun 710	Datsun 710	22.8	4	108.0
Hornet 4 Drive	Hornet 4 Drive	21.4	6	258.0
Hornet Sportabout	Hornet Sportabout	18.7	8	360.0
Valiant	Valiant	18.1	6	225.0
Duster 360	Duster 360	14.3	8	360.0
Merc 240D	Merc 240D	24.4	4	146.7
Merc 230	Merc 230	22.8	4	140.8
Merc 280	Merc 280	19.2	6	167.6

gather宽变长，“key”和“value”都是新增的列，后面表示要合并的列

g1 <- gather(tdata, key = "Key", value = "Value", cyl, disp, 
    mpg)
knitr::kable(g1)

name	Key	Value
Mazda RX4	cyl	6.0
Mazda RX4 Wag	cyl	6.0
Datsun 710	cyl	4.0
Hornet 4 Drive	cyl	6.0
Hornet Sportabout	cyl	8.0
Valiant	cyl	6.0
Duster 360	cyl	8.0
Merc 240D	cyl	4.0
Merc 230	cyl	4.0
Merc 280	cyl	6.0
Mazda RX4	disp	160.0
Mazda RX4 Wag	disp	160.0
Datsun 710	disp	108.0
Hornet 4 Drive	disp	258.0
Hornet Sportabout	disp	360.0
Valiant	disp	225.0
Duster 360	disp	360.0
Merc 240D	disp	146.7
Merc 230	disp	140.8
Merc 280	disp	167.6
Mazda RX4	mpg	21.0
Mazda RX4 Wag	mpg	21.0
Datsun 710	mpg	22.8
Hornet 4 Drive	mpg	21.4
Hornet Sportabout	mpg	18.7
Valiant	mpg	18.1
Duster 360	mpg	14.3
Merc 240D	mpg	24.4
Merc 230	mpg	22.8
Merc 280	mpg	19.2

g2 <- gather(tdata, key = "Key", value = "Value", cyl:disp)
knitr::kable(g2)

name	mpg	Key	Value
Mazda RX4	21.0	cyl	6.0
Mazda RX4 Wag	21.0	cyl	6.0
Datsun 710	22.8	cyl	4.0
Hornet 4 Drive	21.4	cyl	6.0
Hornet Sportabout	18.7	cyl	8.0
Valiant	18.1	cyl	6.0
Duster 360	14.3	cyl	8.0
Merc 240D	24.4	cyl	4.0
Merc 230	22.8	cyl	4.0
Merc 280	19.2	cyl	6.0
Mazda RX4	21.0	disp	160.0
Mazda RX4 Wag	21.0	disp	160.0
Datsun 710	22.8	disp	108.0
Hornet 4 Drive	21.4	disp	258.0
Hornet Sportabout	18.7	disp	360.0
Valiant	18.1	disp	225.0
Duster 360	14.3	disp	360.0
Merc 240D	24.4	disp	146.7
Merc 230	22.8	disp	140.8
Merc 280	19.2	disp	167.6

g3 <- gather(tdata, key = "Key", value = "Value", mpg, cyl, 
    -disp)
knitr::kable(g3)

name	disp	Key	Value
Mazda RX4	160.0	mpg	21.0
Mazda RX4 Wag	160.0	mpg	21.0
Datsun 710	108.0	mpg	22.8
Hornet 4 Drive	258.0	mpg	21.4
Hornet Sportabout	360.0	mpg	18.7
Valiant	225.0	mpg	18.1
Duster 360	360.0	mpg	14.3
Merc 240D	146.7	mpg	24.4
Merc 230	140.8	mpg	22.8
Merc 280	167.6	mpg	19.2
Mazda RX4	160.0	cyl	6.0
Mazda RX4 Wag	160.0	cyl	6.0
Datsun 710	108.0	cyl	4.0
Hornet 4 Drive	258.0	cyl	6.0
Hornet Sportabout	360.0	cyl	8.0
Valiant	225.0	cyl	6.0
Duster 360	360.0	cyl	8.0
Merc 240D	146.7	cyl	4.0
Merc 230	140.8	cyl	4.0
Merc 280	167.6	cyl	6.0

spread长变宽，“key”和“value”表示要操作的列

gdata <- gather(tdata, key = "Key", value = "Value", 2:4)
s1 <- spread(gdata, key = "Key", value = "Value")
knitr::kable(s1)

name	cyl	disp	mpg
Datsun 710	4	108.0	22.8
Duster 360	8	360.0	14.3
Hornet 4 Drive	6	258.0	21.4
Hornet Sportabout	8	360.0	18.7
Mazda RX4	6	160.0	21.0
Mazda RX4 Wag	6	160.0	21.0
Merc 230	4	140.8	22.8
Merc 240D	4	146.7	24.4
Merc 280	6	167.6	19.2
Valiant	6	225.0	18.1

df <- data.frame(x = c(NA, "a.b", "a.d", "b.c"))
s2 <- separate(df, col = x, into = c("A", "B"))
knitr::kable(s2)

A	B
NA	NA
a	b
a	d
b	c

df <- data.frame(x = c(NA, "a.b-c", "a-d", "b-c"))
s3 <- separate(df, x, into = c("A", "B"), sep = "-")
knitr::kable(s3)

A	B
NA	NA
a.b	c
a	d
b	c

x <- separate(df, x, into = c("A", "B"), sep = "-")
u <- unite(x, col = "AB", A, B, sep = "-")
knitr::kable(u)

AB
NA-NA
a.b-c
a-d
b-c