dplyr包常用函数操作

R语言中的有一个数据处理的强大的包，它就是 dplyr 包，dplyr包 像操作数据库一样操作 R，方便，轻松，快捷。

主要内容

1、选择数据表的列: select, rename
2、select 只会选择你指定的列
3、rename 则会改变列名, 并选择其他所有的列
4、选择数据表的行: filter
5、改变数据表的列: mutate, transmute
6、mutate 会保留改变前和改变后的列
7、transmute 则只会保留改变后的列, 而扔掉改变前的列
8、通过 group_by 和 summarize 函数可以把数据进行分组进行分析

---

library(dplyr)
knitr::kable(dplyr::filter(iris, Sepal.Length > 7))

Sepal.Length	Sepal.Width	Petal.Length	Petal.Width	Species
7.1	3.0	5.9	2.1	virginica
7.6	3.0	6.6	2.1	virginica
7.3	2.9	6.3	1.8	virginica
7.2	3.6	6.1	2.5	virginica
7.7	3.8	6.7	2.2	virginica
7.7	2.6	6.9	2.3	virginica
7.7	2.8	6.7	2.0	virginica
7.2	3.2	6.0	1.8	virginica
7.2	3.0	5.8	1.6	virginica
7.4	2.8	6.1	1.9	virginica
7.9	3.8	6.4	2.0	virginica
7.7	3.0	6.1	2.3	virginica

knitr::kable(dplyr::distinct(rbind(iris[1:10, ], iris[1:15, ])))  #unique

Sepal.Length	Sepal.Width	Petal.Length	Petal.Width	Species
5.1	3.5	1.4	0.2	setosa
4.9	3.0	1.4	0.2	setosa
4.7	3.2	1.3	0.2	setosa
4.6	3.1	1.5	0.2	setosa
5.0	3.6	1.4	0.2	setosa
5.4	3.9	1.7	0.4	setosa
4.6	3.4	1.4	0.3	setosa
5.0	3.4	1.5	0.2	setosa
4.4	2.9	1.4	0.2	setosa
4.9	3.1	1.5	0.1	setosa
5.4	3.7	1.5	0.2	setosa
4.8	3.4	1.6	0.2	setosa
4.8	3.0	1.4	0.1	setosa
4.3	3.0	1.1	0.1	setosa
5.8	4.0	1.2	0.2	setosa

knitr::kable(iris %>% select(Species, starts_with("Petal")) %>% filter(Species == 
    "setosa"))

Species	Petal.Length	Petal.Width
setosa	1.4	0.2
setosa	1.4	0.2
setosa	1.3	0.2
setosa	1.5	0.2
setosa	1.4	0.2
setosa	1.7	0.4
setosa	1.4	0.3
setosa	1.5	0.2
setosa	1.4	0.2
setosa	1.5	0.1
setosa	1.5	0.2
setosa	1.6	0.2
setosa	1.4	0.1
setosa	1.1	0.1
setosa	1.2	0.2
setosa	1.5	0.4
setosa	1.3	0.4
setosa	1.4	0.3
setosa	1.7	0.3
setosa	1.5	0.3
setosa	1.7	0.2
setosa	1.5	0.4
setosa	1.0	0.2
setosa	1.7	0.5
setosa	1.9	0.2
setosa	1.6	0.2
setosa	1.6	0.4
setosa	1.5	0.2
setosa	1.4	0.2
setosa	1.6	0.2
setosa	1.6	0.2
setosa	1.5	0.4
setosa	1.5	0.1
setosa	1.4	0.2
setosa	1.5	0.2
setosa	1.2	0.2
setosa	1.3	0.2
setosa	1.4	0.1
setosa	1.3	0.2
setosa	1.5	0.2
setosa	1.3	0.3
setosa	1.3	0.3
setosa	1.3	0.2
setosa	1.6	0.6
setosa	1.9	0.4
setosa	1.4	0.3
setosa	1.6	0.2
setosa	1.4	0.2
setosa	1.5	0.2
setosa	1.4	0.2

knitr::kable(dplyr::slice(iris, 10:15))  #切片，行名不显示

Sepal.Length	Sepal.Width	Petal.Length	Petal.Width	Species
4.9	3.1	1.5	0.1	setosa
5.4	3.7	1.5	0.2	setosa
4.8	3.4	1.6	0.2	setosa
4.8	3.0	1.4	0.1	setosa
4.3	3.0	1.1	0.1	setosa
5.8	4.0	1.2	0.2	setosa

knitr::kable(dplyr::sample_n(iris, 10))  #随机抽取10个

Sepal.Length	Sepal.Width	Petal.Length	Petal.Width	Species
6.7	3.3	5.7	2.5	virginica
5.4	3.4	1.5	0.4	setosa
5.1	3.3	1.7	0.5	setosa
6.0	3.4	4.5	1.6	versicolor
6.7	2.5	5.8	1.8	virginica
5.7	2.8	4.1	1.3	versicolor
5.1	3.5	1.4	0.3	setosa
6.4	2.8	5.6	2.2	virginica
6.3	2.9	5.6	1.8	virginica
5.2	3.5	1.5	0.2	setosa

knitr::kable(dplyr::sample_frac(iris, 0.1))  #百分比抽样

Sepal.Length	Sepal.Width	Petal.Length	Petal.Width	Species
7.2	3.6	6.1	2.5	virginica
6.9	3.1	5.1	2.3	virginica
6.2	3.4	5.4	2.3	virginica
7.7	2.8	6.7	2.0	virginica
4.6	3.2	1.4	0.2	setosa
6.3	2.5	4.9	1.5	versicolor
5.7	2.6	3.5	1.0	versicolor
5.7	2.8	4.1	1.3	versicolor
4.7	3.2	1.6	0.2	setosa
6.3	2.8	5.1	1.5	virginica
6.9	3.1	4.9	1.5	versicolor
5.7	2.5	5.0	2.0	virginica
5.1	3.3	1.7	0.5	setosa
7.2	3.0	5.8	1.6	virginica
5.0	3.2	1.2	0.2	setosa

knitr::kable(head(dplyr::arrange(iris, Sepal.Length)))  #从小到大排序

Sepal.Length	Sepal.Width	Petal.Length	Petal.Width	Species
4.3	3.0	1.1	0.1	setosa
4.4	2.9	1.4	0.2	setosa
4.4	3.0	1.3	0.2	setosa
4.4	3.2	1.3	0.2	setosa
4.5	2.3	1.3	0.3	setosa
4.6	3.1	1.5	0.2	setosa

knitr::kable(head(dplyr::arrange(iris, desc(Sepal.Length))))

Sepal.Length	Sepal.Width	Petal.Length	Petal.Width	Species
7.9	3.8	6.4	2.0	virginica
7.7	3.8	6.7	2.2	virginica
7.7	2.6	6.9	2.3	virginica
7.7	2.8	6.7	2.0	virginica
7.7	3.0	6.1	2.3	virginica
7.6	3.0	6.6	2.1	virginica

knitr::kable(summarise(iris, avg = mean(Sepal.Length)))

avg
5.843333

knitr::kable(summarise(iris, sum = sum(Sepal.Length)))

sum
876.5

# %>% 管道符
knitr::kable(head(mtcars, 20) %>% tail())

	mpg	cyl	disp	hp	drat	wt	qsec	vs	am	gear	carb	Model
15	10.4	8	472.0	205	2.93	5.250	17.98	0	0	3	4	Cadillac Fleetwood
16	10.4	8	460.0	215	3.00	5.424	17.82	0	0	3	4	Lincoln Continental
17	14.7	8	440.0	230	3.23	5.345	17.42	0	0	3	4	Chrysler Imperial
18	32.4	4	78.7	66	4.08	2.200	19.47	1	1	4	1	Fiat 128
19	30.4	4	75.7	52	4.93	1.615	18.52	1	1	4	2	Honda Civic
20	33.9	4	71.1	65	4.22	1.835	19.90	1	1	4	1	Toyota Corolla

knitr::kable(head(dplyr::group_by(iris, Species)))

Sepal.Length	Sepal.Width	Petal.Length	Petal.Width	Species
5.1	3.5	1.4	0.2	setosa
4.9	3.0	1.4	0.2	setosa
4.7	3.2	1.3	0.2	setosa
4.6	3.1	1.5	0.2	setosa
5.0	3.6	1.4	0.2	setosa
5.4	3.9	1.7	0.4	setosa

knitr::kable(iris %>% group_by(Species) %>% summarise(avg = mean(Sepal.Width)) %>% 
    arrange(avg))

avg
3.057333

knitr::kable(head(dplyr::mutate(iris, new = Sepal.Length + Petal.Length)))  #增加列

Sepal.Length	Sepal.Width	Petal.Length	Petal.Width	Species	new
5.1	3.5	1.4	0.2	setosa	6.5
4.9	3.0	1.4	0.2	setosa	6.3
4.7	3.2	1.3	0.2	setosa	6.0
4.6	3.1	1.5	0.2	setosa	6.1
5.0	3.6	1.4	0.2	setosa	6.4
5.4	3.9	1.7	0.4	setosa	7.1

# Connect
a = data.frame(x1 = c("A", "B", "C"), x2 = c(1, 2, 3))
b = data.frame(x1 = c("A", "B", "D"), x3 = c(T, F, T))
knitr::kable(dplyr::left_join(a, b, by = "x1"))

x1	x2	x3
A	1	TRUE
B	2	FALSE
C	3	NA

knitr::kable(dplyr::full_join(a, b, by = "x1"))

x1	x2	x3
A	1	TRUE
B	2	FALSE
C	3	NA
D	NA	TRUE

knitr::kable(dplyr::semi_join(a, b, by = "x1"))

x1	x2
A	1
B	2

knitr::kable(dplyr::anti_join(a, b, by = "x1"))

x1	x2
C	3

first <- slice(mtcars, 1:5)
mtcars <- mutate(mtcars, Model = rownames(mtcars))
first <- slice(mtcars, 1:5)
second <- slice(mtcars, 4:8)
knitr::kable(intersect(first, second))

mpg	cyl	disp	hp	drat	wt	qsec	vs	am	gear	carb	Model
21.4	6	258	110	3.08	3.215	19.44	1	0	3	1	4
18.7	8	360	175	3.15	3.440	17.02	0	0	3	2	5

knitr::kable(union_all(first, second))

mpg	cyl	disp	hp	drat	wt	qsec	vs	am	gear	carb	Model
21.0	6	160.0	110	3.90	2.620	16.46	0	1	4	4	1
21.0	6	160.0	110	3.90	2.875	17.02	0	1	4	4	2
22.8	4	108.0	93	3.85	2.320	18.61	1	1	4	1	3
21.4	6	258.0	110	3.08	3.215	19.44	1	0	3	1	4
18.7	8	360.0	175	3.15	3.440	17.02	0	0	3	2	5
21.4	6	258.0	110	3.08	3.215	19.44	1	0	3	1	4
18.7	8	360.0	175	3.15	3.440	17.02	0	0	3	2	5
18.1	6	225.0	105	2.76	3.460	20.22	1	0	3	1	6
14.3	8	360.0	245	3.21	3.570	15.84	0	0	3	4	7
24.4	4	146.7	62	3.69	3.190	20.00	1	0	4	2	8

knitr::kable(union(first, second))

mpg	cyl	disp	hp	drat	wt	qsec	vs	am	gear	carb	Model
21.0	6	160.0	110	3.90	2.620	16.46	0	1	4	4	1
21.0	6	160.0	110	3.90	2.875	17.02	0	1	4	4	2
22.8	4	108.0	93	3.85	2.320	18.61	1	1	4	1	3
21.4	6	258.0	110	3.08	3.215	19.44	1	0	3	1	4
18.7	8	360.0	175	3.15	3.440	17.02	0	0	3	2	5
18.1	6	225.0	105	2.76	3.460	20.22	1	0	3	1	6
14.3	8	360.0	245	3.21	3.570	15.84	0	0	3	4	7
24.4	4	146.7	62	3.69	3.190	20.00	1	0	4	2	8

knitr::kable(setdiff(first, second))

mpg	cyl	disp	hp	drat	wt	qsec	vs	am	gear	carb	Model
21.0	6	160	110	3.90	2.620	16.46	0	1	4	4	1
21.0	6	160	110	3.90	2.875	17.02	0	1	4	4	2
22.8	4	108	93	3.85	2.320	18.61	1	1	4	1	3

knitr::kable(setdiff(second, first))

mpg	cyl	disp	hp	drat	wt	qsec	vs	am	gear	carb	Model
18.1	6	225.0	105	2.76	3.46	20.22	1	0	3	1	6
14.3	8	360.0	245	3.21	3.57	15.84	0	0	3	4	7
24.4	4	146.7	62	3.69	3.19	20.00	1	0	4	2	8