今天的主題是學(xué)習(xí)R包，以dplyr為例學(xué)習(xí)操作　
library(dplyr)

一、dplyr五個基礎(chǔ)函數(shù)

使用內(nèi)置數(shù)據(jù)集iris的簡化版進行學(xué)習(xí)test <- iris[c(1:2,51:52,101:102),]

1、mutate(),新增列

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

2、select(),按列篩選

select(test,1)#按列號篩選，按第1列篩選
select(test,c(1,5))#按列號篩選，按第1、5列篩選
select(test,Sepal.Length)#按列名篩選
select(test, Petal.Length, Petal.Width)#按列名篩選
vars <- c("Petal.Length", "Petal.Width")#按列名篩選
select(test, one_of(vars))#按列名篩選

3、filter()，篩選行

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

4、arrange()，按某1列或某幾列對整個表格進行排序

arrange(test, Sepal.Length)#默認從小到大排序
arrange(test, desc(Sepal.Length))#用desc從大到小

5、summarise()：匯總

# 計算Sepal.Length的平均值和標(biāo)準(zhǔn)差
summarise(test, mean(Sepal.Length), sd(Sepal.Length))

# 先按照Species分組，計算每組Sepal.Length的平均值和標(biāo)準(zhǔn)差
group_by(test, Species)
summarise(group_by(test, Species),mean(Sepal.Length), sd(Sepal.Length))

二、dplyr兩個實用技能

1、管道操作 %>% (cmd/ctr + shift + M)

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

2、count統(tǒng)計某列的unique值

count(test,Species)

三、dplyr處理關(guān)系數(shù)據(jù)

1、內(nèi)連inner_join,取交集

options(stringsAsFactors = F)#不要引入factor
test1 <- data.frame(x = c('b','e','f','x'), 
                    z = c("A","B","C",'D'),
                    stringsAsFactors = F)
test1
test2 <- data.frame(x = c('a','b','c','d','e','f'), 
                    y = c(1,2,3,4,5,6),
                    stringsAsFactors = F)
test2 
inner_join(test1, test2, by = "x")

2、左連left_join

left_join(test1, test2, by = 'x')
left_join(test2, test1, by = 'x')

3、全連full_join

full_join(test1, test2, by = 'x')

4、半連接：返回能夠與y表匹配的x表所有記錄semi_join

semi_join(x = test1, y = test2, by = 'x')

5、反連接：返回?zé)o法與y表匹配的x表的所記錄anti_join

anti_join(x = test2, y = test1, by = 'x')

6、簡單合并

bind_rows(test1, test2)
bind_cols(test1, test3)