Contents

1 inner join

2 첫 5행만

3 기본 예제

4 참고자료

> data1
  id mid
1 23  43
2  4  56
3 78  29
4 54  99
> data2
  id final
1  4    77
2 23     2
3 54    19
4 70    31
> dplyr::inner_join(data1, data2, by="id")
  id mid final
1 23  43     2
2  4  56    77
3 54  99    19

dplyr::filter(df, row_number() <= 5)

#install.packages("dplyr")
library("dplyr")

df <- tbl_df(iris)
df
class(df)

#필터
filter(df, Species == "setosa", Sepal.Length >= 4)
filter(df, Species == "setosa" | Species == "versicolor")

#정렬
arrange(df, Sepal.Length, desc(Sepal.Width))

#특정 컬럼만 조회
select(df, Sepal.Length, Species)
select(df, -Species)
select(df, Sepal.Width:Petal.Width)
select(df, -(Sepal.Width:Petal.Width))

#열추가
mutate(df, compute = Sepal.Length * Sepal.Width, total.Sepal.Length = sum(Sepal.Length))
transform(df, compute = Sepal.Length * Sepal.Width, total.Sepal.Length = sum(Sepal.Length))

#집계
summarise(df, total=sum(Sepal.Length))
summarise(group_by(df, Species), total=sum(Sepal.Length))

#chain 기능
group_by(df, Species) %>% filter(Sepal.Length >= 5) %>% summarise(total=sum(Sepal.Length))

• 참고:Hands-on with dplyr
  
• data-wrangling-cheatsheet.pdf
  
• data_table_cheat_sheet.pdf