R Dplyr

** Practice Joining with dplyr **

• Left join

library(dplyr)

## Warning: package 'dplyr' was built under R version 3.2.5

## 
## Attaching package: 'dplyr'

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

a1<-data.frame(name=c("Ha","Tuyen","Van","Tri","Tuong"),age=c(23,24,25,21,23))

b1<-data.frame(name=c("Ha","Tri","Van","Hung","Hien"),wt=c(67,68,45,76,69))

# Left_join will keep a1 (first key) and add second key (b1) if match, otherwise excluded elements of b1. The right_joint is the opposite

join_left<-left_join(a1,b1,by="name")

## Warning in left_join_impl(x, y, by$x, by$y, suffix$x, suffix$y): joining
## factors with different levels, coercing to character vector

join_left

##    name age wt
## 1    Ha  23 67
## 2 Tuyen  24 NA
## 3   Van  25 45
## 4   Tri  21 68
## 5 Tuong  23 NA

• inner_join will include only names that are existing in both dataset

my_inner_join<-inner_join(a1,b1,by="name")

## Warning in inner_join_impl(x, y, by$x, by$y, suffix$x, suffix$y): joining
## factors with different levels, coercing to character vector

my_inner_join

##   name age wt
## 1   Ha  23 67
## 2  Van  25 45
## 3  Tri  21 68

• full_join will include both names that are existing in both dataset

my_full_join<-full_join(a1,b1,by="name")

## Warning in full_join_impl(x, y, by$x, by$y, suffix$x, suffix$y): joining
## factors with different levels, coercing to character vector

my_full_join

##    name age wt
## 1    Ha  23 67
## 2 Tuyen  24 NA
## 3   Van  25 45
## 4   Tri  21 68
## 5 Tuong  23 NA
## 6  Hung  NA 76
## 7  Hien  NA 69