Duplicate

Data

ID<-c(16762,16439,16211,16790,16443,16998,
      16543,16779,16945,16111,16224,16980,
      16779,16000,16111,16224,16400,16327)
Name<-c("Ahmed","Osama","Ibraheem","Fahd",
        "Majeda","Hdeel","Mohammed","Remas",
        "Rteel","Abdalrhman","Mhdi","Tala",
        "Remas","Nadiah","Abdalrhman","Mhdi",
        "Lila","Fatima")
Age<-c(30,32,29,7,27,9,32,9,10,29,28,9,
      9,30,29,28,42,33 )
Sex<-c("M","M","M","M","F","F","M","F",
       "F","M","M","F","F","F","M","M",
       "F","F")

data<-data.frame(ID,Name,Age,Sex)
data

##       ID       Name Age Sex
## 1  16762      Ahmed  30   M
## 2  16439      Osama  32   M
## 3  16211   Ibraheem  29   M
## 4  16790       Fahd   7   M
## 5  16443     Majeda  27   F
## 6  16998      Hdeel   9   F
## 7  16543   Mohammed  32   M
## 8  16779      Remas   9   F
## 9  16945      Rteel  10   F
## 10 16111 Abdalrhman  29   M
## 11 16224       Mhdi  28   M
## 12 16980       Tala   9   F
## 13 16779      Remas   9   F
## 14 16000     Nadiah  30   F
## 15 16111 Abdalrhman  29   M
## 16 16224       Mhdi  28   M
## 17 16400       Lila  42   F
## 18 16327     Fatima  33   F

1) Using distinct() function

library(dplyr)

## 
## 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

#Remove duplicates from data 
distinct(data)

##       ID       Name Age Sex
## 1  16762      Ahmed  30   M
## 2  16439      Osama  32   M
## 3  16211   Ibraheem  29   M
## 4  16790       Fahd   7   M
## 5  16443     Majeda  27   F
## 6  16998      Hdeel   9   F
## 7  16543   Mohammed  32   M
## 8  16779      Remas   9   F
## 9  16945      Rteel  10   F
## 10 16111 Abdalrhman  29   M
## 11 16224       Mhdi  28   M
## 12 16980       Tala   9   F
## 13 16000     Nadiah  30   F
## 14 16400       Lila  42   F
## 15 16327     Fatima  33   F

#Remove Duplicate Rows based on a variable
distinct(data,Sex,.keep_all= TRUE)

##      ID   Name Age Sex
## 1 16762  Ahmed  30   M
## 2 16443 Majeda  27   F

#Remove Duplicate Rows based on multiple variables
distinct(data,Sex,Age,.keep_all= TRUE)

##       ID     Name Age Sex
## 1  16762    Ahmed  30   M
## 2  16439    Osama  32   M
## 3  16211 Ibraheem  29   M
## 4  16790     Fahd   7   M
## 5  16443   Majeda  27   F
## 6  16998    Hdeel   9   F
## 7  16945    Rteel  10   F
## 8  16224     Mhdi  28   M
## 9  16000   Nadiah  30   F
## 10 16400     Lila  42   F
## 11 16327   Fatima  33   F

2) Using duplicated() function

which(duplicated(data))

## [1] 13 15 16

#Remove duplicates from data
data[!duplicated(data), ]

##       ID       Name Age Sex
## 1  16762      Ahmed  30   M
## 2  16439      Osama  32   M
## 3  16211   Ibraheem  29   M
## 4  16790       Fahd   7   M
## 5  16443     Majeda  27   F
## 6  16998      Hdeel   9   F
## 7  16543   Mohammed  32   M
## 8  16779      Remas   9   F
## 9  16945      Rteel  10   F
## 10 16111 Abdalrhman  29   M
## 11 16224       Mhdi  28   M
## 12 16980       Tala   9   F
## 14 16000     Nadiah  30   F
## 17 16400       Lila  42   F
## 18 16327     Fatima  33   F

#Remove duplicates from value of the column 
data[!duplicated(data$Age), ]

##       ID     Name Age Sex
## 1  16762    Ahmed  30   M
## 2  16439    Osama  32   M
## 3  16211 Ibraheem  29   M
## 4  16790     Fahd   7   M
## 5  16443   Majeda  27   F
## 6  16998    Hdeel   9   F
## 9  16945    Rteel  10   F
## 11 16224     Mhdi  28   M
## 17 16400     Lila  42   F
## 18 16327   Fatima  33   F

3) Using unique() function

#Remove duplicates from data 
unique(data)

##       ID       Name Age Sex
## 1  16762      Ahmed  30   M
## 2  16439      Osama  32   M
## 3  16211   Ibraheem  29   M
## 4  16790       Fahd   7   M
## 5  16443     Majeda  27   F
## 6  16998      Hdeel   9   F
## 7  16543   Mohammed  32   M
## 8  16779      Remas   9   F
## 9  16945      Rteel  10   F
## 10 16111 Abdalrhman  29   M
## 11 16224       Mhdi  28   M
## 12 16980       Tala   9   F
## 14 16000     Nadiah  30   F
## 17 16400       Lila  42   F
## 18 16327     Fatima  33   F

#unique value of the column 
unique(data$Age)

##  [1] 30 32 29  7 27  9 10 28 42 33