validate data with the help of email_id

[shoaibali]

i have a data frame like below, now i want to check if name before @ are duplicate, if duplicate then mutate new column to(1,0) for TRUE and FALSE so i am able do it.

df <- data.frame(ID =c("DEV2962","KTN2252","ANA2719","ITI2624","DEV2698","HRT2921","","KTN2624","ANA2548","ITI2535","DEV2732","HRT2837","ERV2951","KTN2542","ANA2813","ITI2210"),
                 city=c("del","mum","nav","pun","bang","chen","triv","vish","del","mum","bang","vish","bhop","kol","noi","gurg"),
                 email = c("akash.dev@xyzpart.com","rahul.singh@xyzpart.com","salman.abbas@xyzpart.com","ram.lal@xyzpart.com","ram.lal@xyzpart.com","prabal.garg@xyzpart.com","sanu.ali@xyzpart.com","kunal.singh@xyzpart.com","lakhan.tomar@xyzpart.com","praveen.thakur@xyzpart.com","sarman.ali@xyzpart.com","zuber.khan@xyzpart.com","giriraj.singh@xyzpart.com","lokesh.sharma@xyzpart.com","pooja.pawar@xyzpart.com","nikita.sharma@xyzpart.com"),
                 name= c("dev,akash","singh,rahul","abbas,salman","lal,ram","singh,nkunj","garg,prabal","ali,sanu","singh,kunal","tomar,lakhan","thakur,praveen","ali,sarman","khan,zuber","singh,giriraj","sharma,lokesh","pawar,pooja","sharma,nikita"))


library(stringr)
df <- df %>% 
  mutate(first =str_extract(email, "[^\\@]+"),
         duplicate = as.numeric(duplicated(first))) %>% select(-first)

i also have a same old data frame, to check if mail ID is present in old data frame if present the check all records are same like (name,city,ID)

so i will check my mail id's present in the same old data frame , so if present the i need to validate if all variable like (city,name,ID) is exact match, if not the mutate a new column to true and false.

ID	city	email	name	duplicate_name	discrepancy
DEV2962	del	akash.dev@xyzcomp.com	dev,akash	0	0
KTN2252	mum	rahul.singh@xyzcomp.com	singh,rahul	0	0
ANA2719	nav	salman.abbas@xyzcomp.com	abbas,salman	0	0
ITI2624	pun	ram.lal@xyzcomp.com	lal,ram	0	0
DEV2698	bang	ram.lal@xyzcomp.com	singh,nkunj	1	0
HRT2921	chen	prabal.garg@xyzcomp.com	garg,prabal	0	0
	triv	sanu.ali@xyzcomp.com	ali,sanu	0	0
KTN2624	vish	kunal.singh@xyzcomp.com	singh,kunal	0	0
ANA2548	del	lakhan.tomar@xyzcomp.com	tomar,lakhan	0	0
ITI2535	mum	praveen.thakur@xyzcomp.com	thakur,praveen	0	1
DEV2732	bang	sarman.ali@xyzcomp.com	ali,sarman	0	0
HRT2837	vish	zuber.khan@xyzcomp.com	khan,zuber	0	0
ERV2951	bhop	giriraj.singh@xyzcomp.com	singh,giriraj	0	0
KTN2542	kol	lokesh.sharma@xyzcomp.com	sharma,lokesh	0	0
ANA2813	noi	pooja.pawar@xyzcomp.com	pawar,pooja	0	0
ITI2210	gurg	nikita.sharma@xyzcomp.com	sharma,nikita	0	0

[nirgrahamuk]

Here is an example of how I can find differences between common rows (based on id) of two tables

library(tidyverse)
(data1 <-
  tibble(id=letters[1:3],
         a =LETTERS[23:25],
         b = c(4L,1L,2L)))

(data2 <-
    tibble(id=letters[1:4],
           a =LETTERS[23:26],
           b = 4:1))

#what id's are common between data1 and data2
(commonids<-inner_join(data1,
           data2,
           by="id")  %>% pull(id))

#find discrepencies
discrep <- FALSE
discrep<-map_lgl(commonids,
     ~!isTRUE(all_equal(filter(data1,id %in% .),
                filter(data2,id %in% .))))

# attach them to data1
data1$discrep <- FALSE
data1[which(data1$id %in% commonids),"discrep"] <- discrep
data1