CODEWITHSUNDEEP
rsubsetapplysubstitutionintersect
minoo
minoo

Reputation: 575

subseting a data frame under a specific condition

How can i get rows of a data frame that has a same value in a element of that comparing with another data frame ? I have written this but it didn't work. 

 # example of two data frame

    df1 <- data.frame(V1 = c("a", "g", "h", "l", "n", "e"), V2 = c("b", "n", "i", "m", "i", "f"), stringsAsFactors = F)

    df2 <- data.frame(V1 = c("a", "c", "f","h"), V2 = c("b", "d", "e","z"), stringsAsFactors = F)

    # finding joint values in each element of two data frames
    res1<-intersect(df1$V1,df2$V1)
    res2<-intersect(df1$V2,df2$V2)
    res3<-intersect(df1$V1,df2$V2)
    res4<-intersect(df1$V1,df2$V2)
    # Getting rows that has joint value at least in one element of df1
    ress1<-df1[apply(df1, MARGIN = 1, function(x) all(x== res1)), ]
    ress2<-df1[apply(df1, MARGIN = 1, function(x) all(x== res2)), ]
    ress3<-df1[apply(df1, MARGIN = 1, function(x) all(x== res3)), ]
    ress4<-df1[apply(df1, MARGIN = 1, function(x) all(x== res4)), ]

    # Getting rows that has joint value at least in one element of df2
    resss1<-df2[apply(df2, MARGIN = 1, function(x) all(x== res1)), ]
    resss2<-df2[apply(df2, MARGIN = 1, function(x) all(x== res2)), ]
    resss3<-df2[apply(df2, MARGIN = 1, function(x) all(x== res3)), ]
    resss4<-df2[apply(df2, MARGIN = 1, function(x) all(x== res4)), ]

    # then combine above results

    final.res<-rbind(ress1,ress2,ress3,ress4,resss1,resss2,resss3,resss4)

My favorite result is:

a   b
h   z
h   i
f   e
e   f

Upvotes: 0

Views: 79

Answers (1)

Kirill
Kirill

Reputation: 391

This should work

#Import data
df1 <- data.frame(V1 = c("a", "g", "h", "l", "n", "e"), V2 = c("b", "n", "i", "m", "i", "f"), stringsAsFactors = F)  
df2 <- data.frame(V1 = c("a", "c", "f","h"), V2 = c("b", "d", "e","z"), stringsAsFactors = F)

# Get the intersects
vals <- intersect(c(df1$V1, df1$V2), c(df2$V1, df2$V2))

#Get the subsets and rbind them
full <- rbind(
 subset(df1, df1$V1 %in% vals),
 subset(df1, df1$V2 %in% vals),
 subset(df2, df2$V1 %in% vals),
 subset(df2, df2$V2 %in% vals)
)

#Remove duplicates  
full <- full[!duplicated(full),]

Upvotes: 1

Related Questions