Fill missing values from another dataframe with the same columns

Question

I searched various join questions and none seemed to quite answer this. I have two dataframes which each have an ID column and several information columns.

d         


        

Answer 1

If you want to join only by id column, you can remove phase in the on clause of code below.

Also your data in the question has discrepancies, which are corrected in the data posted in this answer.

library('data.table')
setDT(df1)  # make data table by reference
setDT(df2)  # make data table by reference
df1[ i = df2, color := i.color, on = .(id, phase)] # join df1 with df2 by id and phase values, and replace color values of df2 with color values of df1

tail(df1)
#     id color phase   rand.col
# 1:  95 green   gas  1.5868335
# 2:  96 green   gas  0.5584864
# 3:  97 green   gas -1.2765922
# 4:  98 green   gas -0.5732654
# 5:  99 green   gas -1.2246126
# 6: 100 green   gas -0.4734006

one-liner:

setDT(df1)[df2, color := i.color, on = .(id, phase)]

Data:

set.seed(1L)
df1 <- data.frame(id = c(1:100), color = c(rep("blue", 25), rep("red", 25), 
                                           rep(NA, 50)), phase = c(rep("liquid", 50), rep("gas", 50)),
                  rand.col = rnorm(100))

df2 <- data.frame(id = c(51:100), color = rep("green", 50), phase = rep("gas", 50))

---

EDIT: based on new data posted in the question

Data:

set.seed(1L)
df1 = data.frame(id = c(1:100),  wq2 = rnorm(50), wq3 = rnorm(50), wq4 = rnorm(50), 
                 wq5 = rnorm(50))
set.seed(2423L)
df2 = data.frame(id = c(51:100), wq2 = rnorm(50), wq3 = rnorm(50), wq4 = rnorm(50), 
                 wq5 = rnorm(50))

Code:

library('data.table')
setDT(df1)[ id == 52, ]
#    id       wq2        wq3        wq4         wq5
# 1: 52 0.1836433 -0.6120264 0.04211587 -0.01855983

setDT(df2)[ id == 52, ]
#    id       wq2       wq3        wq4       wq5
# 1: 52 0.3917297 -1.007601 -0.6820783 0.3153687

df1[df2, `:=` ( wq2 = i.wq2,
                wq3 = i.wq3,
                wq4 = i.wq4,
                wq5 = i.wq5), on = .(id)]

setDT(df1)[ id == 52, ]
#    id       wq2       wq3        wq4       wq5
# 1: 52 0.3917297 -1.007601 -0.6820783 0.3153687