Data:
DB1 <- data.frame(orderItemID = 1:10,
orderDate = c(\"2013-01-21\",\"2013-03-31\",\"2013-04-12\",\"2013-06-01\",\"2014-01-01\", \"2014-02-19\",\"2
First, convert the columns to Date
objects:
DB1[,2:3]<-lapply(DB1[,2:3],as.Date)
Then, replace the NA
elements:
DB1$deliveryDate[is.na(DB1$deliveryDate)] <-
DB1$orderDate[is.na(DB1$deliveryDate)] +
mean(difftime(DB1$orderDate,DB1$deliveryDate,units="days"),na.rm=TRUE)
# orderItemID orderDate deliveryDate
#1 1 2013-01-21 2013-01-23
#2 2 2013-03-31 2013-03-01
#3 3 2013-04-12 2013-04-14
#4 4 2013-06-01 2013-06-04
#5 5 2014-01-01 2014-01-03
#6 6 2014-02-19 2014-02-21
#7 7 2014-02-27 2014-02-28
#8 8 2014-10-02 2014-10-04
#9 9 2014-10-31 2014-11-01
#10 10 2014-11-21 2014-11-23
You can do:
DB1 =cbind(DB1$orderItemID,as.data.frame(lapply(DB1[-1], as.character)))
days = round(mean(DB1$deliveryDate-DB1$orderDate, na.rm=T))
mask = is.na(DB1$deliveryDate)
DB1$deliveryDate[mask] = DB1$orderDate[mask]+days
# DB1$orderItemID orderDate deliveryDate
#1 1 2013-01-21 2013-01-23
#2 2 2013-03-31 2013-04-01
#3 3 2013-04-12 2013-04-14
#4 4 2013-06-01 2013-06-04
#5 5 2014-01-01 2014-01-03
#6 6 2014-02-19 2014-02-21
#7 7 2014-02-27 2014-02-28
#8 8 2014-10-02 2014-10-04
#9 9 2014-10-31 2014-11-01
#10 10 2014-11-21 2014-11-23
I re-arrange your data since they were not clean:
DB1 <- data.frame(orderItemID = 1:10,
orderDate = c("2013-01-21","2013-03-31","2013-04-12","2013-06-01","2014-01-01", "2014-02-19","2014-02-27","2014-10-02","2014-10-31","2014-11-21"),
deliveryDate = c("2013-01-23", "2013-04-01", NA, "2013-06-04", "2014-01-03", NA, "2014-02-28", "2014-10-04", "2014-11-01", "2014-11-23"))
Assuming that you have entered your data like this (note that NAs are not enclosed in quotes so they are read as NAs and not "NA")...
DB1 <- data.frame(orderItemID = 1:10,
orderDate = c("2013-01-21","2013-03-31","2013-04-12","2013-06-01","2014-01-01", "2014-02-19","2014-02-27","2014-10-02","2014-10-31","2014-11-21"),
deliveryDate = c("2013-01-23", "2013-03-01", NA, "2013-06-04", "2014-01-03", NA, "2014-02-28", "2014-10-04", "2014-11-01", "2014-11-23"),
stringsAsFactors = FALSE)
...and, per Nicola's answer, done this to get the formatting right...
DB1[,2:3]<-lapply(DB1[,2:3],as.Date)
...this also works:
library(lubridate)
DB1$deliveryDate <- with(DB1, as.Date(ifelse(is.na(deliveryDate), orderDate + days(2), deliveryDate), origin = "1970-01-01"))
Or you could use dplyr and pipe it:
library(lubridate)
library(dplyr)
DB2 <- DB1 %>%
mutate(deliveryDate = ifelse(is.na(deliveryDate), orderDate + days(2), deliveryDate)) %>%
mutate(deliveryDate = as.Date(.[,"deliveryDate"], origin = "1970-01-01"))