Compare Data Tables in R

comparedatatable.R

# Comparing data tables examples

# Examples from 
# http://cran.r-project.org/web/packages/data.table/data.table.pdf
# page 14
library(data.table)

dt1 <- data.table(A = letters[1:10], X = 1:10, key = "A") # a to j
dt2 <- data.table(A = letters[5:14], Y = 1:10, key = "A") # e to n
identical(all.equal(dt1, dt1), TRUE) 
is.character(all.equal(dt1, dt2))

# "Names: 1 string mismatch"            "Component “A”: 10 string mismatches"

# WARNING
# WITHOUT COPY DT2 BECOMES DT3!
dt3 <- dt2[, date:= Sys.Date()] # 10 x 3
all.equal(dt2, dt3) # TRUE even though extra column! AS DT2 NOW CHANGED



# RATHER USE COPY BEFORE COMPARE
dt3 <- copy(dt2)
dt3 <- dt3[, date:= Sys.Date()] # 10 x 3
all.equal(dt2, dt3) # FALSE even though extra column!

# "Length mismatch: comparison on first 2 components"

# COMPARE COLUMNS
# > colnames(dt1)
# [1] "A" "X"
# > colnames(dt3)
# [1] "A"    "Y"    "date"

x <- colnames(dt1) %in% colnames(dt2)
# > x
# [1]  TRUE FALSE

# check order not an issue
c("Y", "A") %in% colnames(dt2) # [1] TRUE TRUE

c("date", "A") %in% colnames(dt3) # [1] TRUE TRUE