In Tableau Desktop, how do I accomplish the following set difference/group differentiation task?
I have items that have been adjusted or have not been modified (adjusted = 1 or adjusted = 0). Please keep in mind that any product may appear more than once (as the real dataset is a a matrix of stacked time series for each product).
I'm curious as to how many products had at least one adjustment and how many did not.
In R, I'd do it like this:
Data example:
dat <- data.frame(
product = c("4005808588763", "4005808250004", "4005808157822",
"4005800031052", "4005808855735", "4005808651818", "4005808322053",
"4005808236879", "4005800091629", "4005808361434", "42277248",
"4005808224074", "9005800249858", "42277835", "4005808627356",
"8005800010985", "4005808323197", "4005808186129", "4005800059254",
"4005808818587", "4005900175410", "72140018627", "4005800059292",
"72140008499", "4005808125968", "42269847", "4005808675173",
"72140016371", "4005808765157", "4005900123763", "4005808816019",
"4005800062575", "4005808293872", "4005900143952", "8850029006536",
"4005800136986", "42231493", "4005808715688", "4005800053085",
"4005800059629", "4005808847419", "4005800031656", "4005900273994",
"4005900261038", "6009661219022", "42240181", "8850029016030",
"4005900146274", "42176152", "4005808158096"),
adjusted = c(1L, 1L, 0L, 1L, 0L, 1L, 1L, 0L, 1L, 0L, 1L, 1L, 0L, 0L, 0L, 0L, 0L,
1L, 0L, 0L, 1L, 1L, 1L, 1L, 1L, 0L, 1L, 1L, 1L, 0L, 0L, 0L, 1L,
0L, 1L, 1L, 1L, 1L, 0L, 0L, 0L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 0L,
1L)
)
# product adjusted
# 1 4005808588763 1
# 2 4005808250004 1
# 3 4005808157822 0
# 4 4005800031052 1
# 5 4005808855735 0
# 6 4005808651818 1
# 7 4005808322053 1
# 8 4005808236879 0
# 9 4005800091629 1
# 10 4005808361434 0
# 11 42277248 1
# 12 4005808224074 1
# 13 9005800249858 0
# 14 42277835 0
# 15 4005808627356 0
# 16 8005800010985 0
# 17 4005808323197 0
# 18 4005808186129 1
# 19 4005800059254 0
# 20 4005808818587 0
# 21 4005900175410 1
# 22 72140018627 1
# 23 4005800059292 1
# 24 72140008499 1
# 25 4005808125968 1
# 26 42269847 0
# 27 4005808675173 1
# 28 72140016371 1
# 29 4005808765157 1
# 30 4005900123763 0
# 31 4005808816019 0
# 32 4005800062575 0
# 33 4005808293872 1
# 34 4005900143952 0
# 35 8850029006536 1
# 36 4005800136986 1
# 37 42231493 1
# 38 4005808715688 1
# 39 4005800053085 0
# 40 4005800059629 0
# 41 4005808847419 0
# 42 4005800031656 1
# 43 4005900273994 1
# 44 4005900261038 1
# 45 6009661219022 1
# 46 42240181 1
# 47 8850029016030 1
# 48 4005900146274 1
# 49 42176152 0
# 50 4005808158096 1
Split into two data frames:
g1 <- filter(dat, adjusted == 0)
g2 <- filter(dat, adjusted == 1)
Find unique product IDs:
(id_1 <- unique(g2$product))
# [1] "4005808588763" "4005808250004" "4005800031052" "4005808651818" "4005808322053"
# [6] "4005800091629" "42277248" "4005808224074" "4005808186129" "4005900175410"
# [11] "72140018627" "4005800059292" "72140008499" "4005808125968" "4005808675173"
# [16] "72140016371" "4005808765157" "4005808293872" "8850029006536" "4005800136986"
# [21] "42231493" "4005808715688" "4005800031656" "4005900273994" "4005900261038"
# [26] "6009661219022" "42240181" "8850029016030" "4005900146274" "4005808158096"
(id_2 <- setdiff(unique(g1$product), id_1))
# [1] "4005808157822" "4005808855735" "4005808236879" "4005808361434" "9005800249858"
# [6] "42277835" "4005808627356" "8005800010985" "4005808323197" "4005800059254"
# [11] "4005808818587" "42269847" "4005900123763" "4005808816019" "4005800062575"
# [16] "4005900143952" "4005800053085" "4005800059629" "4005808847419" "42176152"
I don't really know how to go about implementing such a query.
