Hello,
here's a draft of a solution. I hope it's not overly complicated.
# find all possible combinations
combi <- expand.grid(Dem$Nom, Rap$Nom); names(combi) <- c("Dem", "Rap")
# we need the corresponding departments and units
combi$DemDep <- apply(combi, 1, function(x) Dem$Departement[x[1] == Dem$Nom])
combi$DemUni <- apply(combi, 1, function(x) Dem$Unite[x[1] == Dem$Nom])
combi$RapDep <- apply(combi, 1, function(x) Rap$Departement[x[2] == Rap$Nom])
combi$RapUni <- apply(combi, 1, function(x) Rap$Unite[x[2] == Rap$Nom])
# we exclude the combinations that we don't want
dep <- combi[combi$DemDep != combi$RapDep, c("Dem", "Rap")]
dep$id <- as.numeric(dep$Rap)
uni <- combi[combi$DemUni != combi$RapUni, c("Dem", "Rap")]
uni$id <- as.numeric(uni$Rap)
# preliminary result
resDep <- reshape(dep,
timevar = "id",
idvar = "Dem",
direction = "wide"
)
resUni <- reshape(uni,
timevar = "id",
idvar = "Dem",
direction = "wide"
)
In resDep and resUni you find the results for Rapporteur1 and Rapporteur2. NAs
indicate where conditions did not match. For Rap1/Rap2 you can now choose any
column from resDep and resUni that is not NA for that specific Demandeur. I
wasn't exactly sure about your third condition, so I'll leave that to you. But
with the complete possible matches, you have a more general solution.
Btw, you can construct data.frames just like this:
Dem <- data.frame(
Nom = c("John", "Jim", "Julie", "Charles", "Michel", "Emma", "Sandra", "Elodie", "Thierry", "Albert", "Jean", "Francois", "Pierre",
"Cyril", "Damien", "Jean-Michel", "Vincent", "Daniel", "Yvan", "Catherine"),
Departement = c("D", "A", "A", "C", "D", "B", "D", "B", "C", "D", "B", "B", "B", "A", "C", "D", "B",
"A", "D", "D"),
Unite = c("Unite8", "Unite4", "Unite4", "Unite7", "Unite9", "Unite1", "Unite6", "Unite5", "Unite7", "Unite3", "Unite2", "Unite6", "Unite8",
"Unite8", "Unite3", "Unite8", "Unite9", "Unite7", "Unite9", "Unite5")
)
-dk
-----Ursprüngliche Nachricht-----
Von: r-help-boun...@r-project.org [mailto:r-help-boun...@r-project.org] Im
Auftrag von Arnaud Michel
Gesendet: Dienstag, 14. Oktober 2014 10:46
An: r-help@r-project.org
Betreff: [R] To build a new Df from 2 Df
Hello
I have 2 df Dem and Rap.
I would want to build all the df (dfnew) by associating these two df (Dem and
Rap) in the following way :
For each value of Dem$Nom (dfnew$Demandeur), I associate 2 different values of
Rap$Nom (dfnew$Rapporteur1 and dfnew$Rapporteur2) in such a way
* for each dfnew$Demandeur, dfnew$Rapporteur1 does not have the same
value for Departement as Dem$Departement
* for each dfnew$Demandeur, dfnew$Rapporteur2 does not have the same
value for Unite as Dem$Unite
* the value of table(dfnew$Rapporteur1) and the value of
table(dfnew$Rapporteur2) must be balanced and not too different
(Accepted differences : 1)
table(dfnew$Rapporteur1)
Rapporteur01 Rapporteur02 Rapporteur03 Rapporteur04 Rapporteur05
4 4 4 4
4
Thanks for your help
Michel
Dem <- structure(list(Nom = c("John", "Jim", "Julie", "Charles", "Michel", "Emma", "Sandra", "Elodie", "Thierry", "Albert", "Jean", "Francois", "Pierre", "Cyril", "Damien", "Jean-Michel", "Vincent", "Daniel", "Yvan", "Catherine"), Departement = c("D", "A", "A", "C", "D", "B", "D", "B", "C", "D", "B", "B", "B", "A", "C", "D", "B",
"A", "D", "D"), Unite = c("Unite8", "Unite4", "Unite4", "Unite7", "Unite9", "Unite1", "Unite6", "Unite5", "Unite7", "Unite3", "Unite2", "Unite6", "Unite8", "Unite8", "Unite3", "Unite8", "Unite9", "Unite7", "Unite9", "Unite5")), .Names = c("Nom", "Departement", "Unite"
), row.names = c(NA, -20L), class = "data.frame")
Rap <- structure(list(Nom = c("Rapporteur01", "Rapporteur02", "Rapporteur03", "Rapporteur04", "Rapporteur05"), Departement = c("C", "D", "C", "C", "D"), Unite =
c("Unite10", "Unite6", "Unite5", "Unite5", "Unite4")), .Names = c("Nom", "Departement", "Unite"), row.names = c(NA, -5L), class = "data.frame")
dfnew <- structure(list(Demandeur = structure(c(13L, 12L, 14L, 3L, 15L, 8L, 17L, 7L, 18L, 1L, 10L, 9L, 16L, 4L, 5L, 11L, 19L, 6L, 20L, 2L), .Label = c("Albert", "Catherine", "Charles", "Cyril", "Damien", "Daniel", "Elodie", "Emma", "Francois", "Jean", "Jean-Michel", "Jim", "John", "Julie",
"Michel", "Pierre", "Sandra", "Thierry", "Vincent", "Yvan"), class = "factor"), Rapporteur1 = structure(c(3L, 1L, 3L, 5L, 1L, 5L, 1L, 2L, 5L, 4L, 2L, 4L, 2L, 3L, 5L, 4L, 4L, 2L, 3L, 1L), .Label = c("Rapporteur01", "Rapporteur02", "Rapporteur03", "Rapporteur04", "Rapporteur05"), class = "factor"), Rapporteur2 =
structure(c(1L, 3L, 4L, 4L, 2L, 4L, 5L, 1L, 2L, 3L, 3L, 3L, 5L, 5L, 1L, 1L, 2L, 5L, 4L, 2L), .Label = c("Rapporteur01", "Rapporteur02", "Rapporteur03", "Rapporteur04", "Rapporteur05"), class = "factor")), .Names = c("Demandeur", "Rapporteur1", "Rapporteur2"), row.names = c(NA, -20L), class =
"data.frame")
--
Michel ARNAUD
Cirad Montpellier
[[alternative HTML version deleted]]
______________________________________________
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
