simplify a dataframe

Fri, Jul 12, 2013 1:17 PM

Hello,

My solution is missing a row, but maybe you can find some inspiration.


cols <- c("Matricule", "Nom", "Sexe", "DateNaissance", "contrat", "Pays")
irow1 <- duplicated(df1[, cols])
irow2 <- c(FALSE, df1$Debut[-1] == df1$Fin[-nrow(df1)])

df3 <- df1[!irow1 & !irow2, ]

dim(df2); dim(df3)  # df3 has one row less
df2; df3


Hope this helps,

Rui Barradas

Em 12-07-2013 20:45, Arnaud Michel escreveu:

Hello

I have the following problem : group the lines of a dataframe when no
information change (Matricule, Nom, Sexe, DateNaissance, Contrat, Pays)
and when the value of Debut of lines i = value Fin of lines i-1
I can obtain it with a do loop. Is it possible to avoid the loop ?

The dataframe initial is df1
dput(df1)
structure(list(Matricule = c(1L, 1L, 1L, 6L, 6L, 6L, 6L, 6L,
6L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 934L, 934L, 934L, 934L,
934L, 934L, 934L, 934L, 934L, 934L, 934L, 934L, 934L, 934L, 934L,
934L, 934L, 934L, 934L, 934L, 934L, 934L, 934L, 934L, 934L, 934L,
934L, 934L, 934L, 934L), Nom = c("VERON", "VERON", "VERON", "BENARD",
"BENARD", "BENARD", "BENARD", "BENARD", "BENARD", "DALNIC", "DALNIC",
"DALNIC", "DALNIC", "DALNIC", "DALNIC", "DALNIC", "DALNIC", "DALNIC",
"FORNI", "FORNI", "FORNI", "FORNI", "FORNI", "FORNI", "FORNI",
"FORNI", "FORNI", "FORNI", "FORNI", "FORNI", "FORNI", "FORNI",
"FORNI", "FORNI", "FORNI", "FORNI", "FORNI", "FORNI", "FORNI",
"FORNI", "FORNI", "FORNI", "FORNI", "FORNI", "FORNI", "FORNI",
"FORNI", "FORNI"), Sexe = c("F?minin", "F?minin", "F?minin",
"Masculin", "Masculin", "Masculin", "Masculin", "Masculin", "Masculin",
"F?minin", "F?minin", "F?minin", "F?minin", "F?minin", "F?minin",
"F?minin", "F?minin", "F?minin", "Masculin", "Masculin", "Masculin",
"Masculin", "Masculin", "Masculin", "Masculin", "Masculin", "Masculin",
"Masculin", "Masculin", "Masculin", "Masculin", "Masculin", "Masculin",
"Masculin", "Masculin", "Masculin", "Masculin", "Masculin", "Masculin",
"Masculin", "Masculin", "Masculin", "Masculin", "Masculin", "Masculin",
"Masculin", "Masculin", "Masculin"), DateNaissance = c("02/09/1935",
"02/09/1935", "02/09/1935", "01/04/1935", "01/04/1935", "01/04/1935",
"01/04/1935", "01/04/1935", "01/04/1935", "19/02/1940", "19/02/1940",
"19/02/1940", "19/02/1940", "19/02/1940", "19/02/1940", "19/02/1940",
"19/02/1940", "19/02/1940", "10/07/1961", "10/07/1961", "10/07/1961",
"10/07/1961", "10/07/1961", "10/07/1961", "10/07/1961", "10/07/1961",
"10/07/1961", "10/07/1961", "10/07/1961", "10/07/1961", "10/07/1961",
"10/07/1961", "10/07/1961", "10/07/1961", "10/07/1961", "10/07/1961",
"10/07/1961", "10/07/1961", "10/07/1961", "10/07/1961", "10/07/1961",
"10/07/1961", "10/07/1961", "10/07/1961", "10/07/1961", "10/07/1961",
"10/07/1961", "10/07/1961"), contrat = c("CDI commun", "CDI commun",
"CDI commun", "CDI commun", "CDI commun", "CDI commun", "CDI commun",
"CDI commun", "CDI commun", "CDI commun", "CDI commun", "CDI commun",
"CDI commun", "CDI commun", "CDI commun", "CDI commun", "CDI commun",
"CDI commun", "CDD d?tach? ext. Cirad", "CDD d?tach? ext. Cirad",
"CDD d?tach? ext. Cirad", "CDD d?tach? ext. Cirad", "CDD d?tach? ext.
Cirad",
"CDD d?tach? ext. Cirad", "CDD d?tach? ext. Cirad", "CDD d?tach? ext.
Cirad",
"CDD d?tach? ext. Cirad", "CDI D?tach?s Autres", "CDI D?tach?s Autres",
"CDI D?tach?s Autres", "CDI D?tach?s Autres", "CDI D?tach?s Autres",
"CDI D?tach?s Autres", "CDI D?tach?s Autres", "CDI D?tach?s Autres",
"CDI D?tach?s Autres", "CDI D?tach?s Autres", "CDI D?tach?s Autres",
"CDI D?tach?s Autres", "CDI D?tach?s Autres", "CDI commun", "CDI commun",
"CDI commun", "CDI commun", "CDI commun", "CDI commun", "CDI commun",
"CDI commun"), Pays = c("France", "France", "France", "Philippines",
"Philippines", "Philippines", "France", "France", "France", "France",
"France", "Martinique", "Martinique", "Martinique", "Martinique",
"Martinique", "Martinique", "Martinique", "Cameroun", "Cameroun",
"Cameroun", "Cameroun", "Cameroun", "Cameroun", "Cameroun", "Cameroun",
"Cameroun", "France", "France", "France", "France", "France",
"France", "France", "Congo", "Congo", "Congo", "Congo", "Congo",
"Congo", "Gabon", "Gabon", "Gabon", "Gabon", "Gabon", "Gabon",
"Congo", "Congo"), Debut = c("24/01/1995", "01/05/1997", "31/12/1997",
"02/02/1995", "28/02/1995", "01/03/1995", "13/03/1995", "01/01/1996",
"31/01/1996", "24/01/1995", "01/07/1995", "01/09/1995", "01/07/1997",
"01/01/1998", "01/08/1998", "01/01/2000", "17/01/2000", "29/02/2000",
"26/01/1995", "01/07/1996", "16/09/1997", "01/01/1998", "01/07/1998",
"04/11/1999", "01/01/2001", "01/04/2001", "31/08/2001", "01/09/2001",
"02/09/2001", "01/12/2001", "01/02/2003", "01/04/2003", "01/01/2004",
"01/03/2004", "01/09/2004", "01/01/2005", "01/04/2005", "28/10/2006",
"01/01/2007", "01/04/2007", "01/09/2007", "01/01/2009", "01/04/2009",
"01/01/2010", "01/01/2011", "01/04/2011", "05/09/2012", "01/01/2013"
), Fin = c("30/04/1997", "30/12/1997", "31/12/1997", "27/02/1995",
"28/02/1995", "12/03/1995", "30/06/1995", "30/01/1996", "31/01/1996",
"30/06/1995", "31/08/1995", "30/06/1997", "31/12/1997", "31/07/1998",
"31/12/1999", "16/01/2000", "28/02/2000", "29/02/2000", "30/06/1996",
"15/09/1997", "31/12/1997", "30/06/1998", "03/11/1999", "31/12/2000",
"31/03/2001", "30/08/2001", "31/08/2001", "01/09/2001", "30/11/2001",
"31/01/2003", "31/03/2003", "31/12/2003", "29/02/2004", "31/08/2004",
"31/12/2004", "31/03/2005", "27/10/2006", "31/12/2006", "31/03/2007",
"31/08/2007", "31/12/2008", "31/03/2009", "31/12/2009", "31/12/2010",
"31/03/2011", "04/09/2012", "31/12/2012", "31/12/4712")), .Names =
c("Matricule",
"Nom", "Sexe", "DateNaissance", "contrat", "Pays", "Debut", "Fin"
), class = "data.frame", row.names = c(NA, -48L))

The dataframe to be obtained is df2
dput(df2)
structure(list(Mat = c(1L, 6L, 6L, 6L, 8L, 8L, 934L, 934L, 934L,
934L, 934L), Nom = c("VERON", "BENARD", "BENARD", "BENARD", "DALNIC",
"DALNIC", "FORNI", "FORNI", "FORNI", "FORNI", "FORNI"), Sexe = c("F?minin",
"Masculin", "Masculin", "Masculin", "F?minin", "F?minin", "Masculin",
"Masculin", "Masculin", "Masculin", "Masculin"), DateNaissance =
c("02/09/1935",
"01/04/1935", "01/04/1935", "01/04/1935", "19/02/1940", "19/02/1940",
"10/07/1961", "10/07/1961", "10/07/1961", "10/07/1961", "10/07/1961"
), contrat = c("CDI commun", "CDI commun", "CDI commun", "CDI commun",
"CDI commun", "CDI commun", "CDD d?tach? ext. Cirad", "CDI D?tach?s
Autres",
"CDI D?tach?s Autres", "CDI commun", "CDI commun"), Pays = c("France",
"Philippines", "France", "France", "France", "Martinique", "Cameroun",
"France", "Congo", "Gabon", "Congo"), Debut = c("24/01/1995",
"02/02/1995", "13/03/1995", "01/01/1996", "24/01/1995", "01/09/1995",
"26/01/1995", "01/09/2001", "01/09/2004", "01/09/2007", "05/09/2012"
), Fin = c("31/12/1997", "12/03/1995", "30/06/1995", "31/01/1996",
"31/08/1995", "29/02/2000", "31/08/2001", "31/08/2004", "31/08/2007",
"04/09/2012", "31/12/4712")), .Names = c("Mat", "Nom", "Sexe",
"DateNaissance", "contrat", "Pays", "Debut", "Fin"), class =
"data.frame", row.names = c(NA,
-11L))

Thank you for your help

simplify a dataframe

Thread (9 messages)