Factores, fechas y caracteres

  N <- 100
  edad <- sample(seq(18, 40, 1), N, replace=TRUE)
  summary(edad)

 Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
18.00   24.00   27.50   28.35   33.00   40.00

  sexo <- sample(c('H', 'M'), N, replace=TRUE)
  class(sexo)
  summary(sexo)

[1] "character"
   Length     Class      Mode 
      100 character character

  sexo <- factor(sexo)

  class(sexo)

[1] "factor"

  summary(sexo)

 H  M 
46 54

  levels(sexo)

[1] "H" "M"

  nlevels(sexo)

[1] 2

• Con la función table

  table(edad > 30, sexo)

     sexo
       H  M
FALSE 29 37
TRUE  17 17

  table(edad %in% 20:30, sexo)

     sexo
       H  M
FALSE 21 20
TRUE  25 34

• Con tapply o aggregate

tapply(edad, sexo, mean)

       H        M 
28.97826 27.81481

aggregate(edad ~ sexo, FUN=median)

  sexo edad
1    H   29
2    M   27

  edadSexo <- split(edad, sexo)
  class(edadSexo)

[1] "list"

  sapply(edadSexo, mean)

       H        M 
28.97826 27.81481

• Por ejemplo, con cut

  gEdad <- cut(edad, breaks=4)
  class(gEdad)

[1] "factor"

  levels(gEdad)

[1] "(18,23.5]" "(23.5,29]" "(29,34.5]" "(34.5,40]"

• Nuevamente table

  table(gEdad)

gEdad
(18,23.5] (23.5,29] (29,34.5] (34.5,40] 
       22        41        16        21

  table(gEdad, sexo)

           sexo
gEdad        H  M
  (18,23.5] 10 12
  (23.5,29] 16 25
  (29,34.5]  8  8
  (34.5,40] 12  9

  as.Date('2013-02-06')

[1] "2013-02-06"

  as.Date('2013/02/06')

[1] "2013-02-06"

  as.Date('06.02.2013')

Error in charToDate(x) : 
  character string is not in a standard unambiguous format

  as.Date('06.02.2013', format='%d.%m.%Y')

[1] "2013-02-06"

  as.Date(37, origin='2013-01-01')

[1] "2013-02-07"

  seq(as.Date('2004-01-01'), by='day', length=10)

[1] "2004-01-01" "2004-01-02" "2004-01-03" "2004-01-04" "2004-01-05"
[6] "2004-01-06" "2004-01-07" "2004-01-08" "2004-01-09" "2004-01-10"

  seq(as.Date('2004-01-01'), by='month', length=10)

[1] "2004-01-01" "2004-02-01" "2004-03-01" "2004-04-01" "2004-05-01"
[6] "2004-06-01" "2004-07-01" "2004-08-01" "2004-09-01" "2004-10-01"

  seq(as.Date('2004-01-01'), by='10 day', length=10)

[1] "2004-01-01" "2004-01-11" "2004-01-21" "2004-01-31" "2004-02-10"
[6] "2004-02-20" "2004-03-01" "2004-03-11" "2004-03-21" "2004-03-31"

• help(format.POSIXct)

  as.POSIXct('2013-02-06')

[1] "2013-02-06 CET"

  ISOdate(2013, 2, 7)

[1] "2013-02-07 12:00:00 GMT"

hoy <- as.POSIXct('2013-02-06')

format(hoy, '%Y')

[1] "2013"

format(hoy, '%d')

[1] "06"

format(hoy, '%m')

[1] "02"

format(hoy, '%b')

[1] "feb"

format(hoy, '%d de %B de %Y')

[1] "06 de febrero de 2013"

  hora <- Sys.time()
  hora

[1] "2015-05-07 12:27:21 CEST"

  format(hora, '%H:%M:%S')

[1] "12:27:21"

  format(hora, '%H horas, %M minutos y %S segundos')

[1] "12 horas, 27 minutos y 21 segundos"

seq(as.POSIXct('2004-01-01'), by='month', length=10)

[1] "2004-01-01 CET"  "2004-02-01 CET"  "2004-03-01 CET"  "2004-04-01 CEST"
[5] "2004-05-01 CEST" "2004-06-01 CEST" "2004-07-01 CEST" "2004-08-01 CEST"
[9] "2004-09-01 CEST" "2004-10-01 CEST"

seq(as.POSIXct('2004-01-01 10:00:00'), by='15 min', length=10)

[1] "2004-01-01 10:00:00 CET" "2004-01-01 10:15:00 CET"
[3] "2004-01-01 10:30:00 CET" "2004-01-01 10:45:00 CET"
[5] "2004-01-01 11:00:00 CET" "2004-01-01 11:15:00 CET"
[7] "2004-01-01 11:30:00 CET" "2004-01-01 11:45:00 CET"
[9] "2004-01-01 12:00:00 CET" "2004-01-01 12:15:00 CET"

  as.POSIXct('2013-02-06 15:30:00',
             tz='GMT')

[1] "2013-02-06 15:30:00 GMT"

  as.POSIXct('2013-02-06 15:30:00',
             tz='Europe/Madrid')

[1] "2013-02-06 15:30:00 CET"

hawaii <- as.POSIXct('2013-02-06 15:30:00', tz='HST')
## Character
format(hawaii, tz='GMT')

[1] "2013-02-07 01:30:00"

## POSIXct
as.POSIXct(format(hawaii, tz='GMT'), tz='GMT')

[1] "2013-02-07 01:30:00 GMT"

  cadena <- "Hola mundo"
  class(cadena)

[1] "character"

  nchar(cadena)

[1] 10

  cadenaVec <- c("Hola mundo", "Hello world")
  nchar(cadenaVec)

[1] 10 11

  length(cadenaVec)

[1] 2

cadenaVec[1]

[1] "Hola mundo"

  a <- 2
  b <- 3

  cat('La suma de', a, 'y', b, 'es', a + b, fill=TRUE)

La suma de 2 y 3 es 5

  cat('La suma de', a, 'y', b, 'es', a + b, '\n',
      'La multiplicación de', a, 'por', b, 'es', a*b, '\n')

La suma de 2 y 3 es 5 
La multiplicación de 2 por 3 es 6

  paste('Hello', 'World', sep='_')

[1] "Hello_World"

  paste('X', 1:5, sep='.')

[1] "X.1" "X.2" "X.3" "X.4" "X.5"

  paste(c('A', 'B'), 1:5, sep='.')

[1] "A.1" "B.2" "A.3" "B.4" "A.5"

  paste(c('A', 'B'), 1:5, sep='.', collapse='|')

[1] "A.1|B.2|A.3|B.4|A.5"

  strsplit(cadenaVec, split=' ')

[[1]]
[1] "Hola"  "mundo"

[[2]]
[1] "Hello" "world"

  strsplit(cadenaVec, split='')

[[1]]
 [1] "H" "o" "l" "a" " " "m" "u" "n" "d" "o"

[[2]]
 [1] "H" "e" "l" "l" "o" " " "w" "o" "r" "l" "d"

  chSep <- strsplit(cadenaVec, split=' ')
  class(chSep)

[1] "list"

  length(chSep)

[1] 2

  sapply(chSep, nchar)

     [,1] [,2]
[1,]    4    5
[2,]    5    5

  sub('o', '0', 'Hola Mundo')

[1] "H0la Mundo"

  gsub('o', '0', 'Hola Mundo')

[1] "H0la Mund0"

  substring(cadena, 1) <- 'HOLA'
  cadena

[1] "HOLA mundo"

  tolower(cadena)

[1] "hola mundo"

  toupper(cadena)

[1] "HOLA MUNDO"