# the R book por Michael Crawley
# capitulo 4
setwd("C:\\Users\\Luis\\Documents\\therbook")
worm <- read.table("C:\\Users\\Luis\\Documents\\therbook\\worms.txt",
header = TRUE,sep = "")
worm
## Field.Name Area Slope Vegetation Soil.pH Damp Worm.density
## 1 Nashs.Field 3.6 11 Grassland 4.1 FALSE 4
## 2 Silwood.Bottom 5.1 2 Arable 5.2 FALSE 7
## 3 Nursery.Field 2.8 3 Grassland 4.3 FALSE 2
## 4 Rush.Meadow 2.4 5 Meadow 4.9 TRUE 5
## 5 Gunness.Thicket 3.8 0 Scrub 4.2 FALSE 6
## 6 Oak.Mead 3.1 2 Grassland 3.9 FALSE 2
## 7 Church.Field 3.5 3 Grassland 4.2 FALSE 3
## 8 Ashurst 2.1 0 Arable 4.8 FALSE 4
## 9 The.Orchard 1.9 0 Orchard 5.7 FALSE 9
## 10 Rookery.Slope 1.5 4 Grassland 5.0 TRUE 7
## 11 Garden.Wood 2.9 10 Scrub 5.2 FALSE 8
## 12 North.Gravel 3.3 1 Grassland 4.1 FALSE 1
## 13 South.Gravel 3.7 2 Grassland 4.0 FALSE 2
## 14 Observatory.Ridge 1.8 6 Grassland 3.8 FALSE 0
## 15 Pond.Field 4.1 0 Meadow 5.0 TRUE 6
## 16 Water.Meadow 3.9 0 Meadow 4.9 TRUE 8
## 17 Cheapside 2.2 8 Scrub 4.7 TRUE 4
## 18 Pound.Hill 4.4 2 Arable 4.5 FALSE 5
## 19 Gravel.Pit 2.9 1 Grassland 3.5 FALSE 1
## 20 Farm.Wood 0.8 10 Scrub 5.1 TRUE 3
#by(worm,worm$Vegetation,FUN=mean)# no funciona
by(worm,worm$Vegetation,function(x) lm(worm$Worm.density~worm$Soil.pH,data=x))
## worm$Vegetation: Arable
##
## Call:
## lm(formula = worm$Worm.density ~ worm$Soil.pH, data = x)
##
## Coefficients:
## (Intercept) worm$Soil.pH
## -12.771 3.759
##
## --------------------------------------------------------
## worm$Vegetation: Grassland
##
## Call:
## lm(formula = worm$Worm.density ~ worm$Soil.pH, data = x)
##
## Coefficients:
## (Intercept) worm$Soil.pH
## -12.771 3.759
##
## --------------------------------------------------------
## worm$Vegetation: Meadow
##
## Call:
## lm(formula = worm$Worm.density ~ worm$Soil.pH, data = x)
##
## Coefficients:
## (Intercept) worm$Soil.pH
## -12.771 3.759
##
## --------------------------------------------------------
## worm$Vegetation: Orchard
##
## Call:
## lm(formula = worm$Worm.density ~ worm$Soil.pH, data = x)
##
## Coefficients:
## (Intercept) worm$Soil.pH
## -12.771 3.759
##
## --------------------------------------------------------
## worm$Vegetation: Scrub
##
## Call:
## lm(formula = worm$Worm.density ~ worm$Soil.pH, data = x)
##
## Coefficients:
## (Intercept) worm$Soil.pH
## -12.771 3.759
worm[3,5]# extrae el valor de la fila 3 y la columna 5(Soil.pH)
## [1] 4.3
worm[10:13,7]#extrae los valores del lugar 10 al 13 en la 7ma. variable
## [1] 7 8 1 2
#Suponga que deseamos el Area y Slope (columnas 2 y 3) de la filas 1 to 5:
worm[1:5,2:3]
## Area Slope
## 1 3.6 11
## 2 5.1 2
## 3 2.8 3
## 4 2.4 5
## 5 3.8 0
# Para seleccionar todos los valores en una fila
# la sintaxis es 'numbero coma blanco'. De igual forma,
# para seleccionar todos los valores en una columna la sintaxis 'blanco coma
# numero'. Asi, para seleccionar todas las columnas en la fila 3:
worm[3,]
## Field.Name Area Slope Vegetation Soil.pH Damp Worm.density
## 3 Nursery.Field 2.8 3 Grassland 4.3 FALSE 2
class(worm[3,])
## [1] "data.frame"
# para seleccionar todas las filas en la columna 3:
worm[,3]
## [1] 11 2 3 5 0 2 3 0 0 4 10 1 2 6 0 0 8 2 1 10
class(worm[,3])
## [1] "integer"
# Podemos crear conjuntos de filas y columnas.Por ejemplo,
# para extraer todas las filas de Field.Name y
# Soil.pH (columns 1 and 5) usamos la funcion concatenate,
# c, para hacer un vector de la requerida columna
# numeros c(1,5):
worm[,c(1,5)]
## Field.Name Soil.pH
## 1 Nashs.Field 4.1
## 2 Silwood.Bottom 5.2
## 3 Nursery.Field 4.3
## 4 Rush.Meadow 4.9
## 5 Gunness.Thicket 4.2
## 6 Oak.Mead 3.9
## 7 Church.Field 4.2
## 8 Ashurst 4.8
## 9 The.Orchard 5.7
## 10 Rookery.Slope 5.0
## 11 Garden.Wood 5.2
## 12 North.Gravel 4.1
## 13 South.Gravel 4.0
## 14 Observatory.Ridge 3.8
## 15 Pond.Field 5.0
## 16 Water.Meadow 4.9
## 17 Cheapside 4.7
## 18 Pound.Hill 4.5
## 19 Gravel.Pit 3.5
## 20 Farm.Wood 5.1
# 4.2 Seleccionando filas aleatoriamente
# Usamos la funcion sample() para hacer esto: el default = FALSE
# hace el barajeo cada fila es seleccionada una vez
# hacemos de default replace = F para selecciona
# un numero unico de 8 de las 20 filas aleatoriamente:
worm[sample(1:20,8),]
## Field.Name Area Slope Vegetation Soil.pH Damp Worm.density
## 6 Oak.Mead 3.1 2 Grassland 3.9 FALSE 2
## 19 Gravel.Pit 2.9 1 Grassland 3.5 FALSE 1
## 18 Pound.Hill 4.4 2 Arable 4.5 FALSE 5
## 15 Pond.Field 4.1 0 Meadow 5.0 TRUE 6
## 5 Gunness.Thicket 3.8 0 Scrub 4.2 FALSE 6
## 11 Garden.Wood 2.9 10 Scrub 5.2 FALSE 8
## 16 Water.Meadow 3.9 0 Meadow 4.9 TRUE 8
## 14 Observatory.Ridge 1.8 6 Grassland 3.8 FALSE 0
# en resumen
worm[3,]#selecciona todas la columnas de la fila 3
## Field.Name Area Slope Vegetation Soil.pH Damp Worm.density
## 3 Nursery.Field 2.8 3 Grassland 4.3 FALSE 2
worm[-3,]# elimina toda la fila 3
## Field.Name Area Slope Vegetation Soil.pH Damp Worm.density
## 1 Nashs.Field 3.6 11 Grassland 4.1 FALSE 4
## 2 Silwood.Bottom 5.1 2 Arable 5.2 FALSE 7
## 4 Rush.Meadow 2.4 5 Meadow 4.9 TRUE 5
## 5 Gunness.Thicket 3.8 0 Scrub 4.2 FALSE 6
## 6 Oak.Mead 3.1 2 Grassland 3.9 FALSE 2
## 7 Church.Field 3.5 3 Grassland 4.2 FALSE 3
## 8 Ashurst 2.1 0 Arable 4.8 FALSE 4
## 9 The.Orchard 1.9 0 Orchard 5.7 FALSE 9
## 10 Rookery.Slope 1.5 4 Grassland 5.0 TRUE 7
## 11 Garden.Wood 2.9 10 Scrub 5.2 FALSE 8
## 12 North.Gravel 3.3 1 Grassland 4.1 FALSE 1
## 13 South.Gravel 3.7 2 Grassland 4.0 FALSE 2
## 14 Observatory.Ridge 1.8 6 Grassland 3.8 FALSE 0
## 15 Pond.Field 4.1 0 Meadow 5.0 TRUE 6
## 16 Water.Meadow 3.9 0 Meadow 4.9 TRUE 8
## 17 Cheapside 2.2 8 Scrub 4.7 TRUE 4
## 18 Pound.Hill 4.4 2 Arable 4.5 FALSE 5
## 19 Gravel.Pit 2.9 1 Grassland 3.5 FALSE 1
## 20 Farm.Wood 0.8 10 Scrub 5.1 TRUE 3
worm[1:3,]# selecciona todas las columnas de la fila 1 a la 3
## Field.Name Area Slope Vegetation Soil.pH Damp Worm.density
## 1 Nashs.Field 3.6 11 Grassland 4.1 FALSE 4
## 2 Silwood.Bottom 5.1 2 Arable 5.2 FALSE 7
## 3 Nursery.Field 2.8 3 Grassland 4.3 FALSE 2
worm[-(1:3),]# elimina las filas 1 al 3 de todas las columnas
## Field.Name Area Slope Vegetation Soil.pH Damp Worm.density
## 4 Rush.Meadow 2.4 5 Meadow 4.9 TRUE 5
## 5 Gunness.Thicket 3.8 0 Scrub 4.2 FALSE 6
## 6 Oak.Mead 3.1 2 Grassland 3.9 FALSE 2
## 7 Church.Field 3.5 3 Grassland 4.2 FALSE 3
## 8 Ashurst 2.1 0 Arable 4.8 FALSE 4
## 9 The.Orchard 1.9 0 Orchard 5.7 FALSE 9
## 10 Rookery.Slope 1.5 4 Grassland 5.0 TRUE 7
## 11 Garden.Wood 2.9 10 Scrub 5.2 FALSE 8
## 12 North.Gravel 3.3 1 Grassland 4.1 FALSE 1
## 13 South.Gravel 3.7 2 Grassland 4.0 FALSE 2
## 14 Observatory.Ridge 1.8 6 Grassland 3.8 FALSE 0
## 15 Pond.Field 4.1 0 Meadow 5.0 TRUE 6
## 16 Water.Meadow 3.9 0 Meadow 4.9 TRUE 8
## 17 Cheapside 2.2 8 Scrub 4.7 TRUE 4
## 18 Pound.Hill 4.4 2 Arable 4.5 FALSE 5
## 19 Gravel.Pit 2.9 1 Grassland 3.5 FALSE 1
## 20 Farm.Wood 0.8 10 Scrub 5.1 TRUE 3
worm[c(2,3,5),]# selecciona las filas 2,3,5 de todas las columnas
## Field.Name Area Slope Vegetation Soil.pH Damp Worm.density
## 2 Silwood.Bottom 5.1 2 Arable 5.2 FALSE 7
## 3 Nursery.Field 2.8 3 Grassland 4.3 FALSE 2
## 5 Gunness.Thicket 3.8 0 Scrub 4.2 FALSE 6
worm[,-3]# elimina la columna 3 de todas las filas
## Field.Name Area Vegetation Soil.pH Damp Worm.density
## 1 Nashs.Field 3.6 Grassland 4.1 FALSE 4
## 2 Silwood.Bottom 5.1 Arable 5.2 FALSE 7
## 3 Nursery.Field 2.8 Grassland 4.3 FALSE 2
## 4 Rush.Meadow 2.4 Meadow 4.9 TRUE 5
## 5 Gunness.Thicket 3.8 Scrub 4.2 FALSE 6
## 6 Oak.Mead 3.1 Grassland 3.9 FALSE 2
## 7 Church.Field 3.5 Grassland 4.2 FALSE 3
## 8 Ashurst 2.1 Arable 4.8 FALSE 4
## 9 The.Orchard 1.9 Orchard 5.7 FALSE 9
## 10 Rookery.Slope 1.5 Grassland 5.0 TRUE 7
## 11 Garden.Wood 2.9 Scrub 5.2 FALSE 8
## 12 North.Gravel 3.3 Grassland 4.1 FALSE 1
## 13 South.Gravel 3.7 Grassland 4.0 FALSE 2
## 14 Observatory.Ridge 1.8 Grassland 3.8 FALSE 0
## 15 Pond.Field 4.1 Meadow 5.0 TRUE 6
## 16 Water.Meadow 3.9 Meadow 4.9 TRUE 8
## 17 Cheapside 2.2 Scrub 4.7 TRUE 4
## 18 Pound.Hill 4.4 Arable 4.5 FALSE 5
## 19 Gravel.Pit 2.9 Grassland 3.5 FALSE 1
## 20 Farm.Wood 0.8 Scrub 5.1 TRUE 3
worm[,2:4]# selecciona las columnas de la 2 a la 4 de todas las filas
## Area Slope Vegetation
## 1 3.6 11 Grassland
## 2 5.1 2 Arable
## 3 2.8 3 Grassland
## 4 2.4 5 Meadow
## 5 3.8 0 Scrub
## 6 3.1 2 Grassland
## 7 3.5 3 Grassland
## 8 2.1 0 Arable
## 9 1.9 0 Orchard
## 10 1.5 4 Grassland
## 11 2.9 10 Scrub
## 12 3.3 1 Grassland
## 13 3.7 2 Grassland
## 14 1.8 6 Grassland
## 15 4.1 0 Meadow
## 16 3.9 0 Meadow
## 17 2.2 8 Scrub
## 18 4.4 2 Arable
## 19 2.9 1 Grassland
## 20 0.8 10 Scrub
worm[,-(2:4)]# elimina las columnas de la 2 a la 4 de todas las filas
## Field.Name Soil.pH Damp Worm.density
## 1 Nashs.Field 4.1 FALSE 4
## 2 Silwood.Bottom 5.2 FALSE 7
## 3 Nursery.Field 4.3 FALSE 2
## 4 Rush.Meadow 4.9 TRUE 5
## 5 Gunness.Thicket 4.2 FALSE 6
## 6 Oak.Mead 3.9 FALSE 2
## 7 Church.Field 4.2 FALSE 3
## 8 Ashurst 4.8 FALSE 4
## 9 The.Orchard 5.7 FALSE 9
## 10 Rookery.Slope 5.0 TRUE 7
## 11 Garden.Wood 5.2 FALSE 8
## 12 North.Gravel 4.1 FALSE 1
## 13 South.Gravel 4.0 FALSE 2
## 14 Observatory.Ridge 3.8 FALSE 0
## 15 Pond.Field 5.0 TRUE 6
## 16 Water.Meadow 4.9 TRUE 8
## 17 Cheapside 4.7 TRUE 4
## 18 Pound.Hill 4.5 FALSE 5
## 19 Gravel.Pit 3.5 FALSE 1
## 20 Farm.Wood 5.1 TRUE 3
worm[,c(2,4,5)]# selecciona las columnas 2,4,5 de todas las filas
## Area Vegetation Soil.pH
## 1 3.6 Grassland 4.1
## 2 5.1 Arable 5.2
## 3 2.8 Grassland 4.3
## 4 2.4 Meadow 4.9
## 5 3.8 Scrub 4.2
## 6 3.1 Grassland 3.9
## 7 3.5 Grassland 4.2
## 8 2.1 Arable 4.8
## 9 1.9 Orchard 5.7
## 10 1.5 Grassland 5.0
## 11 2.9 Scrub 5.2
## 12 3.3 Grassland 4.1
## 13 3.7 Grassland 4.0
## 14 1.8 Grassland 3.8
## 15 4.1 Meadow 5.0
## 16 3.9 Meadow 4.9
## 17 2.2 Scrub 4.7
## 18 4.4 Arable 4.5
## 19 2.9 Grassland 3.5
## 20 0.8 Scrub 5.1
worm[,c(1:5,4,5,6)]# añade duplicados
## Field.Name Area Slope Vegetation Soil.pH Vegetation.1 Soil.pH.1
## 1 Nashs.Field 3.6 11 Grassland 4.1 Grassland 4.1
## 2 Silwood.Bottom 5.1 2 Arable 5.2 Arable 5.2
## 3 Nursery.Field 2.8 3 Grassland 4.3 Grassland 4.3
## 4 Rush.Meadow 2.4 5 Meadow 4.9 Meadow 4.9
## 5 Gunness.Thicket 3.8 0 Scrub 4.2 Scrub 4.2
## 6 Oak.Mead 3.1 2 Grassland 3.9 Grassland 3.9
## 7 Church.Field 3.5 3 Grassland 4.2 Grassland 4.2
## 8 Ashurst 2.1 0 Arable 4.8 Arable 4.8
## 9 The.Orchard 1.9 0 Orchard 5.7 Orchard 5.7
## 10 Rookery.Slope 1.5 4 Grassland 5.0 Grassland 5.0
## 11 Garden.Wood 2.9 10 Scrub 5.2 Scrub 5.2
## 12 North.Gravel 3.3 1 Grassland 4.1 Grassland 4.1
## 13 South.Gravel 3.7 2 Grassland 4.0 Grassland 4.0
## 14 Observatory.Ridge 1.8 6 Grassland 3.8 Grassland 3.8
## 15 Pond.Field 4.1 0 Meadow 5.0 Meadow 5.0
## 16 Water.Meadow 3.9 0 Meadow 4.9 Meadow 4.9
## 17 Cheapside 2.2 8 Scrub 4.7 Scrub 4.7
## 18 Pound.Hill 4.4 2 Arable 4.5 Arable 4.5
## 19 Gravel.Pit 2.9 1 Grassland 3.5 Grassland 3.5
## 20 Farm.Wood 0.8 10 Scrub 5.1 Scrub 5.1
## Damp
## 1 FALSE
## 2 FALSE
## 3 FALSE
## 4 TRUE
## 5 FALSE
## 6 FALSE
## 7 FALSE
## 8 FALSE
## 9 FALSE
## 10 TRUE
## 11 FALSE
## 12 FALSE
## 13 FALSE
## 14 FALSE
## 15 TRUE
## 16 TRUE
## 17 TRUE
## 18 FALSE
## 19 FALSE
## 20 TRUE
# 4.3 Ordenando dataframes
worm[order(worm$Slope),]#descendiente
## Field.Name Area Slope Vegetation Soil.pH Damp Worm.density
## 5 Gunness.Thicket 3.8 0 Scrub 4.2 FALSE 6
## 8 Ashurst 2.1 0 Arable 4.8 FALSE 4
## 9 The.Orchard 1.9 0 Orchard 5.7 FALSE 9
## 15 Pond.Field 4.1 0 Meadow 5.0 TRUE 6
## 16 Water.Meadow 3.9 0 Meadow 4.9 TRUE 8
## 12 North.Gravel 3.3 1 Grassland 4.1 FALSE 1
## 19 Gravel.Pit 2.9 1 Grassland 3.5 FALSE 1
## 2 Silwood.Bottom 5.1 2 Arable 5.2 FALSE 7
## 6 Oak.Mead 3.1 2 Grassland 3.9 FALSE 2
## 13 South.Gravel 3.7 2 Grassland 4.0 FALSE 2
## 18 Pound.Hill 4.4 2 Arable 4.5 FALSE 5
## 3 Nursery.Field 2.8 3 Grassland 4.3 FALSE 2
## 7 Church.Field 3.5 3 Grassland 4.2 FALSE 3
## 10 Rookery.Slope 1.5 4 Grassland 5.0 TRUE 7
## 4 Rush.Meadow 2.4 5 Meadow 4.9 TRUE 5
## 14 Observatory.Ridge 1.8 6 Grassland 3.8 FALSE 0
## 17 Cheapside 2.2 8 Scrub 4.7 TRUE 4
## 11 Garden.Wood 2.9 10 Scrub 5.2 FALSE 8
## 20 Farm.Wood 0.8 10 Scrub 5.1 TRUE 3
## 1 Nashs.Field 3.6 11 Grassland 4.1 FALSE 4
worm[rev(order(worm$Slope)),]# ascendiente
## Field.Name Area Slope Vegetation Soil.pH Damp Worm.density
## 1 Nashs.Field 3.6 11 Grassland 4.1 FALSE 4
## 20 Farm.Wood 0.8 10 Scrub 5.1 TRUE 3
## 11 Garden.Wood 2.9 10 Scrub 5.2 FALSE 8
## 17 Cheapside 2.2 8 Scrub 4.7 TRUE 4
## 14 Observatory.Ridge 1.8 6 Grassland 3.8 FALSE 0
## 4 Rush.Meadow 2.4 5 Meadow 4.9 TRUE 5
## 10 Rookery.Slope 1.5 4 Grassland 5.0 TRUE 7
## 7 Church.Field 3.5 3 Grassland 4.2 FALSE 3
## 3 Nursery.Field 2.8 3 Grassland 4.3 FALSE 2
## 18 Pound.Hill 4.4 2 Arable 4.5 FALSE 5
## 13 South.Gravel 3.7 2 Grassland 4.0 FALSE 2
## 6 Oak.Mead 3.1 2 Grassland 3.9 FALSE 2
## 2 Silwood.Bottom 5.1 2 Arable 5.2 FALSE 7
## 19 Gravel.Pit 2.9 1 Grassland 3.5 FALSE 1
## 12 North.Gravel 3.3 1 Grassland 4.1 FALSE 1
## 16 Water.Meadow 3.9 0 Meadow 4.9 TRUE 8
## 15 Pond.Field 4.1 0 Meadow 5.0 TRUE 6
## 9 The.Orchard 1.9 0 Orchard 5.7 FALSE 9
## 8 Ashurst 2.1 0 Arable 4.8 FALSE 4
## 5 Gunness.Thicket 3.8 0 Scrub 4.2 FALSE 6
worm[order(worm$Vegetation,worm$Worm.density,worm$Soil.pH),]
## Field.Name Area Slope Vegetation Soil.pH Damp Worm.density
## 8 Ashurst 2.1 0 Arable 4.8 FALSE 4
## 18 Pound.Hill 4.4 2 Arable 4.5 FALSE 5
## 2 Silwood.Bottom 5.1 2 Arable 5.2 FALSE 7
## 14 Observatory.Ridge 1.8 6 Grassland 3.8 FALSE 0
## 19 Gravel.Pit 2.9 1 Grassland 3.5 FALSE 1
## 12 North.Gravel 3.3 1 Grassland 4.1 FALSE 1
## 6 Oak.Mead 3.1 2 Grassland 3.9 FALSE 2
## 13 South.Gravel 3.7 2 Grassland 4.0 FALSE 2
## 3 Nursery.Field 2.8 3 Grassland 4.3 FALSE 2
## 7 Church.Field 3.5 3 Grassland 4.2 FALSE 3
## 1 Nashs.Field 3.6 11 Grassland 4.1 FALSE 4
## 10 Rookery.Slope 1.5 4 Grassland 5.0 TRUE 7
## 4 Rush.Meadow 2.4 5 Meadow 4.9 TRUE 5
## 15 Pond.Field 4.1 0 Meadow 5.0 TRUE 6
## 16 Water.Meadow 3.9 0 Meadow 4.9 TRUE 8
## 9 The.Orchard 1.9 0 Orchard 5.7 FALSE 9
## 20 Farm.Wood 0.8 10 Scrub 5.1 TRUE 3
## 17 Cheapside 2.2 8 Scrub 4.7 TRUE 4
## 5 Gunness.Thicket 3.8 0 Scrub 4.2 FALSE 6
## 11 Garden.Wood 2.9 10 Scrub 5.2 FALSE 8
# si queremos vegetation,worm.density,
# soil pH y slope, y las queremos en el orden desde la izquierda
# a derecha, especificamos los numeros de las columnas en la
# secuencia que queremos que aparezcan como un vector: c(4,7,5,3):
worm[order(worm$Vegetation,worm$Worm.density),c(4,7,5,3)]
## Vegetation Worm.density Soil.pH Slope
## 8 Arable 4 4.8 0
## 18 Arable 5 4.5 2
## 2 Arable 7 5.2 2
## 14 Grassland 0 3.8 6
## 12 Grassland 1 4.1 1
## 19 Grassland 1 3.5 1
## 3 Grassland 2 4.3 3
## 6 Grassland 2 3.9 2
## 13 Grassland 2 4.0 2
## 7 Grassland 3 4.2 3
## 1 Grassland 4 4.1 11
## 10 Grassland 7 5.0 4
## 4 Meadow 5 4.9 5
## 15 Meadow 6 5.0 0
## 16 Meadow 8 4.9 0
## 9 Orchard 9 5.7 0
## 20 Scrub 3 5.1 10
## 17 Scrub 4 4.7 8
## 5 Scrub 6 4.2 0
## 11 Scrub 8 5.2 10
# 4.4 Usando condiciones logicas para seleccionar filas
worm[worm$Damp==T,]
## Field.Name Area Slope Vegetation Soil.pH Damp Worm.density
## 4 Rush.Meadow 2.4 5 Meadow 4.9 TRUE 5
## 10 Rookery.Slope 1.5 4 Grassland 5.0 TRUE 7
## 15 Pond.Field 4.1 0 Meadow 5.0 TRUE 6
## 16 Water.Meadow 3.9 0 Meadow 4.9 TRUE 8
## 17 Cheapside 2.2 8 Scrub 4.7 TRUE 4
## 20 Farm.Wood 0.8 10 Scrub 5.1 TRUE 3
worm[worm$Worm.density>median(worm$Worm.density)&worm$Soil.pH<5.2,]
## Field.Name Area Slope Vegetation Soil.pH Damp Worm.density
## 4 Rush.Meadow 2.4 5 Meadow 4.9 TRUE 5
## 5 Gunness.Thicket 3.8 0 Scrub 4.2 FALSE 6
## 10 Rookery.Slope 1.5 4 Grassland 5.0 TRUE 7
## 15 Pond.Field 4.1 0 Meadow 5.0 TRUE 6
## 16 Water.Meadow 3.9 0 Meadow 4.9 TRUE 8
## 18 Pound.Hill 4.4 2 Arable 4.5 FALSE 5
# Suponga that que queremos extraer todas las columnas que contienen numeros
# en vez de caracteres o variables logicas
# podemos aplicar la funcion is.numeric
# a traves de todas las columnas
# usando sapply para crear los indices asi:
worm[,sapply(worm, is.numeric)]
## Area Slope Soil.pH Worm.density
## 1 3.6 11 4.1 4
## 2 5.1 2 5.2 7
## 3 2.8 3 4.3 2
## 4 2.4 5 4.9 5
## 5 3.8 0 4.2 6
## 6 3.1 2 3.9 2
## 7 3.5 3 4.2 3
## 8 2.1 0 4.8 4
## 9 1.9 0 5.7 9
## 10 1.5 4 5.0 7
## 11 2.9 10 5.2 8
## 12 3.3 1 4.1 1
## 13 3.7 2 4.0 2
## 14 1.8 6 3.8 0
## 15 4.1 0 5.0 6
## 16 3.9 0 4.9 8
## 17 2.2 8 4.7 4
## 18 4.4 2 4.5 5
## 19 2.9 1 3.5 1
## 20 0.8 10 5.1 3
#con la funcion is.factor()
worm[,sapply(worm, is.factor)]
## Field.Name Vegetation
## 1 Nashs.Field Grassland
## 2 Silwood.Bottom Arable
## 3 Nursery.Field Grassland
## 4 Rush.Meadow Meadow
## 5 Gunness.Thicket Scrub
## 6 Oak.Mead Grassland
## 7 Church.Field Grassland
## 8 Ashurst Arable
## 9 The.Orchard Orchard
## 10 Rookery.Slope Grassland
## 11 Garden.Wood Scrub
## 12 North.Gravel Grassland
## 13 South.Gravel Grassland
## 14 Observatory.Ridge Grassland
## 15 Pond.Field Meadow
## 16 Water.Meadow Meadow
## 17 Cheapside Scrub
## 18 Pound.Hill Arable
## 19 Gravel.Pit Grassland
## 20 Farm.Wood Scrub
# To drop a row or rows from the dataframe,
# use negative subscripts. Thus to drop the middle 10 rows
worm[(6:15),]
## Field.Name Area Slope Vegetation Soil.pH Damp Worm.density
## 6 Oak.Mead 3.1 2 Grassland 3.9 FALSE 2
## 7 Church.Field 3.5 3 Grassland 4.2 FALSE 3
## 8 Ashurst 2.1 0 Arable 4.8 FALSE 4
## 9 The.Orchard 1.9 0 Orchard 5.7 FALSE 9
## 10 Rookery.Slope 1.5 4 Grassland 5.0 TRUE 7
## 11 Garden.Wood 2.9 10 Scrub 5.2 FALSE 8
## 12 North.Gravel 3.3 1 Grassland 4.1 FALSE 1
## 13 South.Gravel 3.7 2 Grassland 4.0 FALSE 2
## 14 Observatory.Ridge 1.8 6 Grassland 3.8 FALSE 0
## 15 Pond.Field 4.1 0 Meadow 5.0 TRUE 6
# todas las filas que no son grasslands
# ( ! significa NOT):
worm[!(worm$Vegetation=="Grassland"),]
## Field.Name Area Slope Vegetation Soil.pH Damp Worm.density
## 2 Silwood.Bottom 5.1 2 Arable 5.2 FALSE 7
## 4 Rush.Meadow 2.4 5 Meadow 4.9 TRUE 5
## 5 Gunness.Thicket 3.8 0 Scrub 4.2 FALSE 6
## 8 Ashurst 2.1 0 Arable 4.8 FALSE 4
## 9 The.Orchard 1.9 0 Orchard 5.7 FALSE 9
## 11 Garden.Wood 2.9 10 Scrub 5.2 FALSE 8
## 15 Pond.Field 4.1 0 Meadow 5.0 TRUE 6
## 16 Water.Meadow 3.9 0 Meadow 4.9 TRUE 8
## 17 Cheapside 2.2 8 Scrub 4.7 TRUE 4
## 18 Pound.Hill 4.4 2 Arable 4.5 FALSE 5
## 20 Farm.Wood 0.8 10 Scrub 5.1 TRUE 3
worm[(worm$Vegetation=="Grassland"),]
## Field.Name Area Slope Vegetation Soil.pH Damp Worm.density
## 1 Nashs.Field 3.6 11 Grassland 4.1 FALSE 4
## 3 Nursery.Field 2.8 3 Grassland 4.3 FALSE 2
## 6 Oak.Mead 3.1 2 Grassland 3.9 FALSE 2
## 7 Church.Field 3.5 3 Grassland 4.2 FALSE 3
## 10 Rookery.Slope 1.5 4 Grassland 5.0 TRUE 7
## 12 North.Gravel 3.3 1 Grassland 4.1 FALSE 1
## 13 South.Gravel 3.7 2 Grassland 4.0 FALSE 2
## 14 Observatory.Ridge 1.8 6 Grassland 3.8 FALSE 0
## 19 Gravel.Pit 2.9 1 Grassland 3.5 FALSE 1
worm[(worm$Vegetation=="Grassland") & worm$Damp==T,]
## Field.Name Area Slope Vegetation Soil.pH Damp Worm.density
## 10 Rookery.Slope 1.5 4 Grassland 5 TRUE 7
worm[which(worm$Damp==F),]
## Field.Name Area Slope Vegetation Soil.pH Damp Worm.density
## 1 Nashs.Field 3.6 11 Grassland 4.1 FALSE 4
## 2 Silwood.Bottom 5.1 2 Arable 5.2 FALSE 7
## 3 Nursery.Field 2.8 3 Grassland 4.3 FALSE 2
## 5 Gunness.Thicket 3.8 0 Scrub 4.2 FALSE 6
## 6 Oak.Mead 3.1 2 Grassland 3.9 FALSE 2
## 7 Church.Field 3.5 3 Grassland 4.2 FALSE 3
## 8 Ashurst 2.1 0 Arable 4.8 FALSE 4
## 9 The.Orchard 1.9 0 Orchard 5.7 FALSE 9
## 11 Garden.Wood 2.9 10 Scrub 5.2 FALSE 8
## 12 North.Gravel 3.3 1 Grassland 4.1 FALSE 1
## 13 South.Gravel 3.7 2 Grassland 4.0 FALSE 2
## 14 Observatory.Ridge 1.8 6 Grassland 3.8 FALSE 0
## 18 Pound.Hill 4.4 2 Arable 4.5 FALSE 5
## 19 Gravel.Pit 2.9 1 Grassland 3.5 FALSE 1
worm[which(worm$Damp==T),]
## Field.Name Area Slope Vegetation Soil.pH Damp Worm.density
## 4 Rush.Meadow 2.4 5 Meadow 4.9 TRUE 5
## 10 Rookery.Slope 1.5 4 Grassland 5.0 TRUE 7
## 15 Pond.Field 4.1 0 Meadow 5.0 TRUE 6
## 16 Water.Meadow 3.9 0 Meadow 4.9 TRUE 8
## 17 Cheapside 2.2 8 Scrub 4.7 TRUE 4
## 20 Farm.Wood 0.8 10 Scrub 5.1 TRUE 3
# 4.5 Omitiendo filas que contienen, NA
worm.omit <- read.table("C:\\Users\\Luis\\Documents\\therbook\\worms.missing.txt",
header = TRUE,sep = "")
worm.omit
## Field.Name Area Slope Vegetation Soil.pH Damp Worm.density
## 1 Nashs.Field 3.6 11 Grassland 4.1 FALSE 4
## 2 Silwood.Bottom 5.1 NA Arable 5.2 FALSE 7
## 3 Nursery.Field 2.8 3 Grassland 4.3 FALSE 2
## 4 Rush.Meadow 2.4 5 Meadow 4.9 TRUE 5
## 5 Gunness.Thicket 3.8 0 Scrub 4.2 FALSE 6
## 6 Oak.Mead 3.1 2 Grassland 3.9 FALSE 2
## 7 Church.Field 3.5 3 Grassland NA NA NA
## 8 Ashurst 2.1 0 Arable 4.8 FALSE 4
## 9 The.Orchard 1.9 0 Orchard 5.7 FALSE 9
## 10 Rookery.Slope 1.5 4 Grassland 5.0 TRUE 7
## 11 Garden.Wood 2.9 10 Scrub 5.2 FALSE 8
## 12 North.Gravel 3.3 1 Grassland 4.1 FALSE 1
## 13 South.Gravel 3.7 2 Grassland 4.0 FALSE 2
## 14 Observatory.Ridge 1.8 6 Grassland 3.8 FALSE 0
## 15 Pond.Field 4.1 0 Meadow 5.0 TRUE 6
## 16 Water.Meadow 3.9 0 Meadow 4.9 TRUE 8
## 17 Cheapside 2.2 8 Scrub 4.7 TRUE 4
## 18 Pound.Hill 4.4 2 Arable 4.5 FALSE 5
## 19 Gravel.Pit NA 1 Grassland 3.5 FALSE 1
## 20 Farm.Wood 0.8 10 Scrub 5.1 TRUE 3
na.omit(worm.omit)
## Field.Name Area Slope Vegetation Soil.pH Damp Worm.density
## 1 Nashs.Field 3.6 11 Grassland 4.1 FALSE 4
## 3 Nursery.Field 2.8 3 Grassland 4.3 FALSE 2
## 4 Rush.Meadow 2.4 5 Meadow 4.9 TRUE 5
## 5 Gunness.Thicket 3.8 0 Scrub 4.2 FALSE 6
## 6 Oak.Mead 3.1 2 Grassland 3.9 FALSE 2
## 8 Ashurst 2.1 0 Arable 4.8 FALSE 4
## 9 The.Orchard 1.9 0 Orchard 5.7 FALSE 9
## 10 Rookery.Slope 1.5 4 Grassland 5.0 TRUE 7
## 11 Garden.Wood 2.9 10 Scrub 5.2 FALSE 8
## 12 North.Gravel 3.3 1 Grassland 4.1 FALSE 1
## 13 South.Gravel 3.7 2 Grassland 4.0 FALSE 2
## 14 Observatory.Ridge 1.8 6 Grassland 3.8 FALSE 0
## 15 Pond.Field 4.1 0 Meadow 5.0 TRUE 6
## 16 Water.Meadow 3.9 0 Meadow 4.9 TRUE 8
## 17 Cheapside 2.2 8 Scrub 4.7 TRUE 4
## 18 Pound.Hill 4.4 2 Arable 4.5 FALSE 5
## 20 Farm.Wood 0.8 10 Scrub 5.1 TRUE 3
complete.cases(worm.omit)
## [1] TRUE FALSE TRUE TRUE TRUE TRUE FALSE TRUE TRUE TRUE TRUE
## [12] TRUE TRUE TRUE TRUE TRUE TRUE TRUE FALSE TRUE
# 4.7 Oredenamiento complejo con direcciones mixtas
# Algunas veces hay multiples variables para ordenar,
# pero las variables deben ser ordenadas en direcciones opuestas.
# este ejemplo, se requiere ordenar la data
# primero por Vegetation en oden alfabetico (el default) y
# despues entre cada tipo de Vegetation ordenar por Worm.density
# en orden decreciente (densidades altas primero). El
# truco aqui esta en usar order (en vez de rev(order))
# pero poner un signo menos en frente de Worm.density
# Asi:
worm[order(worm$Vegetation,-worm$Worm.density),]
## Field.Name Area Slope Vegetation Soil.pH Damp Worm.density
## 2 Silwood.Bottom 5.1 2 Arable 5.2 FALSE 7
## 18 Pound.Hill 4.4 2 Arable 4.5 FALSE 5
## 8 Ashurst 2.1 0 Arable 4.8 FALSE 4
## 10 Rookery.Slope 1.5 4 Grassland 5.0 TRUE 7
## 1 Nashs.Field 3.6 11 Grassland 4.1 FALSE 4
## 7 Church.Field 3.5 3 Grassland 4.2 FALSE 3
## 3 Nursery.Field 2.8 3 Grassland 4.3 FALSE 2
## 6 Oak.Mead 3.1 2 Grassland 3.9 FALSE 2
## 13 South.Gravel 3.7 2 Grassland 4.0 FALSE 2
## 12 North.Gravel 3.3 1 Grassland 4.1 FALSE 1
## 19 Gravel.Pit 2.9 1 Grassland 3.5 FALSE 1
## 14 Observatory.Ridge 1.8 6 Grassland 3.8 FALSE 0
## 16 Water.Meadow 3.9 0 Meadow 4.9 TRUE 8
## 15 Pond.Field 4.1 0 Meadow 5.0 TRUE 6
## 4 Rush.Meadow 2.4 5 Meadow 4.9 TRUE 5
## 9 The.Orchard 1.9 0 Orchard 5.7 FALSE 9
## 11 Garden.Wood 2.9 10 Scrub 5.2 FALSE 8
## 5 Gunness.Thicket 3.8 0 Scrub 4.2 FALSE 6
## 17 Cheapside 2.2 8 Scrub 4.7 TRUE 4
## 20 Farm.Wood 0.8 10 Scrub 5.1 TRUE 3
# el uso del signo menos solo funciona cuando se esta ordenando
# variables numericas.
# para niveles de factores use la funcion rank
# para hacer los niveles numericos asi:
worm[order(-rank(worm$Vegetation,-worm$Worm.density)),]
## Field.Name Area Slope Vegetation Soil.pH Damp Worm.density
## 5 Gunness.Thicket 3.8 0 Scrub 4.2 FALSE 6
## 11 Garden.Wood 2.9 10 Scrub 5.2 FALSE 8
## 17 Cheapside 2.2 8 Scrub 4.7 TRUE 4
## 20 Farm.Wood 0.8 10 Scrub 5.1 TRUE 3
## 9 The.Orchard 1.9 0 Orchard 5.7 FALSE 9
## 4 Rush.Meadow 2.4 5 Meadow 4.9 TRUE 5
## 15 Pond.Field 4.1 0 Meadow 5.0 TRUE 6
## 16 Water.Meadow 3.9 0 Meadow 4.9 TRUE 8
## 1 Nashs.Field 3.6 11 Grassland 4.1 FALSE 4
## 3 Nursery.Field 2.8 3 Grassland 4.3 FALSE 2
## 6 Oak.Mead 3.1 2 Grassland 3.9 FALSE 2
## 7 Church.Field 3.5 3 Grassland 4.2 FALSE 3
## 10 Rookery.Slope 1.5 4 Grassland 5.0 TRUE 7
## 12 North.Gravel 3.3 1 Grassland 4.1 FALSE 1
## 13 South.Gravel 3.7 2 Grassland 4.0 FALSE 2
## 14 Observatory.Ridge 1.8 6 Grassland 3.8 FALSE 0
## 19 Gravel.Pit 2.9 1 Grassland 3.5 FALSE 1
## 2 Silwood.Bottom 5.1 2 Arable 5.2 FALSE 7
## 8 Ashurst 2.1 0 Arable 4.8 FALSE 4
## 18 Pound.Hill 4.4 2 Arable 4.5 FALSE 5
# 4.12 Usando la funcion match en dataframes
unique(worm$Vegetation)
## [1] Grassland Arable Meadow Scrub Orchard
## Levels: Arable Grassland Meadow Orchard Scrub
# y queremos saber el herbicida apropiado a usar
# en c/u de los 20 campos. Los herbicidas estan en otra dataframe
# que contiene las recomendaciones para
# para una comunidad de plantas mucho mayor
herbicidas <- read.table("C:\\Users\\Luis\\Documents\\therbook\\herbicides.txt",header = TRUE)
herbicidas
## Type Herbicide
## 1 Woodland Fusilade
## 2 Conifer Weedwipe
## 3 Arable Twinspan
## 4 Hill Weedwipe
## 5 Bracken Fusilade
## 6 Scrub Weedwipe
## 7 Grassland Allclear
## 8 Chalk Vanquish
## 9 Meadow Propinol
## 10 Lawn Vanquish
## 11 Orchard Fusilade
## 12 Verge Allclear
herbicidas$Herbicide[match(worm$Vegetation,herbicidas$Type)]
## [1] Allclear Twinspan Allclear Propinol Weedwipe Allclear Allclear
## [8] Twinspan Fusilade Allclear Weedwipe Allclear Allclear Allclear
## [15] Propinol Propinol Weedwipe Twinspan Allclear Weedwipe
## Levels: Allclear Fusilade Propinol Twinspan Vanquish Weedwipe
worm$hb<-herbicidas$Herbicide[match(worm$Vegetation,herbicidas$Type)]
worm
## Field.Name Area Slope Vegetation Soil.pH Damp Worm.density
## 1 Nashs.Field 3.6 11 Grassland 4.1 FALSE 4
## 2 Silwood.Bottom 5.1 2 Arable 5.2 FALSE 7
## 3 Nursery.Field 2.8 3 Grassland 4.3 FALSE 2
## 4 Rush.Meadow 2.4 5 Meadow 4.9 TRUE 5
## 5 Gunness.Thicket 3.8 0 Scrub 4.2 FALSE 6
## 6 Oak.Mead 3.1 2 Grassland 3.9 FALSE 2
## 7 Church.Field 3.5 3 Grassland 4.2 FALSE 3
## 8 Ashurst 2.1 0 Arable 4.8 FALSE 4
## 9 The.Orchard 1.9 0 Orchard 5.7 FALSE 9
## 10 Rookery.Slope 1.5 4 Grassland 5.0 TRUE 7
## 11 Garden.Wood 2.9 10 Scrub 5.2 FALSE 8
## 12 North.Gravel 3.3 1 Grassland 4.1 FALSE 1
## 13 South.Gravel 3.7 2 Grassland 4.0 FALSE 2
## 14 Observatory.Ridge 1.8 6 Grassland 3.8 FALSE 0
## 15 Pond.Field 4.1 0 Meadow 5.0 TRUE 6
## 16 Water.Meadow 3.9 0 Meadow 4.9 TRUE 8
## 17 Cheapside 2.2 8 Scrub 4.7 TRUE 4
## 18 Pound.Hill 4.4 2 Arable 4.5 FALSE 5
## 19 Gravel.Pit 2.9 1 Grassland 3.5 FALSE 1
## 20 Farm.Wood 0.8 10 Scrub 5.1 TRUE 3
## hb
## 1 Allclear
## 2 Twinspan
## 3 Allclear
## 4 Propinol
## 5 Weedwipe
## 6 Allclear
## 7 Allclear
## 8 Twinspan
## 9 Fusilade
## 10 Allclear
## 11 Weedwipe
## 12 Allclear
## 13 Allclear
## 14 Allclear
## 15 Propinol
## 16 Propinol
## 17 Weedwipe
## 18 Twinspan
## 19 Allclear
## 20 Weedwipe