#comandos de filtro
library(tidyverse)
## -- Attaching packages --------------------------------------- tidyverse 1.3.1 --
## v ggplot2 3.3.5 v purrr 0.3.4
## v tibble 3.1.5 v dplyr 1.0.7
## v tidyr 1.1.4 v stringr 1.4.0
## v readr 2.0.2 v forcats 0.5.1
## -- Conflicts ------------------------------------------ tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()
data("mtcars")
#select only cars with cylinders
six.cyl.only <- filter(mtcars, cyl == 6)
six.cyl.only
## mpg cyl disp hp drat wt qsec vs am gear carb
## Mazda RX4 21.0 6 160.0 110 3.90 2.620 16.46 0 1 4 4
## Mazda RX4 Wag 21.0 6 160.0 110 3.90 2.875 17.02 0 1 4 4
## Hornet 4 Drive 21.4 6 258.0 110 3.08 3.215 19.44 1 0 3 1
## Valiant 18.1 6 225.0 105 2.76 3.460 20.22 1 0 3 1
## Merc 280 19.2 6 167.6 123 3.92 3.440 18.30 1 0 4 4
## Merc 280C 17.8 6 167.6 123 3.92 3.440 18.90 1 0 4 4
## Ferrari Dino 19.7 6 145.0 175 3.62 2.770 15.50 0 1 5 6
#filtro de condición múltiple
Six.cylinder.and.110.horses.power <- filter(mtcars, cyl == 6, hp == 110)
Six.cylinder.and.110.horses.power
## mpg cyl disp hp drat wt qsec vs am gear carb
## Mazda RX4 21.0 6 160 110 3.90 2.620 16.46 0 1 4 4
## Mazda RX4 Wag 21.0 6 160 110 3.90 2.875 17.02 0 1 4 4
## Hornet 4 Drive 21.4 6 258 110 3.08 3.215 19.44 1 0 3 1
# OR lógica y filtrado
gear.eq.4.or.more.than.8 <- filter(mtcars, gear == 4|cyl > 6)
gear.eq.4.or.more.than.8
## mpg cyl disp hp drat wt qsec vs am gear carb
## Mazda RX4 21.0 6 160.0 110 3.90 2.620 16.46 0 1 4 4
## Mazda RX4 Wag 21.0 6 160.0 110 3.90 2.875 17.02 0 1 4 4
## Datsun 710 22.8 4 108.0 93 3.85 2.320 18.61 1 1 4 1
## Hornet Sportabout 18.7 8 360.0 175 3.15 3.440 17.02 0 0 3 2
## Duster 360 14.3 8 360.0 245 3.21 3.570 15.84 0 0 3 4
## Merc 240D 24.4 4 146.7 62 3.69 3.190 20.00 1 0 4 2
## Merc 230 22.8 4 140.8 95 3.92 3.150 22.90 1 0 4 2
## Merc 280 19.2 6 167.6 123 3.92 3.440 18.30 1 0 4 4
## Merc 280C 17.8 6 167.6 123 3.92 3.440 18.90 1 0 4 4
## Merc 450SE 16.4 8 275.8 180 3.07 4.070 17.40 0 0 3 3
## Merc 450SL 17.3 8 275.8 180 3.07 3.730 17.60 0 0 3 3
## Merc 450SLC 15.2 8 275.8 180 3.07 3.780 18.00 0 0 3 3
## Cadillac Fleetwood 10.4 8 472.0 205 2.93 5.250 17.98 0 0 3 4
## Lincoln Continental 10.4 8 460.0 215 3.00 5.424 17.82 0 0 3 4
## Chrysler Imperial 14.7 8 440.0 230 3.23 5.345 17.42 0 0 3 4
## Fiat 128 32.4 4 78.7 66 4.08 2.200 19.47 1 1 4 1
## Honda Civic 30.4 4 75.7 52 4.93 1.615 18.52 1 1 4 2
## Toyota Corolla 33.9 4 71.1 65 4.22 1.835 19.90 1 1 4 1
## Dodge Challenger 15.5 8 318.0 150 2.76 3.520 16.87 0 0 3 2
## AMC Javelin 15.2 8 304.0 150 3.15 3.435 17.30 0 0 3 2
## Camaro Z28 13.3 8 350.0 245 3.73 3.840 15.41 0 0 3 4
## Pontiac Firebird 19.2 8 400.0 175 3.08 3.845 17.05 0 0 3 2
## Fiat X1-9 27.3 4 79.0 66 4.08 1.935 18.90 1 1 4 1
## Ford Pantera L 15.8 8 351.0 264 4.22 3.170 14.50 0 1 5 4
## Maserati Bora 15.0 8 301.0 335 3.54 3.570 14.60 0 1 5 8
## Volvo 142E 21.4 4 121.0 109 4.11 2.780 18.60 1 1 4 2
#filtrado por mínimos, máximos y otros criterios
library(tidyverse)
smallest.engine.displacement <- filter(mtcars, disp == min(disp))
smallest.engine.displacement
## mpg cyl disp hp drat wt qsec vs am gear carb
## Toyota Corolla 33.9 4 71.1 65 4.22 1.835 19.9 1 1 4 1
#filtro con condiciones separadas por comas
data("ChickWeight")
chick.subset <- filter(ChickWeight, Time < 3, weight > 53)
chick.subset
## weight Time Chick Diet
## 1 55 2 22 2
## 2 55 2 40 3
## 3 55 2 43 4
## 4 54 2 50 4
#filtro de valores perdidos para una colomna
data("airquality")
head(airquality,10) #antes de filtrar
## Ozone Solar.R Wind Temp Month Day
## 1 41 190 7.4 67 5 1
## 2 36 118 8.0 72 5 2
## 3 12 149 12.6 74 5 3
## 4 18 313 11.5 62 5 4
## 5 NA NA 14.3 56 5 5
## 6 28 NA 14.9 66 5 6
## 7 23 299 8.6 65 5 7
## 8 19 99 13.8 59 5 8
## 9 8 19 20.1 61 5 9
## 10 NA 194 8.6 69 5 10
#remover cualquier irela con valores extraviados en la columna Ozone
no.missing.ozone = filter(airquality, !is.na(Ozone))
head(no.missing.ozone,8) #despues del filtrado
## Ozone Solar.R Wind Temp Month Day
## 1 41 190 7.4 67 5 1
## 2 36 118 8.0 72 5 2
## 3 12 149 12.6 74 5 3
## 4 18 313 11.5 62 5 4
## 5 28 NA 14.9 66 5 6
## 6 23 299 8.6 65 5 7
## 7 19 99 13.8 59 5 8
## 8 8 19 20.1 61 5 9
#filtro de irelas con NA en cualquier dataset
airqual.no.NA.anywhere<-filter(airquality[1:10,],complete.cases(airquality[1:10,]))
airqual.no.NA.anywhere
## Ozone Solar.R Wind Temp Month Day
## 1 41 190 7.4 67 5 1
## 2 36 118 8.0 72 5 2
## 3 12 149 12.6 74 5 3
## 4 18 313 11.5 62 5 4
## 5 23 299 8.6 65 5 7
## 6 19 99 13.8 59 5 8
## 7 8 19 20.1 61 5 9
#filtros por %in%
data("iris")
table(iris$Species) #conteo de especies en el dataset
##
## setosa versicolor virginica
## 50 50 50
iris.two.species<-filter(iris,Species%in%c("setosa","virginica"))
table(iris.two.species$Species)
##
## setosa versicolor virginica
## 50 0 50
#filtro para ozono > 29 e incluyendo solo 3 columnas
data("airquality")
airqual.3.colums<-filter(airquality,Ozone>29)[,1:3]
head(airqual.3.colums)
## Ozone Solar.R Wind
## 1 41 190 7.4
## 2 36 118 8.0
## 3 34 307 12.0
## 4 30 322 11.5
## 5 32 92 12.0
## 6 45 252 14.9
#filtro por frecuencias totales de un valor a traves de todas las irelas
table(mtcars$gear)
##
## 3 4 5
## 15 12 5
more.frequent.number.of.gears <- mtcars%>%
group_by(gear)%>%
filter(n()>10)
table(more.frequent.number.of.gears$gear)
##
## 3 4
## 15 12
more.frequent.no.of.gears.and.low.horsepower <- mtcars %>%
group_by(gear) %>%
filter(n() > 10, hp < 105)
table(more.frequent.no.of.gears.and.low.horsepower$gear)
##
## 3 4
## 1 7
#filtrps ´pr nombres de columna usando "starts with"
names(iris) #muestra los nombres de las columnas
## [1] "Sepal.Length" "Sepal.Width" "Petal.Length" "Petal.Width" "Species"
iris.display <- iris %>% dplyr::select(starts_with("S"))
head(iris.display) #usar head para reducir el número de irelas en la salida
## Sepal.Length Sepal.Width Species
## 1 5.1 3.5 setosa
## 2 4.9 3.0 setosa
## 3 4.7 3.2 setosa
## 4 4.6 3.1 setosa
## 5 5.0 3.6 setosa
## 6 5.4 3.9 setosa
#filtro de irelas: Criterios de las columnas. Encontrar irelas con criterios como el máximo
new.mtcars <- mtcars %>% filter_at(vars(cyl, hp),
all_vars(. == max(.)))
new.mtcars
## mpg cyl disp hp drat wt qsec vs am gear carb
## Maserati Bora 15 8 301 335 3.54 3.57 14.6 0 1 5 8
msleep<-ggplot2::msleep
msleep
## # A tibble: 83 x 11
## name genus vore order conservation sleep_total sleep_rem sleep_cycle awake
## <chr> <chr> <chr> <chr> <chr> <dbl> <dbl> <dbl> <dbl>
## 1 Cheet~ Acin~ carni Carn~ lc 12.1 NA NA 11.9
## 2 Owl m~ Aotus omni Prim~ <NA> 17 1.8 NA 7
## 3 Mount~ Aplo~ herbi Rode~ nt 14.4 2.4 NA 9.6
## 4 Great~ Blar~ omni Sori~ lc 14.9 2.3 0.133 9.1
## 5 Cow Bos herbi Arti~ domesticated 4 0.7 0.667 20
## 6 Three~ Brad~ herbi Pilo~ <NA> 14.4 2.2 0.767 9.6
## 7 North~ Call~ carni Carn~ vu 8.7 1.4 0.383 15.3
## 8 Vespe~ Calo~ <NA> Rode~ <NA> 7 NA NA 17
## 9 Dog Canis carni Carn~ domesticated 10.1 2.9 0.333 13.9
## 10 Roe d~ Capr~ herbi Arti~ lc 3 NA NA 21
## # ... with 73 more rows, and 2 more variables: brainwt <dbl>, bodywt <dbl>
msleep.over.5 <- msleep %>%
select(name, sleep_total:sleep_rem, brainwt:bodywt) %>%
filter_at(vars(contains("sleep")), all_vars(.>5))
msleep.over.5
## # A tibble: 2 x 5
## name sleep_total sleep_rem brainwt bodywt
## <chr> <dbl> <dbl> <dbl> <dbl>
## 1 Thick-tailed opposum 19.4 6.6 NA 0.37
## 2 Giant armadillo 18.1 6.1 0.081 60
#arreglar(clasificar)
msleep <- ggplot2::msleep
msleep[,1:4]
## # A tibble: 83 x 4
## name genus vore order
## <chr> <chr> <chr> <chr>
## 1 Cheetah Acinonyx carni Carnivora
## 2 Owl monkey Aotus omni Primates
## 3 Mountain beaver Aplodontia herbi Rodentia
## 4 Greater short-tailed shrew Blarina omni Soricomorpha
## 5 Cow Bos herbi Artiodactyla
## 6 Three-toed sloth Bradypus herbi Pilosa
## 7 Northern fur seal Callorhinus carni Carnivora
## 8 Vesper mouse Calomys <NA> Rodentia
## 9 Dog Canis carni Carnivora
## 10 Roe deer Capreolus herbi Artiodactyla
## # ... with 73 more rows
#ascendente
animal.name.sequence<-arrange(msleep,vore,order)
animal.name.sequence[,1:4]
## # A tibble: 83 x 4
## name genus vore order
## <chr> <chr> <chr> <chr>
## 1 Cheetah Acinonyx carni Carnivora
## 2 Northern fur seal Callorhinus carni Carnivora
## 3 Dog Canis carni Carnivora
## 4 Domestic cat Felis carni Carnivora
## 5 Gray seal Haliochoerus carni Carnivora
## 6 Tiger Panthera carni Carnivora
## 7 Jaguar Panthera carni Carnivora
## 8 Lion Panthera carni Carnivora
## 9 Caspian seal Phoca carni Carnivora
## 10 Genet Genetta carni Carnivora
## # ... with 73 more rows
#descendente
animal.name.sequence.desc<-arrange(msleep,vore,desc(order))
head(animal.name.sequence.desc[,1:4])
## # A tibble: 6 x 4
## name genus vore order
## <chr> <chr> <chr> <chr>
## 1 Northern grasshopper mouse Onychomys carni Rodentia
## 2 Slow loris Nyctibeus carni Primates
## 3 Thick-tailed opposum Lutreolina carni Didelphimorphia
## 4 Long-nosed armadillo Dasypus carni Cingulata
## 5 Pilot whale Globicephalus carni Cetacea
## 6 Common porpoise Phocoena carni Cetacea
#renombrar
names(iris)
## [1] "Sepal.Length" "Sepal.Width" "Petal.Length" "Petal.Width" "Species"
#mostras nombres de columnas
renamed.iris <- rename(iris, width.of.petals = Petal.Width,
various.plants.and.animals = Species)
names(renamed.iris)
## [1] "Sepal.Length" "Sepal.Width"
## [3] "Petal.Length" "width.of.petals"
## [5] "various.plants.and.animals"
#mudar
data("ChickWeight")
ChickWeight[1:2,] #primeras dos irelas
## weight Time Chick Diet
## 1 42 0 1 1
## 2 51 2 1 1
#primeras 2 irelas con nuevos campos añadidos
Chickweight.with.log <- mutate(ChickWeight,log.of.weight = log10(weight))
Chickweight.with.log[1:2,]
## weight Time Chick Diet log.of.weight
## 1 42 0 1 1 1.623249
## 2 51 2 1 1 1.707570
#mutate_all para añadir nuevos campos al mismo tiempo
msleep <- ggplot2::msleep
names(msleep)
## [1] "name" "genus" "vore" "order" "conservation"
## [6] "sleep_total" "sleep_rem" "sleep_cycle" "awake" "brainwt"
## [11] "bodywt"
#ahora añade variales con raiz cuadrada7columnas para variables en columnas 6-11
msleep.with.square.roots <- mutate_all(msleep[,6:11],
funs("square root" = sqrt( . )))
## Warning: `funs()` was deprecated in dplyr 0.8.0.
## Please use a list of either functions or lambdas:
##
## # Simple named list:
## list(mean = mean, median = median)
##
## # Auto named with `tibble::lst()`:
## tibble::lst(mean, median)
##
## # Using lambdas
## list(~ mean(., trim = .2), ~ median(., na.rm = TRUE))
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was generated.
names(msleep.with.square.roots)
## [1] "sleep_total" "sleep_rem"
## [3] "sleep_cycle" "awake"
## [5] "brainwt" "bodywt"
## [7] "sleep_total_square root" "sleep_rem_square root"
## [9] "sleep_cycle_square root" "awake_square root"
## [11] "brainwt_square root" "bodywt_square root"
msleep.with.square.roots
## # A tibble: 83 x 12
## sleep_total sleep_rem sleep_cycle awake brainwt bodywt `sleep_total_square~
## <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 12.1 NA NA 11.9 NA 50 3.48
## 2 17 1.8 NA 7 0.0155 0.48 4.12
## 3 14.4 2.4 NA 9.6 NA 1.35 3.79
## 4 14.9 2.3 0.133 9.1 0.00029 0.019 3.86
## 5 4 0.7 0.667 20 0.423 600 2
## 6 14.4 2.2 0.767 9.6 NA 3.85 3.79
## 7 8.7 1.4 0.383 15.3 NA 20.5 2.95
## 8 7 NA NA 17 NA 0.045 2.65
## 9 10.1 2.9 0.333 13.9 0.07 14 3.18
## 10 3 NA NA 21 0.0982 14.8 1.73
## # ... with 73 more rows, and 5 more variables: sleep_rem_square root <dbl>,
## # sleep_cycle_square root <dbl>, awake_square root <dbl>,
## # brainwt_square root <dbl>, bodywt_square root <dbl>
#mutate_at para añadir espacios
data("Titanic")
Titanic <- as.data.frame(Titanic)
head(Titanic)
## Class Sex Age Survived Freq
## 1 1st Male Child No 0
## 2 2nd Male Child No 0
## 3 3rd Male Child No 35
## 4 Crew Male Child No 0
## 5 1st Female Child No 0
## 6 2nd Female Child No 0
titanic.with.ranks <- mutate_at(Titanic, vars(Class,Age,Survived),
funs(Rank = min_rank(desc(.))))
head(titanic.with.ranks)
## Class Sex Age Survived Freq Class_Rank Age_Rank Survived_Rank
## 1 1st Male Child No 0 25 17 17
## 2 2nd Male Child No 0 17 17 17
## 3 3rd Male Child No 35 9 17 17
## 4 Crew Male Child No 0 1 17 17
## 5 1st Female Child No 0 25 17 17
## 6 2nd Female Child No 0 17 17 17
#mutate_if
divide.by.10 <- function (a.number) (a.number / 10)
new.df <- CO2 %>%
mutate_if(is.numeric, divide.by.10)
head(new.df)
## Plant Type Treatment conc uptake
## 1 Qn1 Quebec nonchilled 9.5 1.60
## 2 Qn1 Quebec nonchilled 17.5 3.04
## 3 Qn1 Quebec nonchilled 25.0 3.48
## 4 Qn1 Quebec nonchilled 35.0 3.72
## 5 Qn1 Quebec nonchilled 50.0 3.53
## 6 Qn1 Quebec nonchilled 67.5 3.92
df <- data.frame(
alpha = c(22, 1, NA),
almond = c(0, 5, 10),
grape = c(0, 2, 2),
apple = c(NA, 5, 10))
df
## alpha almond grape apple
## 1 22 0 0 NA
## 2 1 5 2 5
## 3 NA 10 2 10
#Detección de cadena e indicador de duplicado TRUE/FALSE
msleep <- ggplot2::msleep
table(msleep$vore)
##
## carni herbi insecti omni
## 19 32 5 20
msleep.no.c.or.a <- filter(msleep, !str_detect(vore,
paste(c("c","a"), collapse = "|")))
table(msleep.no.c.or.a$vore)
##
## herbi omni
## 32 20
msleep.with.dup.indicator<-mutate(msleep,duplicate.indicator=duplicated(conservation))
msleep.with.dup.indicator[1:6,]
## # A tibble: 6 x 12
## name genus vore order conservation sleep_total sleep_rem sleep_cycle awake
## <chr> <chr> <chr> <chr> <chr> <dbl> <dbl> <dbl> <dbl>
## 1 Cheetah Acin~ carni Carn~ lc 12.1 NA NA 11.9
## 2 Owl mo~ Aotus omni Prim~ <NA> 17 1.8 NA 7
## 3 Mounta~ Aplo~ herbi Rode~ nt 14.4 2.4 NA 9.6
## 4 Greate~ Blar~ omni Sori~ lc 14.9 2.3 0.133 9.1
## 5 Cow Bos herbi Arti~ domesticated 4 0.7 0.667 20
## 6 Three-~ Brad~ herbi Pilo~ <NA> 14.4 2.2 0.767 9.6
## # ... with 3 more variables: brainwt <dbl>, bodywt <dbl>,
## # duplicate.indicator <lgl>
msleep.with.dup.indicator<-mutate(msleep,duplicate.indicator=duplicated(conservation))
msleep.with.dup.indicator[1:6,c(1,2,3,12)]
## # A tibble: 6 x 4
## name genus vore duplicate.indicator
## <chr> <chr> <chr> <lgl>
## 1 Cheetah Acinonyx carni FALSE
## 2 Owl monkey Aotus omni FALSE
## 3 Mountain beaver Aplodontia herbi FALSE
## 4 Greater short-tailed shrew Blarina omni TRUE
## 5 Cow Bos herbi FALSE
## 6 Three-toed sloth Bradypus herbi TRUE
msleep.with.dup.indicator2 <- mutate(msleep,
duplicate.indicator = duplicated(conservation, genus)) %>%
arrange(conservation,genus)
msleep.with.dup.indicator2
## # A tibble: 83 x 12
## name genus vore order conservation sleep_total sleep_rem sleep_cycle awake
## <chr> <chr> <chr> <chr> <chr> <dbl> <dbl> <dbl> <dbl>
## 1 Giraf~ Gira~ herbi Arti~ cd 1.9 0.4 NA 22.1
## 2 Pilot~ Glob~ carni Ceta~ cd 2.7 0.1 NA 21.4
## 3 Cow Bos herbi Arti~ domesticated 4 0.7 0.667 20
## 4 Dog Canis carni Carn~ domesticated 10.1 2.9 0.333 13.9
## 5 Guine~ Cavis herbi Rode~ domesticated 9.4 0.8 0.217 14.6
## 6 Chinc~ Chin~ herbi Rode~ domesticated 12.5 1.5 0.117 11.5
## 7 Horse Equus herbi Peri~ domesticated 2.9 0.6 1 21.1
## 8 Donkey Equus herbi Peri~ domesticated 3.1 0.4 NA 20.9
## 9 Domes~ Felis carni Carn~ domesticated 12.5 3.2 0.417 11.5
## 10 Rabbit Oryc~ herbi Lago~ domesticated 8.4 0.9 0.417 15.6
## # ... with 73 more rows, and 3 more variables: brainwt <dbl>, bodywt <dbl>,
## # duplicate.indicator <lgl>
#Crear dataframe 2
fruit <- c("apple","pear","orange","grape", "orange","orange")
x <- c(1,2,4,9,4,6)
y <- c(22,3,4,55,15,9)
z <- c(3,1,4,10,12,8)
w <- c(2,2,2,4,5,6)
df <- data.frame(fruit,x,y,z,w)
df
## fruit x y z w
## 1 apple 1 22 3 2
## 2 pear 2 3 1 2
## 3 orange 4 4 4 2
## 4 grape 9 55 10 4
## 5 orange 4 15 12 5
## 6 orange 6 9 8 6
df.show.single.dup <- mutate(df, duplicate.indicator = duplicated(fruit))
df.show.single.dup
## fruit x y z w duplicate.indicator
## 1 apple 1 22 3 2 FALSE
## 2 pear 2 3 1 2 FALSE
## 3 orange 4 4 4 2 FALSE
## 4 grape 9 55 10 4 FALSE
## 5 orange 4 15 12 5 TRUE
## 6 orange 6 9 8 6 TRUE
fruit <- c("apple","pear","orange","grape", "orange","orange")
x <- c(1,2,4,9,4,6)
y <- c(22,3,4,55,15,9)
z <- c(3,1,4,10,12,8)
df <- data.frame(fruit,x,y,z)
df <- mutate(df, z = NULL)
df
## fruit x y
## 1 apple 1 22
## 2 pear 2 3
## 3 orange 4 4
## 4 grape 9 55
## 5 orange 4 15
## 6 orange 6 9
#Secuencia de codigo requerida
(!require("nycflights13"))
## Loading required package: nycflights13
## [1] FALSE
install.packages("nycflights13")
## Warning: package 'nycflights13' is in use and will not be installed
library(nycflights13)
library(tidyverse)
mutate(flights,
gain = arr_delay - dep_delay,
hours = air_time / 60,
gain_per_hour = gain / hours,
gain_per_minute = 60 * gain_per_hour)
## # A tibble: 336,776 x 23
## year month day dep_time sched_dep_time dep_delay arr_time sched_arr_time
## <int> <int> <int> <int> <int> <dbl> <int> <int>
## 1 2013 1 1 517 515 2 830 819
## 2 2013 1 1 533 529 4 850 830
## 3 2013 1 1 542 540 2 923 850
## 4 2013 1 1 544 545 -1 1004 1022
## 5 2013 1 1 554 600 -6 812 837
## 6 2013 1 1 554 558 -4 740 728
## 7 2013 1 1 555 600 -5 913 854
## 8 2013 1 1 557 600 -3 709 723
## 9 2013 1 1 557 600 -3 838 846
## 10 2013 1 1 558 600 -2 753 745
## # ... with 336,766 more rows, and 15 more variables: arr_delay <dbl>,
## # carrier <chr>, flight <int>, tailnum <chr>, origin <chr>, dest <chr>,
## # air_time <dbl>, distance <dbl>, hour <dbl>, minute <dbl>, time_hour <dttm>,
## # gain <dbl>, hours <dbl>, gain_per_hour <dbl>, gain_per_minute <dbl>
newfield.flights <- flights %>%
mutate(gain = arr_delay - dep_delay,
hours = air_time / 60) %>%
mutate(gain_per_hour = gain / hours) %>%
mutate(gain_per_minute = 60 * gain_per_hour)
newfield.flights[1:6,c(1:2,20:23)]
## # A tibble: 6 x 6
## year month gain hours gain_per_hour gain_per_minute
## <int> <int> <dbl> <dbl> <dbl> <dbl>
## 1 2013 1 9 3.78 2.38 143.
## 2 2013 1 16 3.78 4.23 254.
## 3 2013 1 31 2.67 11.6 698.
## 4 2013 1 -17 3.05 -5.57 -334.
## 5 2013 1 -19 1.93 -9.83 -590.
## 6 2013 1 16 2.5 6.4 384
#Transmutar. Quedarse unicamente con las variables creadas
fruit <- c("apple","pear","orange","grape", "orange","orange")
x <- c(1,2,4,9,4,6)
y <- c(22,3,4,55,15,9)
z <- c(3,1,4,10,12,8)
df <- data.frame(fruit,x,y,z)
df #antes de transmutar
## fruit x y z
## 1 apple 1 22 3
## 2 pear 2 3 1
## 3 orange 4 4 4
## 4 grape 9 55 10
## 5 orange 4 15 12
## 6 orange 6 9 8
df <- transmute(df, new.variable = x + y + z)
df#despues de transmutar
## new.variable
## 1 26
## 2 6
## 3 12
## 4 74
## 5 31
## 6 23
#Usar Across para aplicar una función sobre múltiple columnas
double.it <- function(x) x*2
head(iris)
## Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## 1 5.1 3.5 1.4 0.2 setosa
## 2 4.9 3.0 1.4 0.2 setosa
## 3 4.7 3.2 1.3 0.2 setosa
## 4 4.6 3.1 1.5 0.2 setosa
## 5 5.0 3.6 1.4 0.2 setosa
## 6 5.4 3.9 1.7 0.4 setosa
iris %>%
mutate(across(where(is.numeric), double.it)) %>%
head() #muestra un nuevo dataframe de iris con valures duplicados para las variables numéricas
## Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## 1 10.2 7.0 2.8 0.4 setosa
## 2 9.8 6.0 2.8 0.4 setosa
## 3 9.4 6.4 2.6 0.4 setosa
## 4 9.2 6.2 3.0 0.4 setosa
## 5 10.0 7.2 2.8 0.4 setosa
## 6 10.8 7.8 3.4 0.8 setosa
#mutación condicional usando case_when
row1 <- c("a","b","c","d","e","f","column.to.be.changed")
row2 <- c(1,1,1,6,6,1,2)
row3 <- c(3,4,4,6,4,4,4)
row4 <- c(4,6,25,5,5,2,9)
row5 <- c(5,3,6,3,3,6,2)
df <- as.data.frame(rbind(row2,row3,row4,row5))
names(df) <- row1
df
## a b c d e f column.to.be.changed
## row2 1 1 1 6 6 1 2
## row3 3 4 4 6 4 4 4
## row4 4 6 25 5 5 2 9
## row5 5 3 6 3 3 6 2
new.df <-df %>%
mutate(column.to.be.changed = case_when(a == 2 | a == 5 |
a == 7 | (a == 1 & b == 4) ~ 2, a == 0 | a == 1 | a == 4 |
a == 3 | c == 4 ~ 3, TRUE ~ NA_real_))
new.df
## a b c d e f column.to.be.changed
## row2 1 1 1 6 6 1 3
## row3 3 4 4 6 4 4 3
## row4 4 6 25 5 5 2 3
## row5 5 3 6 3 3 6 2
#Borrar columnas
fruit <- c("apple","pear","orange","grape", "orange","orange")
x <- c(1,2,4,9,4,6)
y <- c(22,3,4,55,15,9)
z <- c(3,1,4,10,12,8)
df <- data.frame(fruit,x,y,z) #antes de seleccionar
df
## fruit x y z
## 1 apple 1 22 3
## 2 pear 2 3 1
## 3 orange 4 4 4
## 4 grape 9 55 10
## 5 orange 4 15 12
## 6 orange 6 9 8
#poner un - en frente de la valiable que será mostrada en la tabla. En este caso fruit
new.df.no.fruit <- dplyr::select(df, -fruit)
new.df.no.fruit #after select
## x y z
## 1 1 22 3
## 2 2 3 1
## 3 4 4 4
## 4 9 55 10
## 5 4 15 12
## 6 6 9 8
#Borrar columnas por nombre usando start_with or end_with
data("mtcars")
names(mtcars)
## [1] "mpg" "cyl" "disp" "hp" "drat" "wt" "qsec" "vs" "am" "gear"
## [11] "carb"
#Borrar todas las columnas que empiecen por d
mtcars.no.col.names.start.with.d <- select(mtcars, -starts_with("d"))
names(mtcars.no.col.names.start.with.d)
## [1] "mpg" "cyl" "hp" "wt" "qsec" "vs" "am" "gear" "carb"
mtcars.no.col.names.ends.with <- select(mtcars,
- ends_with("t"))
names(mtcars.no.col.names.ends.with)
## [1] "mpg" "cyl" "disp" "hp" "qsec" "vs" "am" "gear" "carb"
#Reorganizar el orden de las columnas
fruit <- c("apple","pear","orange","grape", "orange","orange")
x <- c(1,2,4,9,4,6)
y <- c(22,3,4,55,15,9)
z <- c(3,1,4,10,12,8)
df <- data.frame(fruit,x,y,z)
df
## fruit x y z
## 1 apple 1 22 3
## 2 pear 2 3 1
## 3 orange 4 4 4
## 4 grape 9 55 10
## 5 orange 4 15 12
## 6 orange 6 9 8
#select_all para activar la función All colums
#crear un nuevo dataframe
state <- c("Maryland", "Alaska", "New Jersey")
income <- c(76067,74444,73702)
median.us <- c(61372,61372,61372)
life.expectancy <- c(78.8,78.3,80.3)
top.3.states <- data.frame(state, income, median.us,
life.expectancy)
top.3.states #antes - el nombre de las columnas no estpa capitalizado
## state income median.us life.expectancy
## 1 Maryland 76067 61372 78.8
## 2 Alaska 74444 61372 78.3
## 3 New Jersey 73702 61372 80.3
#capitalizar los nombres de las columnas usando la función "toupper"
new.top.3.states <- select_all(top.3.states, toupper)
new.top.3.states #luego de aplucar la funcion "toupper"
## STATE INCOME MEDIAN.US LIFE.EXPECTANCY
## 1 Maryland 76067 61372 78.8
## 2 Alaska 74444 61372 78.3
## 3 New Jersey 73702 61372 80.3
#seleccionar columnas utilizando la función Pull
top.3.states <- data.frame(state, income, median.us, life.expectancy)
top.3.states #muestra valores del dataframe
## state income median.us life.expectancy
## 1 Maryland 76067 61372 78.8
## 2 Alaska 74444 61372 78.3
## 3 New Jersey 73702 61372 80.3
#obtener solo los valores the la primera columna de la izquierda
pull.first.column <- pull(top.3.states,1)
pull.first.column
## [1] "Maryland" "Alaska" "New Jersey"
#usar un número negativo para mostras la primera columna de la derecha.
pull.last.column <- pull(top.3.states,-1)
pull.last.column
## [1] 78.8 78.3 80.3
#seleccionar irelas: cualquier variable presenta condiciones
nrow(mtcars)
## [1] 32
#mostrar cualquier cosa, más de 200 datos
mtcars.more.than.200 <- filter_all(mtcars, any_vars(. > 200))
nrow(mtcars.more.than.200)
## [1] 16
#seleccionar columnas: omitir si los nombres de las columnas contienen caracteres especificos
names(mtcars)
## [1] "mpg" "cyl" "disp" "hp" "drat" "wt" "qsec" "vs" "am" "gear"
## [11] "carb"
#nombres de las columnas de los dataframe luego de seleccionarlos
cars.with.no.p <- mtcars %>%
dplyr::select(-contains("p"))
names(cars.with.no.p)#ninguna columna que empiece por p está incluida en el dataframe
## [1] "cyl" "drat" "wt" "qsec" "vs" "am" "gear" "carb"
#elegir usando Wildcard Matching
names(mtcars)
## [1] "mpg" "cyl" "disp" "hp" "drat" "wt" "qsec" "vs" "am" "gear"
## [11] "carb"
subset.mtcars <- select(mtcars,
matches("pg|gea"))
names(subset.mtcars)
## [1] "mpg" "gear"
#uniser a la izquierda (el mpas común)
us.state.areas <- as.data.frame(cbind(state.abb, state.area))
us.state.areas[1:3,]
## state.abb state.area
## 1 AL 51609
## 2 AK 589757
## 3 AZ 113909
us.state.abbreviation.and.name <- as.data.frame(cbind(state.abb,
state.name))
us.state.abbreviation.and.name[1:3,]
## state.abb state.name
## 1 AL Alabama
## 2 AK Alaska
## 3 AZ Arizona
state.info.abb.area.name <- us.state.areas %>%
left_join(us.state.abbreviation.and.name, by = "state.abb")
head(state.info.abb.area.name)
## state.abb state.area state.name
## 1 AL 51609 Alabama
## 2 AK 589757 Alaska
## 3 AZ 113909 Arizona
## 4 AR 53104 Arkansas
## 5 CA 158693 California
## 6 CO 104247 Colorado
#unión interna. Primero crear el dataframe
names <- c("Sally","Tom","Frieda","Alfonzo")
team.scores <- c(3,5,2,7)
team.league <- c("alpha","beta","gamma", "omicron")
team.info <- data.frame(names, team.scores, team.league)
#crear un segundo dataframe
names = c("Sally","Tom", "Bill", "Alfonzo")
school.grades <- c("A","B","C","B")
school.info <- data.frame(names, school.grades)
school.and.team <- inner_join(team.info, school.info, by = "names")
school.and.team
## names team.scores team.league school.grades
## 1 Sally 3 alpha A
## 2 Tom 5 beta B
## 3 Alfonzo 7 omicron B
#anti union
names <- c("Sally","Tom","Frieda","Alfonzo")
team.scores <- c(3,5,2,7)
team.league <- c("alpha","beta","gamma", "omicron")
team.info <- data.frame(names, team.scores, team.league)
team.info
## names team.scores team.league
## 1 Sally 3 alpha
## 2 Tom 5 beta
## 3 Frieda 2 gamma
## 4 Alfonzo 7 omicron
names <- c("Sally","Tom", "Bill", "Alfonzo")
school.grades <- c("A","B","C","B")
school.info <- data.frame(names, school.grades)
school.info
## names school.grades
## 1 Sally A
## 2 Tom B
## 3 Bill C
## 4 Alfonzo B
team.info.but.no.grades <- anti_join(team.info, school.info,
by = "names")
team.info.but.no.grades
## names team.scores team.league
## 1 Frieda 2 gamma
#unión completa
names = c("Sally","Tom","Frieda","Alfonzo")
team.scores = c(3,5,2,7)
team.league = c("alpha","beta","gamma", "omicron")
team.info = data.frame(names, team.scores, team.league)
names = c("Sally","Tom", "Bill", "Alfonzo")
school.grades = c("A","B","C","B")
school.info = data.frame(names, school.grades)
team.info.and.or.grades <- full_join(team.info, school.info, by = "names")
team.info.and.or.grades
## names team.scores team.league school.grades
## 1 Sally 3 alpha A
## 2 Tom 5 beta B
## 3 Frieda 2 gamma <NA>
## 4 Alfonzo 7 omicron B
## 5 Bill NA <NA> C
#semiunión
team.info.with.grades <- semi_join(team.info, school.info)
## Joining, by = "names"
team.info.with.grades
## names team.scores team.league
## 1 Sally 3 alpha
## 2 Tom 5 beta
## 3 Alfonzo 7 omicron
#unión por la derecha
us.state.areas <- as.data.frame(cbind(state.abb, state.area))
us.state.areas[1:3,]
## state.abb state.area
## 1 AL 51609
## 2 AK 589757
## 3 AZ 113909
us.state.abbreviation.and.name <- as.data.frame(cbind(state.abb,
state.name))
us.state.abbreviation.and.name[1:3,]
## state.abb state.name
## 1 AL Alabama
## 2 AK Alaska
## 3 AZ Arizona
us.state.abbreviation.and.name[1,1] <- "Intentional Mismatch"
us.state.with.abbreviation.and.name.and.area <- right_join(us.state.areas,
us.state.abbreviation.and.name, by = "state.abb")
us.state.with.abbreviation.and.name.and.area[1:3,]
## state.abb state.area state.name
## 1 AK 589757 Alaska
## 2 AZ 113909 Arizona
## 3 AR 53104 Arkansas
#slice
msleep <- ggplot2::msleep
nrow(msleep) #primeras 83 irelas
## [1] 83
msleep.only.first.5 <- slice(msleep, -6:-n())
nrow(msleep.only.first.5)
## [1] 5
msleep.20.rows <- msleep %>%
slice(20:39)
nrow(msleep.20.rows)
## [1] 20
nrow(msleep) - nrow(msleep.20.rows)
## [1] 63
#resumir
library(MASS)
##
## Attaching package: 'MASS'
## The following object is masked from 'package:dplyr':
##
## select
data(gehan)
gehan2 <- gehan
library(tidyverse)
#cuantos pacientes estuvieron en el ensayo médico
gehan2 %>% summarise( kount = n())
## kount
## 1 42
gehan2 %>%
group_by(treat) %>%
summarise(kount = n())
## # A tibble: 2 x 2
## treat kount
## <fct> <int>
## 1 6-MP 21
## 2 control 21
gehan2 %>%
group_by(treat) %>%
summarise(average.remiss.time = mean(time),
median.remiss.time = median(time),
std.dev.remiss.time = sd(time),
median.abs.deviation = mad(time),
IQR.remiss.time = IQR(time))
## # A tibble: 2 x 6
## treat average.remiss.time median.remiss.t~ std.dev.remiss.~ median.abs.devi~
## <fct> <dbl> <int> <dbl> <dbl>
## 1 6-MP 17.1 16 10.0 10.4
## 2 control 8.67 8 6.47 5.93
## # ... with 1 more variable: IQR.remiss.time <dbl>
gehan2 %>%
group_by(treat) %>%
summarise(minimum.remission = min(time),
max.remission = max(time))
## # A tibble: 2 x 3
## treat minimum.remission max.remission
## <fct> <int> <int>
## 1 6-MP 6 35
## 2 control 1 23
#resumir a través de
library(MASS)
subset.survey <- survey[1:10,]
library(dplyr)
head(subset.survey)
## Sex Wr.Hnd NW.Hnd W.Hnd Fold Pulse Clap Exer Smoke Height M.I
## 1 Female 18.5 18.0 Right R on L 92 Left Some Never 173.00 Metric
## 2 Male 19.5 20.5 Left R on L 104 Left None Regul 177.80 Imperial
## 3 Male 18.0 13.3 Right L on R 87 Neither None Occas NA <NA>
## 4 Male 18.8 18.9 Right R on L NA Neither None Never 160.00 Metric
## 5 Male 20.0 20.0 Right Neither 35 Right Some Never 165.00 Metric
## 6 Female 18.0 17.7 Right L on R 64 Right Some Never 172.72 Imperial
## Age
## 1 18.250
## 2 17.583
## 3 16.917
## 4 20.333
## 5 23.667
## 6 21.000
subset.survey %>%
na.omit() %>% #remove any NAs
group_by(Sex) %>%
summarise(across(where(is.numeric), mean,
.names = "mean_{col}")) %>%
head()
## # A tibble: 2 x 6
## Sex mean_Wr.Hnd mean_NW.Hnd mean_Pulse mean_Height mean_Age
## <fct> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 Female 17.8 17.7 76.7 168. 25.0
## 2 Male 19.1 19.2 76.8 174. 20.3
new.sleep <- msleep %>%
group_by(vore, order)
s <- summarise(new.sleep, n())
## `summarise()` has grouped output by 'vore'. You can override using the `.groups` argument.
s
## # A tibble: 32 x 3
## # Groups: vore [5]
## vore order `n()`
## <chr> <chr> <int>
## 1 carni Carnivora 12
## 2 carni Cetacea 3
## 3 carni Cingulata 1
## 4 carni Didelphimorphia 1
## 5 carni Primates 1
## 6 carni Rodentia 1
## 7 herbi Artiodactyla 5
## 8 herbi Diprotodontia 1
## 9 herbi Hyracoidea 2
## 10 herbi Lagomorpha 1
## # ... with 22 more rows
new.sleep.totals <- msleep %>%
group_by(vore, order) %>%
summarise(n())
## `summarise()` has grouped output by 'vore'. You can override using the `.groups` argument.
new.sleep.totals
## # A tibble: 32 x 3
## # Groups: vore [5]
## vore order `n()`
## <chr> <chr> <int>
## 1 carni Carnivora 12
## 2 carni Cetacea 3
## 3 carni Cingulata 1
## 4 carni Didelphimorphia 1
## 5 carni Primates 1
## 6 carni Rodentia 1
## 7 herbi Artiodactyla 5
## 8 herbi Diprotodontia 1
## 9 herbi Hyracoidea 2
## 10 herbi Lagomorpha 1
## # ... with 22 more rows
#Reunir: convertir múltiples columnas en una sola
state <- c("Maryland", "Alaska", "New Jersey")
income <- c(76067,74444,73702)
median.us <- c(61372,61372,61372)
life.expectancy <- c(78.8,78.3,80.3)
teen.birth.rate.2015 <- c(17,29.3,12.1)
teen.birth.rate.2007 <- c(34.3,42.9,24.9)
teen.birth.rate.1991 <- c(54.1, 66, 41.3)
top.3.states <- data.frame(state, income, median.us,
life.expectancy,
teen.birth.rate.2015, teen.birth.rate.2007,
teen.birth.rate.1991)
names(top.3.states) <- c("state", "income", "median.us",
"life.expectancy","2015","2007","1991")
top.3.states
## state income median.us life.expectancy 2015 2007 1991
## 1 Maryland 76067 61372 78.8 17.0 34.3 54.1
## 2 Alaska 74444 61372 78.3 29.3 42.9 66.0
## 3 New Jersey 73702 61372 80.3 12.1 24.9 41.3
new.top.3.states <- top.3.states %>%
gather("2015", "2007", "1991", key = "year", value = "cases")
new.top.3.states
## state income median.us life.expectancy year cases
## 1 Maryland 76067 61372 78.8 2015 17.0
## 2 Alaska 74444 61372 78.3 2015 29.3
## 3 New Jersey 73702 61372 80.3 2015 12.1
## 4 Maryland 76067 61372 78.8 2007 34.3
## 5 Alaska 74444 61372 78.3 2007 42.9
## 6 New Jersey 73702 61372 80.3 2007 24.9
## 7 Maryland 76067 61372 78.8 1991 54.1
## 8 Alaska 74444 61372 78.3 1991 66.0
## 9 New Jersey 73702 61372 80.3 1991 41.3
library(tidyverse)
library(nycflights13)
library(dplyr)
#Extenderse: consolidar muchas irelas en una sola
df_1 <- data_frame(Type = c("TypeA", "TypeA", "TypeB", "TypeB"),
Answer = c("Yes", "No", NA, "No"), n = 1:4)
## Warning: `data_frame()` was deprecated in tibble 1.1.0.
## Please use `tibble()` instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was generated.
df_1 #antes
## # A tibble: 4 x 3
## Type Answer n
## <chr> <chr> <int>
## 1 TypeA Yes 1
## 2 TypeA No 2
## 3 TypeB <NA> 3
## 4 TypeB No 4
df_2 <- df_1 %>%
filter(!is.na(Answer)) %>%
spread(key=Answer, value=n)
df_2 #despues
## # A tibble: 2 x 3
## Type No Yes
## <chr> <int> <int>
## 1 TypeA 2 1
## 2 TypeB 4 NA
#separar: dividir una sola columna en muchas columnas
state <- c("Maryland", "Alaska", "New Jersey")
income <- c(76067,74444,73702)
median.us <- c(61372,61372,61372)
life.expectancy <- c(78.8,78.3,80.3)
teen.birth <- c("17//34.3//54.1", "29.0//42.9//66.0", "12.1//24.9//41.3")
top.3.states <- data.frame(state, income, median.us,
life.expectancy,teen.birth)
top.3.states
## state income median.us life.expectancy teen.birth
## 1 Maryland 76067 61372 78.8 17//34.3//54.1
## 2 Alaska 74444 61372 78.3 29.0//42.9//66.0
## 3 New Jersey 73702 61372 80.3 12.1//24.9//41.3
top.3.states.separated.years <- top.3.states %>%
separate(teen.birth,
into = c("2015", "2007","1991"), sep = "//")
top.3.states.separated.years
## state income median.us life.expectancy 2015 2007 1991
## 1 Maryland 76067 61372 78.8 17 34.3 54.1
## 2 Alaska 74444 61372 78.3 29.0 42.9 66.0
## 3 New Jersey 73702 61372 80.3 12.1 24.9 41.3
#Basic counts
m <- mutate(new.sleep, kount = n()) #nnueva variable, cuenta agregada al extremo derecho
m[1:5,c(1:4,10:12)] #límite de números oara llenar una página
## # A tibble: 5 x 7
## # Groups: vore, order [5]
## name genus vore order brainwt bodywt kount
## <chr> <chr> <chr> <chr> <dbl> <dbl> <int>
## 1 Cheetah Acinonyx carni Carnivora NA 50 12
## 2 Owl monkey Aotus omni Primates 0.0155 0.48 10
## 3 Mountain beaver Aplodontia herbi Rodentia NA 1.35 16
## 4 Greater short-tailed shrew Blarina omni Soricomorp~ 0.00029 0.019 3
## 5 Cow Bos herbi Artiodacty~ 0.423 600 5
#filtrar por recuento de vore que superen los 14
f <- filter(new.sleep, n() > 14)
f[1:5,c(1:4,10:11)]
## # A tibble: 5 x 6
## # Groups: vore, order [1]
## name genus vore order brainwt bodywt
## <chr> <chr> <chr> <chr> <dbl> <dbl>
## 1 Mountain beaver Aplodontia herbi Rodentia NA 1.35
## 2 Guinea pig Cavis herbi Rodentia 0.0055 0.728
## 3 Chinchilla Chinchilla herbi Rodentia 0.0064 0.42
## 4 Western american chipmunk Eutamias herbi Rodentia NA 0.071
## 5 Mongolian gerbil Meriones herbi Rodentia NA 0.053
#Funciones Nth
salary.description <- c("Golden parachute type","Well to do",
"Average","Below average", "bring date seeds instead of flowers")
first(salary.description)
## [1] "Golden parachute type"
#última entrada
last(salary.description)
## [1] "bring date seeds instead of flowers"
#del tercero al fin
nth(salary.description, -3)
## [1] "Average"
#segundo elemento del vector
nth(salary.description,2)
## [1] "Well to do"
#contar valores distintos
library(tidyverse)
a.vector <- c(22,33,44,1,2,3,3,3,4)
original.length <- length(a.vector)
original.length
## [1] 9
#mostrar solo el número de diferentes números
distinct.a.vector <- n_distinct(a.vector)
distinct.a.vector
## [1] 7
test1 <- if_else(original.length == distinct.a.vector, "all values
unique","some duplicate values in vector")
test1
## [1] "some duplicate values in vector"
#ambos vectores contienen valores únicos
b.vector <- c(1,2,3,4,5,6)
length(b.vector)
## [1] 6
distinct.b.vector <- n_distinct(b.vector)
distinct.b.vector #show count (length) of distinct numbers
## [1] 6
test2 <- if_else(length(b.vector) == distinct.b.vector, "all values
unique", "duplicates")
test2
## [1] "all values\nunique"
#na_if
test <- c(100, 0, 999)
x <- 5000/test
x
## [1] 50.000000 Inf 5.005005
x <- 5000/na_if(test,0) # si aparece un 0 durante e test
x
## [1] 50.000000 NA 5.005005
class(x) #use class para mostrar el tipo de variable
## [1] "numeric"
#juntar datos para reemplazar datos perdidos
x <- c(33,4,11,NA,9)
x
## [1] 33 4 11 NA 9
x <- coalesce(x,0)
x
## [1] 33 4 11 0 9
#Ranking via index
y <- c(100,4,12,6,8,3)
rank1 <-row_number(y)
rank1
## [1] 6 2 5 3 4 1
y[rank1[1]] #rank más bajo; en este caso, rank1[1] puntos de # y[6] que es 3 (el más bajo)
## [1] 3
y[rank1[6]] #número más alto del ranking, en este caso el primero # número, 100
## [1] 100
#Rango mínimo
rank2 <- min_rank(y) #en este caso específico (para y), da los mismos resultados como #row_number
rank2
## [1] 6 2 5 3 4 1
#rango denso
rank3 <- dense_rank(y)
rank3
## [1] 6 2 5 3 4 1
#porcentaje del rango
rank4 <- percent_rank(y)
rank4
## [1] 1.0 0.2 0.8 0.4 0.6 0.0
#función de distribución acumulativa
y <- c(100,4,12,6,8,3)
rank5 <- cume_dist(y)
rank5
## [1] 1.0000000 0.3333333 0.8333333 0.5000000 0.6666667 0.1666667
rank6 = ntile(y, 3) #en este caso, escoger 3 cubos
rank6
## [1] 3 1 3 2 2 1
test.vector <- c(2,22,33,44,77,89,99)
quantile(test.vector, prob = seq(0,1,length = 11),type = 5)
## 0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%
## 2.0 6.0 20.0 28.6 36.3 44.0 67.1 81.8 90.0 97.0 99.0
#muestreo
data("ChickWeight")
my.sample <- sample_n(ChickWeight, 5)
my.sample
## weight Time Chick Diet
## 1 153 14 41 4
## 2 58 4 2 1
## 3 141 12 6 1
## 4 108 14 4 1
## 5 162 16 2 1
set.seed(833)
my.sample <- sample_n(ChickWeight, 10, replace = TRUE)
my.sample
## weight Time Chick Diet
## 1 98 8 45 4
## 2 42 0 17 1
## 3 98 8 36 3
## 4 51 2 11 1
## 5 198 20 3 1
## 6 237 21 49 4
## 7 205 16 50 4
## 8 170 16 39 3
## 9 332 18 35 3
## 10 144 14 33 3
my.sample <- sample_n(mtcars, 12, weight = cyl)
my.sample[,1:5]
## mpg cyl disp hp drat
## AMC Javelin 15.2 8 304.0 150 3.15
## Porsche 914-2 26.0 4 120.3 91 4.43
## Merc 280 19.2 6 167.6 123 3.92
## Cadillac Fleetwood 10.4 8 472.0 205 2.93
## Merc 240D 24.4 4 146.7 62 3.69
## Datsun 710 22.8 4 108.0 93 3.85
## Merc 280C 17.8 6 167.6 123 3.92
## Mazda RX4 Wag 21.0 6 160.0 110 3.90
## Merc 450SLC 15.2 8 275.8 180 3.07
## Chrysler Imperial 14.7 8 440.0 230 3.23
## Maserati Bora 15.0 8 301.0 335 3.54
## Valiant 18.1 6 225.0 105 2.76
test1 <- sample_frac(ChickWeight, 0.02)
test1
## weight Time Chick Diet
## 1 48 2 13 1
## 2 62 6 12 1
## 3 197 20 45 4
## 4 234 18 42 4
## 5 58 4 28 2
## 6 163 16 3 1
## 7 103 8 41 4
## 8 103 8 42 4
## 9 120 18 19 1
## 10 48 2 36 3
## 11 80 6 48 4
## 12 137 12 33 3
by_hair_color <- starwars %>% group_by(hair_color)
my.sample <- sample_frac(by_hair_color, .07, replace = TRUE)
my.sample[,1:5]
## # A tibble: 5 x 5
## # Groups: hair_color [3]
## name height mass hair_color skin_color
## <chr> <int> <dbl> <chr> <chr>
## 1 Eeth Koth 171 NA black brown
## 2 Dormé 165 NA brown light
## 3 Sebulba 112 40 none grey, red
## 4 Shaak Ti 178 57 none red, blue, white
## 5 Tion Medon 206 80 none grey
row.kount.only <- ChickWeight %>% tally()
row.kount.only
## n
## 1 578
diet.kount <- ChickWeight %>% count(Diet)
diet.kount
## Diet n
## 1 1 220
## 2 2 120
## 3 3 120
## 4 4 118
#add_count para agrupación de filtrado de grupos
single.species.kount <- starwars %>%
add_count(species) %>%
filter(n == 1)
single.species.kount[,1:6]
## # A tibble: 29 x 6
## name height mass hair_color skin_color eye_color
## <chr> <int> <dbl> <chr> <chr> <chr>
## 1 Greedo 173 74 <NA> green black
## 2 Jabba Desilijic Tiure 175 1358 <NA> green-tan, brown orange
## 3 Yoda 66 17 white green brown
## 4 Bossk 190 113 none green red
## 5 Ackbar 180 83 none brown mottle orange
## 6 Wicket Systri Warrick 88 20 brown brown brown
## 7 Nien Nunb 160 68 none grey black
## 8 Nute Gunray 191 90 none mottled green red
## 9 Watto 137 NA black blue, grey yellow
## 10 Sebulba 112 40 none grey, red orange
## # ... with 19 more rows
#renombrar
mtcars <- rename(mtcars, spam_mpg = mpg)
data(mtcars)
names(mtcars)
## [1] "mpg" "cyl" "disp" "hp" "drat" "wt" "qsec" "vs" "am" "gear"
## [11] "carb"
mtcars <- rename(mtcars, spam_mpg = mpg)
names(mtcars)
## [1] "spam_mpg" "cyl" "disp" "hp" "drat" "wt"
## [7] "qsec" "vs" "am" "gear" "carb"
#case_when
data(starwars)
new.starwars <- starwars %>%
dplyr::select(name, mass, gender, species, height) %>%
mutate(type = case_when(height > 200 | mass > 200 ~ "large",
species == "Droid" ~ "robot", TRUE ~ "other"))
new.starwars
## # A tibble: 87 x 6
## name mass gender species height type
## <chr> <dbl> <chr> <chr> <int> <chr>
## 1 Luke Skywalker 77 masculine Human 172 other
## 2 C-3PO 75 masculine Droid 167 robot
## 3 R2-D2 32 masculine Droid 96 robot
## 4 Darth Vader 136 masculine Human 202 large
## 5 Leia Organa 49 feminine Human 150 other
## 6 Owen Lars 120 masculine Human 178 other
## 7 Beru Whitesun lars 75 feminine Human 165 other
## 8 R5-D4 32 masculine Droid 97 robot
## 9 Biggs Darklighter 84 masculine Human 183 other
## 10 Obi-Wan Kenobi 77 masculine Human 182 other
## # ... with 77 more rows