Como muchos de los packages del tidyverse, la idea es simplificar y unificar las interfases.

Sirven para modelar variables categóricas.

x1 <- c("Dec", "Abr", "Ene", "Mar")
x1

## [1] "Dec" "Abr" "Ene" "Mar"

Orden:

sort(x1)

## [1] "Abr" "Dec" "Ene" "Mar"

Errores de tipeo:

x2 <- c("Dec", "Abr", "Ene", "Marzo")

Evitan estos problemas.

niveles <- c("Ene", "Feb", "Mar", "Abr", 
             "May", "Jun", "Jul", "Ag",
            "Set", "Oct", "Nov", "Dec")

x1

## [1] "Dec" "Abr" "Ene" "Mar"

meses_factor <- factor(x1, levels=niveles)
sort(meses_factor)

## [1] Ene Mar Abr Dec
## Levels: Ene Feb Mar Abr May Jun Jul Ag Set Oct Nov Dec

Si hay un error:

x2

## [1] "Dec"   "Abr"   "Ene"   "Marzo"

meses_factor_2 <- factor(x2, levels=niveles)
meses_factor_2

## [1] Dec  Abr  Ene  <NA>
## Levels: Ene Feb Mar Abr May Jun Jul Ag Set Oct Nov Dec

library(dplyr)
library(forcats)

head(gss_cat)

## # A tibble: 6 x 9
##    year marital         age race   rincome        party… relig denom tvho…
##   <int> <fctr>        <int> <fctr> <fctr>         <fctr> <fct> <fct> <int>
## 1  2000 Never married    26 White  $8000 to 9999  Ind,n… Prot… Sout…    12
## 2  2000 Divorced         48 White  $8000 to 9999  Not s… Prot… Bapt…    NA
## 3  2000 Widowed          67 White  Not applicable Indep… Prot… No d…     2
## 4  2000 Never married    39 White  Not applicable Ind,n… Orth… Not …     4
## 5  2000 Divorced         25 White  Not applicable Not s… None  Not …     1
## 6  2000 Married          25 White  $20000 - 24999 Stron… Prot… Sout…    NA

Vamos a usar ggplot para graficar los datos, pero podrían ser tablas.

library(ggplot2)
ggplot(gss_cat, aes(x=race)) + geom_bar()

ggplot(gss_cat, aes(x=race)) + geom_bar() + 
                scale_x_discrete(drop=FALSE)

Explorar la distribución de rincome:

ggplot(gss_cat, aes(x=rincome)) + geom_bar() + 
       theme(axis.text.x=element_text(angle=90))

relig <- gss_cat %>% 
         group_by(relig) %>%
         summarize(age=mean(age, na.rm=TRUE),
                   tvhours=mean(tvhours, na.rm=TRUE),
                   n=n())

ggplot(relig, aes(tvhours, relig)) + geom_point()

Como son un factor, puedo usar fct_reorder, esta función lleva: un factor y un vector numérico. Devuelve el mismo factor pero con los niveles reordenados.

relig <- relig %>% 
         mutate(relig_factor = fct_reorder(relig, tvhours))

ggplot(relig, aes(tvhours, relig_factor)) + geom_point()

Tangente, en el libro está así:

ggplot(relig, aes(tvhours, fct_reorder(relig, tvhours))) + 
       geom_point()

rincome <- gss_cat %>%
           group_by(rincome) %>%
           summarize(age = mean(age, na.rm=TRUE),
                     tvhours = mean(tvhours, na.rm=TRUE),
                     n=n())

ggplot(rincome, aes(tvhours, rincome)) + 
       geom_point()  

No tiene sentido reordenarlos por otra variable como en el caso anterior. Sin embargo, podemos querer mandar algunos para adelante para resaltarlos:

ggplot(rincome, aes(tvhours, relevel(rincome, "Not applicable"))) + 
       geom_point()

gss_cat %>%
        mutate(marital = marital %>% fct_infreq() ) %>%

ggplot(aes(marital)) + geom_bar()

fct_rev lo revierte:

gss_cat %>%
mutate(marital = marital %>% fct_infreq() %>% fct_rev()) %>%

ggplot(aes(marital)) + geom_bar()

gss_cat %>% count(partyid)

## # A tibble: 10 x 2
##    partyid                n
##    <fctr>             <int>
##  1 No answer            154
##  2 Don't know             1
##  3 Other party          393
##  4 Strong republican   2314
##  5 Not str republican  3032
##  6 Ind,near rep        1791
##  7 Independent         4119
##  8 Ind,near dem        2499
##  9 Not str democrat    3690
## 10 Strong democrat     3490

gss_cat %>% 
  mutate(partyid = fct_recode(partyid,
         "Republican, strong" = "Strong republican",
         "Republican, weak" = "Not str republican",
         "Independent, near rep" = "Ind,near rep",
         "Independent, near dem" = "Ind,near dem",
         "Democrat, weak" = "Not str democrat",
         "Democrat, strong" = "Strong democrat")) %>% 
  count(partyid) 

count(partyid) 

## # A tibble: 10 x 2
##    partyid                   n
##    <fctr>                <int>
##  1 No answer               154
##  2 Don't know                1
##  3 Other party             393
##  4 Republican, strong     2314
##  5 Republican, weak       3032
##  6 Independent, near rep  1791
##  7 Independent            4119
##  8 Independent, near dem  2499
##  9 Democrat, weak         3690
## 10 Democrat, strong       3490

gss_cat %>%
  mutate(partyid = fct_collapse(partyid,
         other = c("No answer", "Don't know", "Other party"),
         rep = c("Strong republican", "Not str republican"),
         ind = c("Ind,near rep", "Independent", "Ind,near dem"),
         dem = c("Not str democrat", "Strong democrat"))) %>%
  count(partyid)

## # A tibble: 4 x 2
##   partyid     n
##   <fctr>  <int>
## 1 other     548
## 2 rep      5346
## 3 ind      8409
## 4 dem      7180

Colapsa los factores chicos en un "otros".

gss_cat %>%
  mutate(relig = fct_lump(relig, n = 10, other_level="otros")) %>%
  count(relig, sort = TRUE)

count(relig, sort = TRUE)

## # A tibble: 11 x 2
##    relig                       n
##    <fctr>                  <int>
##  1 Protestant              10846
##  2 Catholic                 5124
##  3 None                     3523
##  4 Christian                 689
##  5 Jewish                    388
##  6 otros                     234
##  7 Other                     224
##  8 Buddhism                  147
##  9 Inter-nondenominational   109
## 10 Moslem/islam              104
## 11 Orthodox-christian         95

1. Calcular cuántas empresas hay en cada zona franca y hacer un dot plot.

2. Calcular el VBP agregado por Zona, quedarse solo con las "principales". Lo mismo con empleados.