Factor

Creating a factor

Fix the order and spelling of a string:

x1 <- c("Dec", "Apr", "Jan", "Mar")
month_levels <- c(
  "Jan", "Feb", "Mar", "Apr", "May", "Jun", 
  "Jul", "Aug", "Sep", "Oct", "Nov", "Dec"
)
y1 <- factor(x1, levels = month_levels)
sort(y1)

#[1] Jan Mar Apr Dec
#Levels: Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec

# fix the order according to the given one
f1 <- factor(x1, levels = unique(x1))

#to see the level of a factor
levels(gss_cat$race)

#draw a bar plot
ggplot(gss_cat, aes(race)) +
  geom_bar() +
  scale_x_discrete(drop = F) #force the level that has no value to display

Reorder

##fct_reorder()
ggplot(relig_summary) +
  geom_point(aes(tvhours,fct_reorder(relig, tvhours)))
#fct_reorder() reorders the `relig` according to `tvhours`

##fct_relevel()
#set the reference level(put a level to the front)
fct_relevel(rincome, "Not applicable")
#it can be seen that "Not applicable" is pulled to the front using "level()" as well as in the plot

##fct_reorder2()
by_age <- 
  gss_cat %>%
  filter(!is.na(age)) %>%
  group_by(age, marital) %>%
  count() %>%
  group_by(age) %>%
  mutate(prop = n / sum(n))
ggplot(by_age, aes(age, prop, colour = fct_reorder2(marital, age, prop))) +
  geom_line(na.rm = T) +
  labs(colour = "Marital Status")
#fct_reorder2() reorders the values from the largest "prop" of every "age" of "marital" to the smallest,putting the biggest on the top and smallest on the bottom

##fct_infreq() & fct_rev()
#descending order
gss_cat %>%
  mutate(marital = marital %>% fct_infreq()) %>%
  ggplot(aes(marital)) +
    geom_bar()
#ascending order
gss_cat %>%
  mutate(marital = marital %>% fct_infreq() %>% fct_rev()) %>%
  ggplot(aes(marital)) +
    geom_bar()

Change the value of levels

Replace the right with the left,and count the number of each group:

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",
    "Other"                 = "No answer",
    "Other"                 = "Don't know",
    "Other"                 = "Other party"
  )) %>%
  count(partyid)

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)

gss_cat %>%
  mutate(relig = fct_lump(relig, n = 10)) %>% #lump the observations into ten rows
  count(relig, sort = TRUE) %>% #`sort = T` put the levels in descending order
  print(n = Inf) #print all the rows(but here it seems useless)