11  因子

R提供了因子这一数据结构（容器），专门用来存放名义型和有序型的分类变量。因子本质上是一个带有水平（level）属性的整数向量，其中 “水平” 是指事前确定可能取值的有限集合。例如，性别有两个水平：男、女。

forcats包是处理因子的强大工具。forcats中的所有函数可参见forcats中的所有函数。

11.1 因子基础

  • 使用forcats::fct()函数将向量转换为因子。

    • fct()是factor()函数的一个简化版和严格版，如果向量中有未包含在水平中的值，则会报错。
    • 使用levels参数指定因子的水平。fct()默认按照因子水平首次出现的顺序进行排序。

  • 使用levels()函数查看或修改因子的水平。

  • readr读取数据时，可以直接使用col_factor()函数将变量读入为因子。

x1 <- c("Dec", "Apr", "Jan", "Mar")
x2 <- c("Dec", "Apr", "Jam", "Mar")
# 设定因子水平
month_levels <- c(
  "Jan", "Feb", "Mar", "Apr",
  "May", "Jun", "Jul", "Aug",
  "Sep", "Oct", "Nov", "Dec"
)

# 按照指定水平创建因子
y1 <- factor(x1, levels = month_levels)
y1
[1] Dec Apr Jan Mar
Levels: Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec
sort(y1) # 按照因子水平排序
[1] Jan Mar Apr Dec
Levels: Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec
# 因子中有未包含在水平中的值
y2 <- factor(x2, levels = month_levels) # factor()不会报错，而使用NA填充未包含的值
y2
[1] Dec  Apr  <NA> Mar 
Levels: Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec
# orcats::fct(x2, levels = month_levels) 会报错，并提示未包含的值

11.2 修改因子顺序

在进行更复杂的数据变化时,建议将fct_**()等操作移出aes(),而是在数据变形时直接进行变化.
# fct_reorder()-按一个变量的顺序重新排列因子
relig_summary <- gss_cat |>
  group_by(relig) |>
  summarise(
    tvhours = mean(tvhours, na.rm = TRUE),
    n = n()
  )

ggplot(relig_summary, aes(x = tvhours, y = fct_reorder(relig, tvhours))) +
  geom_point()

# fct_relevel()-手动调整因子水平的顺序-将任意数量的因子水平移动致指定位置.
rincome_summary <- gss_cat |>
  group_by(rincome) |>
  summarize(
    age = mean(age, na.rm = TRUE),
    n = n()
  )
rincome_summary |>
  mutate(rincome = fct_relevel(rincome, "Not applicable")) |>
  ggplot(aes(x = age, y = rincome)) +
  geom_point()

# fct_reorder2(.f, .x, .y)-根据与变量.x的最大值关联的变量.y值对因子.f进行重新排序.
by_age <- gss_cat |>
  filter(!is.na(age)) |>
  count(age, marital) |>
  group_by(age) |>
  mutate(prop = n / sum(n))
by_age |>
  mutate(marital = fct_reorder2(marital, age, prop)) |>
  ggplot(aes(x = age, y = prop, color = marital)) +
  geom_line(linewidth = 1) +
  scale_color_brewer(palette = "Set1") +
  labs(color = "marital")

# fct_infreq()-按照频数递减的顺序重新排列因子;fct_rev()函数倒序排列因子.
gss_cat |>
  mutate(marital = fct_infreq(marital)) |>
  ggplot(aes(x = marital)) +
  geom_bar()

11.3 修改因子水平

# fct_recode()-手动修改因子水平的编码(名称)，新值在左边，旧值在右边
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)
# A tibble: 10 × 2
   partyid                   n
   <fct>                 <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
# fct_code()-将多个因子分配致同一新级别
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)
# A tibble: 8 × 2
  partyid                   n
  <fct>                 <int>
1 Other                   548
2 Republican, strong     2314
3 Republican, weak       3032
4 Independent, near rep  1791
5 Independent            4119
6 Independent, near dem  2499
7 Democrat, weak         3690
8 Democrat, strong       3490
# fct_collapse()-将多个因子合并为一个水平-折叠大量因子水平
# 比fct_recode()更清晰易读
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 × 2
  partyid     n
  <fct>   <int>
1 other     548
2 rep      5346
3 ind      8409
4 dem      7180
# fct_lump()系列-将少于某一值的水平折叠
gss_cat |>
  # 保留前n个最常见的分类，其余的合并为"Other"类
  mutate(relig = fct_lump(relig, 10)) |>
  count(relig, sort = TRUE)
# A tibble: 10 × 2
   relig                       n
   <fct>                   <int>
 1 Protestant              10846
 2 Catholic                 5124
 3 None                     3523
 4 Christian                 689
 5 Other                     458
 6 Jewish                    388
 7 Buddhism                  147
 8 Inter-nondenominational   109
 9 Moslem/islam              104
10 Orthodox-christian         95

11.4 有序因子

有序因子是一类特殊的因子:

  • 使用 ordered() 函数创建，表示因子水平之间存在严格的顺序关系，但并不根据具体数值进行界定。
  • 有序因子的顺序可以通过 < 符号进行识别。