[R语言] forcats包 因子操作《R for data s

《R for Data Science》第十五章 factors 啃书知识点积累
参考链接：R for Data Science

Creating factors

x1 <- c("Dec", "Apr", "Jan", "Mar")

纯粹创建一个向量记录月份，有两个缺点：

1. 没有很好的办法避免打字错误

x2 <- c("Dec", "Apr", "Jam", "Mar")

2. 排序只能按照首字母顺序

sort(x1)
#> [1] "Apr" "Dec" "Jan" "Mar"

策略：创建factor
首先创建levels

month_levels <- c(
  "Jan", "Feb", "Mar", "Apr", "May", "Jun", 
  "Jul", "Aug", "Sep", "Oct", "Nov", "Dec"
)

然后创建因子

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

• 如果向量中的值不存在于levels中会被静默转换为NA
  可以用readr::parse_factor捕获warning

x2 <- c("Dec", "Apr", "Jam", "Mar")

y2 <- factor(x2, levels = month_levels)
y2
#> [1] Dec  Apr  <NA> Mar 
#> Levels: Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec

y2 <- parse_factor(x2, levels = month_levels)
#> Warning: 1 parsing failure.
#> row col           expected actual
#>   3  -- value in level set    Jam

• 如果不设定levels，会自动创建按照字母表顺序的levels

factor(x1)
#> [1] Dec Apr Jan Mar
#> Levels: Apr Dec Jan Mar

• 按照分类变量第一次出现的顺序设定levels

方法一：创建时用unique

f1 <- factor(x1, levels = unique(x1))
f1
#> [1] Dec Apr Jan Mar
#> Levels: Dec Apr Jan Mar

方法二：创建后用fct_inorder

f2 <- x1 %>% factor() %>% fct_inorder()
f2
#> [1] Dec Apr Jan Mar
#> Levels: Dec Apr Jan Mar

• ·levels·直接查询因子内部水平

levels(f2)
#> [1] "Dec" "Apr" "Jan" "Mar"

General Social Survey

??forcats::gss_cat

• 分类变量映射ggplot2的x轴

会自动转factor并且删除没有任何值的级别，可以用drop=FALSE强迫显示

library(ggplot2)
library(patchwork)

p1 <- ggplot(gss_cat, aes(race)) +
  geom_bar() 

p2 <- ggplot(gss_cat, aes(race)) +
  geom_bar() +
  scale_x_discrete(drop = FALSE)

p1 + p2

- Exercises

gss_cat %>%
  # 过滤掉符合条件的
  filter(!rincome %in% c("Not applicable")) %>%
  # 修改变量中某一亚群的名字
  mutate(rincome = fct_recode(rincome,
                              "Less than $1000" = "Lt $1000"
  )) %>%
  # 区别填充色的预处理
  mutate(rincome_na = rincome %in% c("Refused", "Don't know", "No answer")) %>%
  ggplot(aes(x = rincome, fill = rincome_na)) +
  geom_bar() +
  coord_flip() +
  scale_y_continuous("Number of Respondents", labels = scales::comma) +
  scale_x_discrete("Respondent's Income") +
  # 区别填充
  scale_fill_manual(values = c("FALSE" = "black", "TRUE" = "gray")) +
  theme(legend.position = "None")

Modifying factor order

It’s often useful to change the order of the factor levels in a visualisation.

- 依数值重排序 fct_reorder

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

p1 <- ggplot(relig_summary, aes(tvhours, relig)) + 
  geom_point()

# 默认降序
p2 <- ggplot(relig_summary, aes(tvhours, fct_reorder(relig, tvhours))) +
  geom_point()

# 也可以用EDA提到的reorder
ggplot(relig_summary, aes(tvhours, reorder(relig, tvhours))) +
  geom_point()

p1 + p2

- 自定义重排序 fct_relevel

It takes a factor, f, and then any number of levels that you want to move to the front of the line.

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

p1 <- ggplot(rincome_summary, aes(age, rincome)) + 
  geom_point()

p2 <- ggplot(rincome_summary, aes(age, fct_relevel(rincome, "Not applicable"))) +
  geom_point()

p1 + p2

- 调节图例顺序 fct_reorder2()

fct_reorder2() reorders the factor by the y values associated with the largest x values. This makes the plot easier to read because the line colours line up with the legend.

主要作用是调节图例顺序便于阅读

by_age <- gss_cat %>%
  filter(!is.na(age)) %>%
  count(age, marital) %>%
  group_by(age) %>%
  mutate(prop = n / sum(n))

ggplot(by_age, aes(age, prop, colour = marital)) +
  geom_line(na.rm = TRUE)

ggplot(by_age, aes(age, prop, colour = fct_reorder2(marital, age, prop))) +
  geom_line() +
  labs(colour = "marital")

• 另一个例子：各党派每年比例的变化

p1 <- gss_cat %>%
  mutate(
    partyid =
      fct_collapse(
         partyid,
         Others = c("No answer", "Don't know", "Other party"),
         Republican = c("Strong republican", "Not str republican"),
         Independent = c("Ind,near rep", "Independent", "Ind,near dem"),
         Democrat = c("Not str democrat", "Strong democrat")
      )
  ) %>%
  count(year, partyid) %>% 
  group_by(year) %>%
  mutate(proportions = n / sum(n)) %>% 
  ggplot(aes(year, proportions,
    colour = partyid
  )) +
  geom_point() +
  geom_line(size = 1) 

p2 <- gss_cat %>%
  mutate(
    partyid =
      fct_collapse(
        partyid,
        Others = c("No answer", "Don't know", "Other party"),
        Republican = c("Strong republican", "Not str republican"),
        Independent = c("Ind,near rep", "Independent", "Ind,near dem"),
        Democrat = c("Not str democrat", "Strong democrat")
      )
  ) %>%
  count(year, partyid) %>% 
  group_by(year) %>%
  mutate(proportions = n / sum(n)) %>% 
  ggplot(aes(year, proportions,
             colour = fct_reorder2(partyid, year, proportions)
  )) +
  geom_point() +
  geom_line(size = 1) +
  labs(colour = "Party ID")    

p1 + p2

- 柱形图的简易重排

利用fct_infreq()和fct_rev()

# 调节为顺序递增
p1 <- gss_cat %>%
  mutate(marital = marital %>% fct_infreq()) %>%
  ggplot(aes(marital)) +
  geom_bar()

# 配合fct_rev是顺序递减
p2 <- gss_cat %>%
  mutate(marital = marital %>% fct_infreq() %>% fct_rev()) %>%
  ggplot(aes(marital)) +
  geom_bar()

p1 + p2

• 判断一个dataset哪些变量是factor

str(gss_cat)
# 或者有更简便的办法
keep(gss_cat,is.factor) %>% 
  names(.)
# [1] "marital" "race"    "rincome" "partyid" "relig"   "denom"  

Modifying factor levels

More powerful than changing the orders of the levels is changing their values.

- 修改变量中的值 fct_recode()

gss_cat %>% 
  count(partyid)
#> # A tibble: 10 x 2
#>   partyid                n
#>   <fct>              <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
#> # … with 4 more rows

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 x 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
#> # … with 4 more rows

fct_recode() will leave levels that aren’t explicitly mentioned as is, and will warn you if you accidentally refer to a level that doesn’t exist.

• 可以将多个不同值整合为同一种便于分组

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)

- 同时整合多个值 fct_collapse()

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
#>   <fct>   <int>
#> 1 other     548
#> 2 rep      5346
#> 3 ind      8409
#> 4 dem      7180

• 放一个案例：整合收入数据可视化

gss_cat %>%
  mutate(
    rincome =
      fct_collapse(
        rincome,
        `Unknown` = c("No answer", "Don't know", "Refused", "Not applicable"),
        `Less than $5000` = c("Lt $1000", str_c(
          "$", c("1000", "3000", "4000"),
          " to ", c("2999", "3999", "4999")
        )),
        `$5000 to 10000` = str_c(
          "$", c("5000", "6000", "7000", "8000"),
          " to ", c("5999", "6999", "7999", "9999")
        )
      )
  ) %>%
  ggplot(aes(x = rincome)) +
  geom_bar() +
  coord_flip()

- 自动堆砌值，多值化少值 fct_lump()

整合方式是从最少堆开始逐渐向上吞并

一般用于无序数据的整合

gss_cat %>%
  mutate(relig = fct_lump(relig)) %>%
  count(relig)
#> # A tibble: 2 x 2
#>   relig          n
#>   <fct>      <int>
#> 1 Protestant 10846
#> 2 Other      10637

• 可以用参数n控制最后整合成的堆数

gss_cat %>%
  mutate(relig = fct_lump(relig, n = 10)) %>%
  count(relig, sort = TRUE) %>%
  print(n = Inf)
#> # A tibble: 10 x 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


gss_cat %>%
  mutate(relig = fct_lump(relig, n = 5)) %>%
  count(relig, sort = TRUE)
# # A tibble: 6 x 2
#   relig          n
#   <fct>      <int>
# 1 Protestant 10846
# 2 Catholic    5124
# 3 None        3523
# 4 Other        913
# 5 Christian    689
# 6 Jewish       388