Factors

Jeff Stevens

2025-03-12

Introduction

The problem

What is needed to create data2 from data1?

data1

# A tibble: 8 × 2
  species      n
  <chr>    <int>
1 Droid        6
2 Gungan       3
3 Human       35
4 Kaminoan     2
5 Mirialan     2
6 Twi'lek      2
7 Wookiee      2
8 Zabrak       2

data2

# A tibble: 4 × 2
  species     n
  <fct>   <int>
1 Human      35
2 Other      10
3 Android     6
4 Gungan      3

Factors

Categorical variables represented by augmented integers

(x1 <- c("Apr", "Jun", "Oct", "Jan"))

[1] "Apr" "Jun" "Oct" "Jan"

(y1 <- factor(x1))

[1] Apr Jun Oct Jan
Levels: Apr Jan Jun Oct

class(y1)

[1] "factor"

typeof(y1)

[1] "integer"

Mental model

View/set factor levels

levels()

y1

[1] Apr Jun Oct Jan
Levels: Apr Jan Jun Oct

levels(y1)

[1] "Apr" "Jan" "Jun" "Oct"

(y2 <- factor(x1, levels = month.abb))

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

levels(y2)

 [1] "Jan" "Feb" "Mar" "Apr" "May" "Jun" "Jul" "Aug" "Sep" "Oct" "Nov" "Dec"

Label factors

labels argument

(y3 <- factor(y1, labels = c("April", "January", "June", "October")))

[1] April   June    October January
Levels: April January June October

Note you have to label them in the order they appear as levels.

Factors with {forcats}

library(forcats)

Data set

gss_cat

# A tibble: 21,483 × 9
    year marital         age race  rincome        partyid    relig denom tvhours
   <int> <fct>         <int> <fct> <fct>          <fct>      <fct> <fct>   <int>
 1  2000 Never married    26 White $8000 to 9999  Ind,near … Prot… Sout…      12
 2  2000 Divorced         48 White $8000 to 9999  Not str r… Prot… Bapt…      NA
 3  2000 Widowed          67 White Not applicable Independe… Prot… No d…       2
 4  2000 Never married    39 White Not applicable Ind,near … Orth… Not …       4
 5  2000 Divorced         25 White Not applicable Not str d… None  Not …       1
 6  2000 Married          25 White $20000 - 24999 Strong de… Prot… Sout…      NA
 7  2000 Never married    36 White $25000 or more Not str r… Chri… Not …       3
 8  2000 Divorced         44 White $7000 to 7999  Ind,near … Prot… Luth…      NA
 9  2000 Married          44 White $25000 or more Not str d… Prot… Other       0
10  2000 Married          47 White $25000 or more Strong re… Prot… Sout…       3
# ℹ 21,473 more rows

Reordering factor levels

Check level order

y1

[1] Apr Jun Oct Jan
Levels: Apr Jan Jun Oct

levels(y1)

[1] "Apr" "Jan" "Jun" "Oct"

By default, level elements are sorted alphabetically.

Check level order with pipes

marital <- gss_cat |>
  pull(marital)
marital |> levels()

[1] "No answer"     "Never married" "Separated"     "Divorced"     
[5] "Widowed"       "Married"      

Here, order was determined already.

Reordering levels

Why reorder levels?

Reordering levels

In reverse order of factor levels with fct_rev()

levels(marital)

[1] "No answer"     "Never married" "Separated"     "Divorced"     
[5] "Widowed"       "Married"      

marital |> fct_rev() |>
  levels()

[1] "Married"       "Widowed"       "Divorced"      "Separated"    
[5] "Never married" "No answer"    

Reordering levels

In the order based on number of observations of each level with fct_infreq()

gss_cat |>
  count(marital, sort = TRUE)

# A tibble: 6 × 2
  marital           n
  <fct>         <int>
1 Married       10117
2 Never married  5416
3 Divorced       3383
4 Widowed        1807
5 Separated       743
6 No answer        17

marital |> fct_infreq() |>
  levels()

[1] "Married"       "Never married" "Divorced"      "Widowed"      
[5] "Separated"     "No answer"    

Order factors by another variable

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

# A tibble: 15 × 3
   relig                   tvhours     n
   <fct>                     <dbl> <int>
 1 No answer                  2.72    93
 2 Don't know                 4.62    15
 3 Inter-nondenominational    2.87   109
 4 Native american            3.46    23
 5 Christian                  2.79   689
 6 Orthodox-christian         2.42    95
 7 Moslem/islam               2.44   104
 8 Other eastern              1.67    32
 9 Hinduism                   1.89    71
10 Buddhism                   2.38   147
11 Other                      2.73   224
12 None                       2.71  3523
13 Jewish                     2.52   388
14 Catholic                   2.96  5124
15 Protestant                 3.15 10846

Order factors by another variable

Order factors by another variable

fct_reorder()

mutate(relig = fct_reorder(relig, tvhours))

Manually reorder factor levels

fct_relevel()

Manually reorder factor levels

fct_relevel()

relig_summary_releveled <- relig_summary |>
  mutate(relig = fct_relevel(relig, c("None", "Other"), after = 2))
levels(relig_summary_releveled$relig)

 [1] "No answer"               "Don't know"             
 [3] "None"                    "Other"                  
 [5] "Inter-nondenominational" "Native american"        
 [7] "Christian"               "Orthodox-christian"     
 [9] "Moslem/islam"            "Other eastern"          
[11] "Hinduism"                "Buddhism"               
[13] "Jewish"                  "Catholic"               
[15] "Protestant"              "Not applicable"         

Manually reorder factor levels

fct_relevel()

Recode factors

Recode factor levels

fct_recode()

gss_cat |>
  count(partyid)

# A tibble: 10 × 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
 7 Independent         4119
 8 Ind,near dem        2499
 9 Not str democrat    3690
10 Strong democrat     3490

Recode factor levels

fct_recode()

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

Collapse multiple levels

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

Combine factor levels

Based on number of groups: fct_lump_n()

gss_cat |>
  count(relig, sort = TRUE)

# A tibble: 15 × 2
   relig                       n
   <fct>                   <int>
 1 Protestant              10846
 2 Catholic                 5124
 3 None                     3523
 4 Christian                 689
 5 Jewish                    388
 6 Other                     224
 7 Buddhism                  147
 8 Inter-nondenominational   109
 9 Moslem/islam              104
10 Orthodox-christian         95
11 No answer                  93
12 Hinduism                   71
13 Other eastern              32
14 Native american            23
15 Don't know                 15

gss_cat |>
  mutate(relig = fct_lump_n(relig, n = 5)) |>
  count(relig, sort = TRUE)

# A tibble: 6 × 2
  relig          n
  <fct>      <int>
1 Protestant 10846
2 Catholic    5124
3 None        3523
4 Other        913
5 Christian    689
6 Jewish       388

Combine factor levels

Based on proportion of total: fct_lump_prop()

gss_cat |>
  mutate(relig = fct_lump_prop(relig, prop = 0.1, 
                               other_level = "Something else")) |>
  count(relig, sort = TRUE)

# A tibble: 4 × 2
  relig              n
  <fct>          <int>
1 Protestant     10846
2 Catholic        5124
3 None            3523
4 Something else  1990

Combine factor levels

Based on minimum number: fct_lump_min()

gss_cat |>
  mutate(relig = fct_lump_min(relig, min = 200)) |>
  count(relig, sort = TRUE)

# A tibble: 6 × 2
  relig          n
  <fct>      <int>
1 Protestant 10846
2 Catholic    5124
3 None        3523
4 Other        913
5 Christian    689
6 Jewish       388

Solving the problem

library(tidyverse)
nrows <- 12
set.seed(100)
data1 <- starwars |> 
  count(species) |> 
  filter(n > 1) |> 
  drop_na()

Solving the problem

What code generates data2 from data1?

data1

# A tibble: 8 × 2
  species      n
  <chr>    <int>
1 Droid        6
2 Gungan       3
3 Human       35
4 Kaminoan     2
5 Mirialan     2
6 Twi'lek      2
7 Wookiee      2
8 Zabrak       2

data2

# A tibble: 4 × 2
  species     n
  <fct>   <int>
1 Human      35
2 Other      10
3 Android     6
4 Gungan      3

Let’s code!

Factors