Chapter 15

Introduction

Creating factors

General Social Survery

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

Modifying factor levels

Unordered factor levels

# Transform data: Calculate average tv hours by religion
tvhours_by_relig <- gss_cat %>% 
  group_by(relig) %>%
  summarise(
    avg_tvhours = mean(tvhours, na.rm = TRUE)
  )

tvhours_by_relig
## # A tibble: 15 × 2
##    relig                   avg_tvhours
##    <fct>                         <dbl>
##  1 No answer                      2.72
##  2 Don't know                     4.62
##  3 Inter-nondenominational        2.87
##  4 Native american                3.46
##  5 Christian                      2.79
##  6 Orthodox-christian             2.42
##  7 Moslem/islam                   2.44
##  8 Other eastern                  1.67
##  9 Hinduism                       1.89
## 10 Buddhism                       2.38
## 11 Other                          2.73
## 12 None                           2.71
## 13 Jewish                         2.52
## 14 Catholic                       2.96
## 15 Protestant                     3.15
# Plot
tvhours_by_relig %>%
  ggplot(aes(x = avg_tvhours, y = relig)) + 
  geom_point()

Ordered factor levels

tvhours_by_relig %>%
  ggplot(aes(x = avg_tvhours, y = fct_reorder(.f = relig, .x = avg_tvhours))) + 
  geom_point() +
  # Labeling 
  labs(y = NULL, x = "Mean Daily Hours Watching Tv")

Moving a single level to the front

tvhours_by_relig %>%
  ggplot(aes(x = avg_tvhours, 
             y = fct_reorder(.f = relig, .x = avg_tvhours) %>%
                 fct_relevel("Don't know")
             )) + 
  geom_point() +
  # Labeling 
  labs(y = NULL, x = "Mean Daily Hours Watching Tv")

Modifying factor levels

gss_cat %>% distinct(race)
## # A tibble: 3 × 1
##   race 
##   <fct>
## 1 White
## 2 Black
## 3 Other
gss_cat %>% 
  
  # Rename levels
  mutate(race_rev = fct_recode(race, "African American" = "Black")) %>%
  select(race, race_rev) %>%
  filter(race == "Black")
## # A tibble: 3,129 × 2
##    race  race_rev        
##    <fct> <fct>           
##  1 Black African American
##  2 Black African American
##  3 Black African American
##  4 Black African American
##  5 Black African American
##  6 Black African American
##  7 Black African American
##  8 Black African American
##  9 Black African American
## 10 Black African American
## # ℹ 3,119 more rows
# Collapse multiple levels into one
gss_cat %>%
  mutate(race_col = fct_collapse(race, "Minority" = c("Black", "Other"))) %>%
  select(race, race_col) %>%
  filter(race != "White")
## # A tibble: 5,088 × 2
##    race  race_col
##    <fct> <fct>   
##  1 Black Minority
##  2 Black Minority
##  3 Black Minority
##  4 Other Minority
##  5 Black Minority
##  6 Other Minority
##  7 Black Minority
##  8 Other Minority
##  9 Black Minority
## 10 Black Minority
## # ℹ 5,078 more rows
# Lump small levels into other levels
gss_cat %>% count(race)
## # A tibble: 3 × 2
##   race      n
##   <fct> <int>
## 1 Other  1959
## 2 Black  3129
## 3 White 16395
gss_cat %>% mutate(race_lump = fct_lump(race)) %>% distinct(race_lump)
## # A tibble: 2 × 1
##   race_lump
##   <fct>    
## 1 White    
## 2 Other

Chapter 16

Creating date/times

# From strings
"2026-03-24" %>% ymd()
## [1] "2026-03-24"
# From numbers
20260324 %>% ymd()
## [1] "2026-03-24"
20260324105530 %>% ymd_hms()
## [1] "2026-03-24 10:55:30 UTC"

From individual components

flights %>% select(year:day, hour, minute) %>%
  mutate(departure = 
           make_datetime(year = year, month = month, day = day, hour = hour, min = minute)
         )
## # A tibble: 336,776 × 6
##     year month   day  hour minute departure          
##    <int> <int> <int> <dbl>  <dbl> <dttm>             
##  1  2013     1     1     5     15 2013-01-01 05:15:00
##  2  2013     1     1     5     29 2013-01-01 05:29:00
##  3  2013     1     1     5     40 2013-01-01 05:40:00
##  4  2013     1     1     5     45 2013-01-01 05:45:00
##  5  2013     1     1     6      0 2013-01-01 06:00:00
##  6  2013     1     1     5     58 2013-01-01 05:58:00
##  7  2013     1     1     6      0 2013-01-01 06:00:00
##  8  2013     1     1     6      0 2013-01-01 06:00:00
##  9  2013     1     1     6      0 2013-01-01 06:00:00
## 10  2013     1     1     6      0 2013-01-01 06:00:00
## # ℹ 336,766 more rows

From other types

# From date to date-time
today() %>% as_datetime()
## [1] "2026-03-24 UTC"
# From date-time to date
now() %>% as_date()
## [1] "2026-03-24"

Date-time components

Getting components

date_time <- ymd_hms(now())
date_time
## [1] "2026-03-24 11:29:24 UTC"
year(date_time)
## [1] 2026
month(date_time, label = TRUE, abbr = FALSE)
## [1] March
## 12 Levels: January < February < March < April < May < June < ... < December
yday(date_time)
## [1] 83
mday(date_time)
## [1] 24
wday(date_time, label = TRUE, abbr = FALSE)
## [1] Tuesday
## 7 Levels: Sunday < Monday < Tuesday < Wednesday < Thursday < ... < Saturday
# Creates flights dt
make_datetime_100 <- function(year, month, day, time) {
  make_datetime(year, month, day, time %/% 100, time %% 100)
}

flights_dt <- flights %>% 
  filter(!is.na(dep_time), !is.na(arr_time)) %>% 
  mutate(
    dep_time = make_datetime_100(year, month, day, dep_time),
    arr_time = make_datetime_100(year, month, day, arr_time),
    sched_dep_time = make_datetime_100(year, month, day, sched_dep_time),
    sched_arr_time = make_datetime_100(year, month, day, sched_arr_time)
  ) %>% 
  select(origin, dest, ends_with("delay"), ends_with("time"))
flights_dt %>%
  
  transmute(wday = wday(dep_time, label = TRUE)) %>%
  ggplot(aes(wday)) +
  geom_bar()

Rounding

# Floor date for rounding down
flights_dt %>%
  
  mutate(week = floor_date(dep_time, "month")) %>%
  select(dep_time, week) %>%
  sample_n(10)
## # A tibble: 10 × 2
##    dep_time            week               
##    <dttm>              <dttm>             
##  1 2013-07-20 13:35:00 2013-07-01 00:00:00
##  2 2013-08-27 19:39:00 2013-08-01 00:00:00
##  3 2013-02-17 17:22:00 2013-02-01 00:00:00
##  4 2013-03-14 16:03:00 2013-03-01 00:00:00
##  5 2013-04-15 09:58:00 2013-04-01 00:00:00
##  6 2013-08-15 14:55:00 2013-08-01 00:00:00
##  7 2013-05-31 13:41:00 2013-05-01 00:00:00
##  8 2013-09-17 18:29:00 2013-09-01 00:00:00
##  9 2013-08-10 23:59:00 2013-08-01 00:00:00
## 10 2013-09-04 15:59:00 2013-09-01 00:00:00
# Ceiling date for rounding up
flights_dt %>%
  
  mutate(week = ceiling_date(dep_time, "month")) %>%
  select(dep_time, week) %>%
  sample_n(10)
## # A tibble: 10 × 2
##    dep_time            week               
##    <dttm>              <dttm>             
##  1 2013-07-14 18:47:00 2013-08-01 00:00:00
##  2 2013-09-28 11:44:00 2013-10-01 00:00:00
##  3 2013-08-29 18:08:00 2013-09-01 00:00:00
##  4 2013-01-29 06:58:00 2013-02-01 00:00:00
##  5 2013-06-23 18:31:00 2013-07-01 00:00:00
##  6 2013-05-18 16:18:00 2013-06-01 00:00:00
##  7 2013-01-11 20:03:00 2013-02-01 00:00:00
##  8 2013-01-08 07:35:00 2013-02-01 00:00:00
##  9 2013-03-27 20:19:00 2013-04-01 00:00:00
## 10 2013-04-21 15:45:00 2013-05-01 00:00:00

Setting components

flights_dt %>% 
  mutate(dep_hour = update(dep_time, yday = 1)) %>%
  select(dep_time, dep_hour) %>%
  sample_n(10)
## # A tibble: 10 × 2
##    dep_time            dep_hour           
##    <dttm>              <dttm>             
##  1 2013-03-05 19:46:00 2013-01-01 19:46:00
##  2 2013-05-21 18:18:00 2013-01-01 18:18:00
##  3 2013-04-09 06:26:00 2013-01-01 06:26:00
##  4 2013-09-10 09:20:00 2013-01-01 09:20:00
##  5 2013-11-21 06:04:00 2013-01-01 06:04:00
##  6 2013-02-15 06:57:00 2013-01-01 06:57:00
##  7 2013-06-12 06:24:00 2013-01-01 06:24:00
##  8 2013-09-12 21:26:00 2013-01-01 21:26:00
##  9 2013-03-01 16:54:00 2013-01-01 16:54:00
## 10 2013-08-29 17:51:00 2013-01-01 17:51:00

Time spans