Ch15 Factors

Creating Factors

x1 <- c("Dec", "Apr", "Jan", "Mar")
x2 <- c("Dec", "Apr", "Jam", "Mar")
sort(x1)
## [1] "Apr" "Dec" "Jan" "Mar"
month_levels <- c(
  "Jan", "Feb", "Mar", "Apr", "May", "Jun", 
  "Jul", "Aug", "Sep", "Oct", "Nov", "Dec"
) 

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)
## [1] Jan Mar Apr Dec
## Levels: Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec
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
factor(x1) 
## [1] Dec Apr Jan Mar
## Levels: Apr Dec Jan Mar
f1 <- factor(x1, levels = unique(x1))
f1
## [1] Dec Apr Jan Mar
## Levels: Dec Apr Jan Mar
f2 <- x1 %>% factor() %>% fct_inorder()
f2
## [1] Dec Apr Jan Mar
## Levels: Dec Apr Jan Mar
levels(f2) 
## [1] "Dec" "Apr" "Jan" "Mar"

General Social Survey

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 order

Unordered factor levels

# Transform data: calculate avg. 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")
## <ggplot2::labels> List of 2
##  $ y: NULL
##  $ x: chr "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 vector levels

gss_cat %>% distinct(race)
## # A tibble: 3 × 1
##   race 
##   <fct>
## 1 White
## 2 Black
## 3 Other
# Recode
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

Ch16 Dates and times

Creating date/times

From strings

# From strings
"2026/04/07" %>% ymd()
## [1] "2026-04-07"
# From numbers
20260426 %>% ymd()
## [1] "2026-04-26"
"2026-04-26 4-37-30" %>% ymd_hms()
## [1] "2026-04-26 04:37:30 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] "2026-04-07 UTC"
# From date-time to date
now() %>% as_date()
## [1] "2026-04-07"

Date-time components

Getting components

date_time <- ymd_hms("2026-04-26 18-18-18")
date_time
## [1] "2026-04-26 18:18:18 UTC"
year(date_time)
## [1] 2026
month(date_time, label = TRUE, abbr = FALSE)
## [1] April
## 12 Levels: January < February < March < April < May < June < ... < December
day(date_time)
## [1] 26
mday(date_time)
## [1] 26
wday(date_time, label = TRUE, abbr = FALSE)
## [1] Sunday
## 7 Levels: Sunday < Monday < Tuesday < Wednesday < Thursday < ... < Saturday
# Create 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
## # A tibble: 328,063 × 9
##    origin dest  dep_delay arr_delay dep_time            sched_dep_time     
##    <chr>  <chr>     <dbl>     <dbl> <dttm>              <dttm>             
##  1 EWR    IAH           2        11 2013-01-01 05:17:00 2013-01-01 05:15:00
##  2 LGA    IAH           4        20 2013-01-01 05:33:00 2013-01-01 05:29:00
##  3 JFK    MIA           2        33 2013-01-01 05:42:00 2013-01-01 05:40:00
##  4 JFK    BQN          -1       -18 2013-01-01 05:44:00 2013-01-01 05:45:00
##  5 LGA    ATL          -6       -25 2013-01-01 05:54:00 2013-01-01 06:00:00
##  6 EWR    ORD          -4        12 2013-01-01 05:54:00 2013-01-01 05:58:00
##  7 EWR    FLL          -5        19 2013-01-01 05:55:00 2013-01-01 06:00:00
##  8 LGA    IAD          -3       -14 2013-01-01 05:57:00 2013-01-01 06:00:00
##  9 JFK    MCO          -3        -8 2013-01-01 05:57:00 2013-01-01 06:00:00
## 10 LGA    ORD          -2         8 2013-01-01 05:58:00 2013-01-01 06:00:00
## # ℹ 328,053 more rows
## # ℹ 3 more variables: arr_time <dttm>, sched_arr_time <dttm>, air_time <dbl>
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 2013-08-30 15:40:00 2013-08-01 00:00:00
##  2 2013-04-20 12:00:00 2013-04-01 00:00:00
##  3 2013-11-24 19:00:00 2013-11-01 00:00:00
##  4 2013-01-26 08:31:00 2013-01-01 00:00:00
##  5 2013-12-27 08:21:00 2013-12-01 00:00:00
##  6 2013-06-02 16:47:00 2013-06-01 00:00:00
##  7 2013-07-23 06:28:00 2013-07-01 00:00:00
##  8 2013-08-26 16:30:00 2013-08-01 00:00:00
##  9 2013-12-20 22:25:00 2013-12-01 00:00:00
## 10 2013-09-14 08:15:00 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 2013-10-03 17:00:00 2013-11-01 00:00:00
##  2 2013-10-22 14:52:00 2013-11-01 00:00:00
##  3 2013-11-26 17:04:00 2013-12-01 00:00:00
##  4 2013-08-05 08:12:00 2013-09-01 00:00:00
##  5 2013-09-06 06:49:00 2013-10-01 00:00:00
##  6 2013-09-20 12:46:00 2013-10-01 00:00:00
##  7 2013-09-22 06:02:00 2013-10-01 00:00:00
##  8 2013-12-02 12:39:00 2014-01-01 00:00:00
##  9 2013-04-02 20:27:00 2013-05-01 00:00:00
## 10 2013-12-11 18:54:00 2014-01-01 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 2013-06-23 06:37:00 2013-01-01 06:37:00
##  2 2013-06-12 07:59:00 2013-01-01 07:59:00
##  3 2013-05-25 05:50:00 2013-01-01 05:50:00
##  4 2013-07-14 18:58:00 2013-01-01 18:58:00
##  5 2013-07-06 06:20:00 2013-01-01 06:20:00
##  6 2013-07-29 11:55:00 2013-01-01 11:55:00
##  7 2013-02-19 08:29:00 2013-01-01 08:29:00
##  8 2013-04-12 14:07:00 2013-01-01 14:07:00
##  9 2013-04-18 20:33:00 2013-01-01 20:33:00
## 10 2013-11-21 06:32:00 2013-01-01 06:32:00

Time spans

Durations
#### Subtracting two dates
h_age <- today() - ymd(19791014)
h_age
## Time difference of 16977 days
#### Constructor functions
dseconds(15)
## [1] "15s"
dminutes(10)
## [1] "600s (~10 minutes)"
dhours(c(12, 24))
## [1] "43200s (~12 hours)" "86400s (~1 days)"
ddays(0:5)
## [1] "0s"                "86400s (~1 days)"  "172800s (~2 days)"
## [4] "259200s (~3 days)" "345600s (~4 days)" "432000s (~5 days)"
dweeks(3)
## [1] "1814400s (~3 weeks)"
dyears(1)
## [1] "31557600s (~1 years)"
#### Adding and multiplying
2 * dyears(1)
## [1] "63115200s (~2 years)"
dyears(1) + dweeks(12) + dhours(15)
## [1] "38869200s (~1.23 years)"
#### Adding and subtracting
tomorrow <- today() + ddays(1)
last_year <- today() - dyears(1)

Periods

#### Constructor functions
seconds(15)
## [1] "15S"
minutes(10)
## [1] "10M 0S"
hours(c(12, 24))
## [1] "12H 0M 0S" "24H 0M 0S"
days(7)
## [1] "7d 0H 0M 0S"
months(1:6)
## [1] "1m 0d 0H 0M 0S" "2m 0d 0H 0M 0S" "3m 0d 0H 0M 0S" "4m 0d 0H 0M 0S"
## [5] "5m 0d 0H 0M 0S" "6m 0d 0H 0M 0S"
weeks(3)
## [1] "21d 0H 0M 0S"
years(1)
## [1] "1y 0m 0d 0H 0M 0S"
#### Adding and multiplying
10 * (months(6) + days(1))
## [1] "60m 10d 0H 0M 0S"
days(50) + hours(25) + minutes(2)
## [1] "50d 25H 2M 0S"
flights_dt %>% 
  filter(arr_time < dep_time)
## # A tibble: 10,633 × 9
##    origin dest  dep_delay arr_delay dep_time            sched_dep_time     
##    <chr>  <chr>     <dbl>     <dbl> <dttm>              <dttm>             
##  1 EWR    BQN           9        -4 2013-01-01 19:29:00 2013-01-01 19:20:00
##  2 JFK    DFW          59        NA 2013-01-01 19:39:00 2013-01-01 18:40:00
##  3 EWR    TPA          -2         9 2013-01-01 20:58:00 2013-01-01 21:00:00
##  4 EWR    SJU          -6       -12 2013-01-01 21:02:00 2013-01-01 21:08:00
##  5 EWR    SFO          11       -14 2013-01-01 21:08:00 2013-01-01 20:57:00
##  6 LGA    FLL         -10        -2 2013-01-01 21:20:00 2013-01-01 21:30:00
##  7 EWR    MCO          41        43 2013-01-01 21:21:00 2013-01-01 20:40:00
##  8 JFK    LAX          -7       -24 2013-01-01 21:28:00 2013-01-01 21:35:00
##  9 EWR    FLL          49        28 2013-01-01 21:34:00 2013-01-01 20:45:00
## 10 EWR    FLL          -9       -14 2013-01-01 21:36:00 2013-01-01 21:45:00
## # ℹ 10,623 more rows
## # ℹ 3 more variables: arr_time <dttm>, sched_arr_time <dttm>, air_time <dbl>
flights_dt <- flights_dt %>%
    mutate(
    overnight = arr_time < dep_time,
    arr_time = arr_time + days(overnight * 1),
    sched_arr_time = sched_arr_time + days(overnight * 1)
  )

flights_dt %>% 
  filter(overnight, arr_time < dep_time) 
## # A tibble: 0 × 10
## # ℹ 10 variables: origin <chr>, dest <chr>, dep_delay <dbl>, arr_delay <dbl>,
## #   dep_time <dttm>, sched_dep_time <dttm>, arr_time <dttm>,
## #   sched_arr_time <dttm>, air_time <dbl>, overnight <lgl>

Intervals

years(1) / days(1)
## [1] 365.25
#### Interval
next_year <- today() + years(1)
(today() %--% next_year) / ddays(1)
## [1] 365
#### Integer division
(today() %--% next_year) %/% days(1)
## [1] 365