Chapter 15 Factors

Creating factors

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 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")

Modifying factor levels

Chapter 16

Creating data/times

From Strings

# From Strings
"2022/10/28" %>% ymd()
## [1] "2022-10-28"
# From Numbers
20221028 %>% ymd()
## [1] "2022-10-28"
"2022-10-28 4-41-30" %>% ymd_hms()
## [1] "2022-10-28 04:41:30 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] "2024-11-04 UTC"
# From Date-Time to Date
now() %>% as_date()
## [1] "2024-11-04"

Data-time components

Getting components

date_time <- ymd_hms("2022-10-28 18-18-18")
date_time
## [1] "2022-10-28 18:18:18 UTC"
year(date_time)
## [1] 2022
month(date_time, label = TRUE, abbr = FALSE)
## [1] October
## 12 Levels: January < February < March < April < May < June < ... < December
yday(date_time)
## [1] 301
mday(date_time)
## [1] 28
wday(date_time, label = TRUE, abbr = FALSE)
## [1] Friday
## 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 %>% 
  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 2013-01-25 17:16:00 2013-01-01 00:00:00
##  2 2013-10-19 19:30:00 2013-10-01 00:00:00
##  3 2013-12-19 09:44:00 2013-12-01 00:00:00
##  4 2013-09-27 06:31:00 2013-09-01 00:00:00
##  5 2013-06-08 08:24:00 2013-06-01 00:00:00
##  6 2013-10-11 16:35:00 2013-10-01 00:00:00
##  7 2013-11-16 08:20:00 2013-11-01 00:00:00
##  8 2013-06-03 06:23:00 2013-06-01 00:00:00
##  9 2013-09-21 08:07:00 2013-09-01 00:00:00
## 10 2013-04-09 19:25:00 2013-04-01 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 2013-09-11 15:39:00 2013-10-01 00:00:00
##  2 2013-08-15 14:33:00 2013-09-01 00:00:00
##  3 2013-01-24 18:28:00 2013-02-01 00:00:00
##  4 2013-11-01 19:33:00 2013-12-01 00:00:00
##  5 2013-05-30 18:09:00 2013-06-01 00:00:00
##  6 NA                  NA                 
##  7 2013-06-23 09:31:00 2013-07-01 00:00:00
##  8 2013-02-26 17:53:00 2013-03-01 00:00:00
##  9 2013-10-27 14:26:00 2013-11-01 00:00:00
## 10 2013-03-24 11:24:00 2013-04-01 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 NA                  NA                 
##  2 NA                  NA                 
##  3 2013-03-15 14:52:00 2013-01-01 14:52:00
##  4 2013-05-13 07:14:00 2013-01-01 07:14:00
##  5 2013-02-28 13:01:00 2013-01-01 13:01:00
##  6 2013-09-07 07:51:00 2013-01-01 07:51:00
##  7 2013-04-06 17:56:00 2013-01-01 17:56:00
##  8 2013-02-15 07:19:00 2013-01-01 07:19:00
##  9 2013-10-22 09:50:00 2013-01-01 09:50:00
## 10 2013-12-06 20:02:00 2013-01-01 20:02:00

Time Spans