Chapter 15

Genral 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 Order

#Transform Data: calculate average TV hours by religion
tvhours_by_relig <- gss_cat %>%
    group_by(relig) %>%
    summarise(avg_tvhours = mean(tvhours, na.rm = TRUE))
#plot
tvhours_by_relig %>%
    ggplot(aes(x = avg_tvhours, y = relig)) +
    geom_point()

Order Factor Levels

tvhours_by_relig %>%
    ggplot(aes(x = avg_tvhours, y = fct_reorder(.f = relig, .x = avg_tvhours))) +
    geom_point() + 
    #Label
    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() + 
    #Label
    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
#recode function
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
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 Dates and Times

#from strings
"2024-11-01" %>% ymd()
## [1] "2024-11-01"
"2024-11-01 3-24-45" %>% ymd_hms()
## [1] "2024-11-01 03:24:45 UTC"
#from numbers
20241102 %>% ymd()
## [1] "2024-11-02"

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"

Date-Time component

Getting Components

date_time <- ymd_hms("2024-11-04 14-31-39")
date_time
## [1] "2024-11-04 14:31:39 UTC"
year(date_time)
## [1] 2024
month(date_time, label = TRUE, abbr = FALSE)
## [1] November
## 12 Levels: January < February < March < April < May < June < ... < December
yday(date_time)
## [1] 309
mday(date_time)
## [1] 4
wday(date_time, label = TRUE, abbr = FALSE)
## [1] Monday
## 7 Levels: Sunday < Monday < Tuesday < Wednesday < Thursday < ... < Saturday
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, abbr = FALSE)) %>%
    ggplot(aes(wday)) +
    geom_bar()

Roudning

# floor data 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 2013-07-16 18:12:00 2013-07-01 00:00:00
##  2 2013-10-19 18:37:00 2013-10-01 00:00:00
##  3 2013-02-24 17:23:00 2013-02-01 00:00:00
##  4 2013-09-20 07:11:00 2013-09-01 00:00:00
##  5 2013-10-08 08:52:00 2013-10-01 00:00:00
##  6 2013-02-17 13:37:00 2013-02-01 00:00:00
##  7 2013-09-27 18:15:00 2013-09-01 00:00:00
##  8 2013-04-20 06:10:00 2013-04-01 00:00:00
##  9 2013-01-21 10:59:00 2013-01-01 00:00:00
## 10 2013-10-18 10:38:00 2013-10-01 00:00:00
# ceiling data 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 2013-01-13 13:37:00 2013-02-01 00:00:00
##  2 2013-03-01 15:32:00 2013-04-01 00:00:00
##  3 2013-05-16 09:47:00 2013-06-01 00:00:00
##  4 2013-02-28 08:57:00 2013-03-01 00:00:00
##  5 2013-08-22 21:02:00 2013-09-01 00:00:00
##  6 2013-10-08 07:53:00 2013-11-01 00:00:00
##  7 2013-01-07 12:14:00 2013-02-01 00:00:00
##  8 2013-10-30 09:57:00 2013-11-01 00:00:00
##  9 2013-03-22 15:37:00 2013-04-01 00:00:00
## 10 2013-02-26 06:28:00 2013-03-01 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 2013-11-23 13:54:00 2013-01-01 13:54:00
##  2 2013-06-05 12:05:00 2013-01-01 12:05:00
##  3 2013-10-29 22:35:00 2013-01-01 22:35:00
##  4 2013-04-09 17:00:00 2013-01-01 17:00:00
##  5 2013-03-28 10:45:00 2013-01-01 10:45:00
##  6 2013-10-19 17:58:00 2013-01-01 17:58:00
##  7 2013-06-22 17:54:00 2013-01-01 17:54:00
##  8 2013-09-16 11:59:00 2013-01-01 11:59:00
##  9 2013-05-18 08:59:00 2013-01-01 08:59:00
## 10 2013-11-29 17:12:00 2013-01-01 17:12:00

Time Spans