Chapter 15

Introduction

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

#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

# Ordered factor levels

tvhours_by_relig %>%
  ggplot(aes(x = avg_tvhours, 
             y = fct_reorder(relig, avg_tvhours))) +
  geom_point() +
  labs(y = NULL, x = "Mean Daily Hours Watching TV")

Moving a single level to the front

# Moving a single level to the front

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

Modifying factor levels

# View distinct race categories
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_cal = fct_collapse(race, "Minority" = c("Black", "Other"))) %>% 
  select(race, race_cal) %>%
  filter(race != "White")
## # A tibble: 5,088 × 2
##    race  race_cal
##    <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

Introduction

Creating date/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 %>%
  mutate(departure = make_datetime(
    year = year,
    month = month,
    day = day,
    hour = hour,
    min = minute
  ))
## # A tibble: 336,776 × 20
##     year month   day dep_time sched_dep_time dep_delay arr_time sched_arr_time
##    <int> <int> <int>    <int>          <int>     <dbl>    <int>          <int>
##  1  2013     1     1      517            515         2      830            819
##  2  2013     1     1      533            529         4      850            830
##  3  2013     1     1      542            540         2      923            850
##  4  2013     1     1      544            545        -1     1004           1022
##  5  2013     1     1      554            600        -6      812            837
##  6  2013     1     1      554            558        -4      740            728
##  7  2013     1     1      555            600        -5      913            854
##  8  2013     1     1      557            600        -3      709            723
##  9  2013     1     1      557            600        -3      838            846
## 10  2013     1     1      558            600        -2      753            745
## # ℹ 336,766 more rows
## # ℹ 12 more variables: arr_delay <dbl>, carrier <chr>, flight <int>,
## #   tailnum <chr>, origin <chr>, dest <chr>, air_time <dbl>, distance <dbl>,
## #   hour <dbl>, minute <dbl>, time_hour <dttm>, departure <dttm>

From other types

#From date-time
today() %>% as_datetime()
## [1] "2026-11-09 UTC"
#From date-time to dat 
now() %>% as_date()
## [1] "2026-11-09"

Date-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 %>% 
  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 2013-11-07 14:49:00 2013-11-01 00:00:00
##  2 2013-11-30 15:55:00 2013-11-01 00:00:00
##  3 2013-03-17 11:58:00 2013-03-01 00:00:00
##  4 2013-02-09 22:44:00 2013-02-01 00:00:00
##  5 2013-06-06 11:51:00 2013-06-01 00:00:00
##  6 2013-01-20 11:57:00 2013-01-01 00:00:00
##  7 2013-12-24 13:45:00 2013-12-01 00:00:00
##  8 2013-02-25 06:49:00 2013-02-01 00:00:00
##  9 2013-09-20 09:15:00 2013-09-01 00:00:00
## 10 2013-03-01 06:49:00 2013-03-01 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 2013-05-19 19:28:00 2013-06-01 00:00:00
##  2 2013-12-31 07:13:00 2014-01-01 00:00:00
##  3 2013-12-20 09:02:00 2014-01-01 00:00:00
##  4 2013-01-03 10:09:00 2013-02-01 00:00:00
##  5 2013-12-17 08:58:00 2014-01-01 00:00:00
##  6 2013-05-13 06:35:00 2013-06-01 00:00:00
##  7 2013-07-10 10:23:00 2013-08-01 00:00:00
##  8 2013-05-17 19:24:00 2013-06-01 00:00:00
##  9 2013-12-05 07:56:00 2014-01-01 00:00:00
## 10 2013-03-02 07:29:00 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 2013-12-31 16:29:00 2013-01-01 16:29:00
##  2 2013-08-18 17:46:00 2013-01-01 17:46:00
##  3 2013-10-28 06:07:00 2013-01-01 06:07:00
##  4 2013-03-10 18:23:00 2013-01-01 18:23:00
##  5 2013-06-06 14:34:00 2013-01-01 14:34:00
##  6 2013-03-29 13:25:00 2013-01-01 13:25:00
##  7 2013-02-22 15:03:00 2013-01-01 15:03:00
##  8 2013-10-17 10:25:00 2013-01-01 10:25:00
##  9 2013-07-18 22:15:00 2013-01-01 22:15:00
## 10 2013-11-14 20:45:00 2013-01-01 20:45:00

Time spans