Chapter 15

Introduction

Creating factors

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

General socail 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

unordered factor levels

# Transform data: 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()

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")
## Warning: 1 unknown level in `f`: Don't Know
## 1 unknown level in `f`: Don't Know

Modifying factor 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_co1 = fct_collapse(race, "Minority" = c("Black", "Other"))) %>% 
    select(race, race_co1) %>%
    filter(race != "White") 
## # A tibble: 5,088 × 2
##    race  race_co1
##    <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 mubers 
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, 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] "2024-04-09 UTC"
# From date-time to date 
now() %>% as_date()
## [1] "2024-04-09"

Data-time components

Getting Compnents

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
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 raounding 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 2013-05-29 09:43:00 2013-05-01 00:00:00
##  2 2013-05-17 18:28:00 2013-05-01 00:00:00
##  3 2013-01-22 14:26:00 2013-01-01 00:00:00
##  4 2013-05-03 14:33:00 2013-05-01 00:00:00
##  5 2013-12-30 20:04:00 2013-12-01 00:00:00
##  6 2013-06-19 12:35:00 2013-06-01 00:00:00
##  7 2013-02-07 21:27:00 2013-02-01 00:00:00
##  8 2013-03-12 07:40:00 2013-03-01 00:00:00
##  9 2013-07-18 08:23:00 2013-07-01 00:00:00
## 10 2013-09-06 07:52:00 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 2013-01-14 17:40:00 2013-02-01 00:00:00
##  2 2013-12-31 22:18:00 2014-01-01 00:00:00
##  3 2013-04-30 09:41:00 2013-05-01 00:00:00
##  4 2013-05-05 18:09:00 2013-06-01 00:00:00
##  5 2013-11-26 07:09:00 2013-12-01 00:00:00
##  6 2013-08-17 19:39:00 2013-09-01 00:00:00
##  7 2013-06-01 09:01:00 2013-07-01 00:00:00
##  8 2013-08-27 17:09:00 2013-09-01 00:00:00
##  9 2013-03-16 11:42:00 2013-04-01 00:00:00
## 10 2013-07-10 08:26:00 2013-08-01 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 2013-07-11 20:09:00 2013-01-01 20:09:00
##  2 2013-02-10 15:49:00 2013-01-01 15:49:00
##  3 2013-06-04 10:29:00 2013-01-01 10:29:00
##  4 2013-11-07 18:08:00 2013-01-01 18:08:00
##  5 2013-06-05 07:15:00 2013-01-01 07:15:00
##  6 2013-01-30 06:42:00 2013-01-01 06:42:00
##  7 2013-01-02 20:24:00 2013-01-01 20:24:00
##  8 2013-07-27 06:23:00 2013-01-01 06:23:00
##  9 2013-11-22 05:59:00 2013-01-01 05:59:00
## 10 2013-06-30 19:28:00 2013-01-01 19:28:00

Time spans

dseconds(15)
## [1] "15s"
#> [1] "15s"
dminutes(10)
## [1] "600s (~10 minutes)"
#> [1] "600s (~10 minutes)"
dhours(c(12, 24))
## [1] "43200s (~12 hours)" "86400s (~1 days)"
#> [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)"
#> [1] "0s"                "86400s (~1 days)"  "172800s (~2 days)"
#> [4] "259200s (~3 days)" "345600s (~4 days)" "432000s (~5 days)"
dweeks(3)
## [1] "1814400s (~3 weeks)"
#> [1] "1814400s (~3 weeks)"
dyears(1)
## [1] "31557600s (~1 years)"
#> [1] "31557600s (~1 years)"