Chapter 15

Introduction

Creating Factors

Gerneral Social Servay

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

# transforms 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()

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

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 muliple 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

Chapter 16 Dates and Time

Introduction

Creating Date/Times

From Strings

# from strings 
"2022-10-28" %>% ymd()
## [1] "2022-10-28"
# from numbers 
20221928 %>% ymd()
## Warning: All formats failed to parse. No formats found.
## [1] NA
"2022-10-28 4-41-30" %>% ymd_hms()
## [1] "2022-10-28 04:41:30 UTC"

From ind 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] "2025-11-04 UTC"
# From date-time to date 
now() %>% as_date()
## [1] "2025-11-04"

Date,time component

Getting componetns

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")) %>%
    sample_n(10)
## # A tibble: 10 × 10
##    origin dest  dep_delay arr_delay dep_time            sched_dep_time     
##    <chr>  <chr>     <dbl>     <dbl> <dttm>              <dttm>             
##  1 LGA    SRQ          23        24 2013-09-17 11:38:00 2013-09-17 11:15:00
##  2 JFK    IND          -5        -4 2013-11-11 15:05:00 2013-11-11 15:10:00
##  3 EWR    DTW          -6        -3 2013-06-16 08:31:00 2013-06-16 08:37:00
##  4 LGA    PIT         132       112 2013-08-13 18:12:00 2013-08-13 16:00:00
##  5 JFK    SRQ          -4       -21 2013-11-28 07:42:00 2013-11-28 07:46:00
##  6 EWR    SFO          -3       -46 2013-07-15 07:40:00 2013-07-15 07:43:00
##  7 EWR    SJU           5       -15 2013-01-04 09:34:00 2013-01-04 09:29:00
##  8 EWR    MCI          -8         5 2013-06-06 11:54:00 2013-06-06 12:02:00
##  9 LGA    MIA          -5       -13 2013-09-13 09:45:00 2013-09-13 09:50:00
## 10 LGA    DFW          -5       -17 2013-07-19 06:50:00 2013-07-19 06:55:00
## # ℹ 4 more variables: arr_time <dttm>, sched_arr_time <dttm>, air_time <dbl>,
## #   week <dttm>
# ceiling_date for rounding up
flights_dt %>%
    mutate(week = ceiling_date(dep_time, "month")) %>%
    sample_n(10)
## # A tibble: 10 × 10
##    origin dest  dep_delay arr_delay dep_time            sched_dep_time     
##    <chr>  <chr>     <dbl>     <dbl> <dttm>              <dttm>             
##  1 LGA    PIT          -9         0 2013-10-26 12:51:00 2013-10-26 13:00:00
##  2 EWR    STL          29        10 2013-09-30 17:59:00 2013-09-30 17:30:00
##  3 LGA    MSP          -3         3 2013-12-08 08:27:00 2013-12-08 08:30:00
##  4 LGA    GRR          -9         1 2013-01-24 09:41:00 2013-01-24 09:50:00
##  5 LGA    DEN          10         4 2013-09-27 17:45:00 2013-09-27 17:35:00
##  6 EWR    DTW          12        15 2013-01-14 13:02:00 2013-01-14 12:50:00
##  7 EWR    SAN           1       -20 2013-09-23 17:26:00 2013-09-23 17:25:00
##  8 EWR    CHS           9         3 2013-07-31 15:02:00 2013-07-31 14:53:00
##  9 EWR    DEN          25        29 2013-11-04 16:44:00 2013-11-04 16:19:00
## 10 JFK    LAX          -3         4 2013-04-20 15:57:00 2013-04-20 16:00:00
## # ℹ 4 more variables: arr_time <dttm>, sched_arr_time <dttm>, air_time <dbl>,
## #   week <dttm>

Setting compnents

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 2013-01-10 14:40:00 2013-01-01 14:40:00
##  2 2013-02-04 19:01:00 2013-01-01 19:01:00
##  3 2013-10-11 19:54:00 2013-01-01 19:54:00
##  4 2013-06-30 16:29:00 2013-01-01 16:29:00
##  5 2013-04-17 07:48:00 2013-01-01 07:48:00
##  6 2013-09-18 14:36:00 2013-01-01 14:36:00
##  7 2013-08-23 21:02:00 2013-01-01 21:02:00
##  8 2013-06-25 08:02:00 2013-01-01 08:02:00
##  9 2013-08-28 06:07:00 2013-01-01 06:07:00
## 10 2013-02-14 10:48:00 2013-01-01 10:48:00

Times spans