# Load package
library(tidyverse)
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.4     ✔ readr     2.1.5
## ✔ forcats   1.0.0     ✔ stringr   1.5.1
## ✔ ggplot2   3.5.1     ✔ tibble    3.2.1
## ✔ lubridate 1.9.4     ✔ tidyr     1.3.1
## ✔ purrr     1.0.4     
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
library(nycflights13)
library(lubridate)

Chapter 15

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

By religion

#unordered
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
tvhours_by_relig %>%
    
    ggplot(aes(x = avg_tvhours, y = relig)) +
    geom_point()

#ordered
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")

By age

rincome_by_age <- gss_cat %>%
    
    group_by(rincome) %>%
    summarise(
        avg_age = mean(age, na.rm = TRUE)
    )

rincome_by_age %>%
    
    ggplot(aes(x = avg_age, y = fct_reorder(.f = rincome, .x = avg_age))) +
    geom_point() +
    
#label
labs(y = NULL, x = "Age")

ggplot(rincome_by_age, aes(avg_age, fct_relevel(rincome, "Not applicable"))) +
  geom_point()

Modifying factor levels

gss_cat %>%
  mutate(partyid = fct_recode(partyid,
    "Republican, strong"    = "Strong republican",
    "Republican, weak"      = "Not str republican",
    "Independent, near rep" = "Ind,near rep",
    "Independent, near dem" = "Ind,near dem",
    "Democrat, weak"        = "Not str democrat",
    "Democrat, strong"      = "Strong democrat",
    "Other"                 = "No answer",
    "Other"                 = "Don't know",
    "Other"                 = "Other party"
  ))
## # 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  Independe… Prot… Sout…      12
##  2  2000 Divorced         48 White $8000 to 9999  Republica… Prot… Bapt…      NA
##  3  2000 Widowed          67 White Not applicable Independe… Prot… No d…       2
##  4  2000 Never married    39 White Not applicable Independe… Orth… Not …       4
##  5  2000 Divorced         25 White Not applicable Democrat,… None  Not …       1
##  6  2000 Married          25 White $20000 - 24999 Democrat,… Prot… Sout…      NA
##  7  2000 Never married    36 White $25000 or more Republica… Chri… Not …       3
##  8  2000 Divorced         44 White $7000 to 7999  Independe… Prot… Luth…      NA
##  9  2000 Married          44 White $25000 or more Democrat,… Prot… Other       0
## 10  2000 Married          47 White $25000 or more Republica… Prot… Sout…       3
## # ℹ 21,473 more rows
gss_cat %>%
  mutate(partyid = fct_collapse(partyid,
    other = c("No answer", "Don't know", "Other party"),
    rep = c("Strong republican", "Not str republican"),
    ind = c("Ind,near rep", "Independent", "Ind,near dem"),
    dem = c("Not str democrat", "Strong democrat")
  )) %>%
  count(partyid)
## # A tibble: 4 × 2
##   partyid     n
##   <fct>   <int>
## 1 other     548
## 2 rep      5346
## 3 ind      8409
## 4 dem      7180
gss_cat %>%
  mutate(relig = fct_lump(relig, n = 10)) %>%
  count(relig, sort = TRUE) %>%
  print(n = Inf)
## # A tibble: 10 × 2
##    relig                       n
##    <fct>                   <int>
##  1 Protestant              10846
##  2 Catholic                 5124
##  3 None                     3523
##  4 Christian                 689
##  5 Other                     458
##  6 Jewish                    388
##  7 Buddhism                  147
##  8 Inter-nondenominational   109
##  9 Moslem/islam              104
## 10 Orthodox-christian         95

Chapter 16

Creating date/times

#from strings
"2025-04-09" %>% ymd()
## [1] "2025-04-09"
"2025-04-09 5-52-12" %>% ymd_hms()
## [1] "2025-04-09 05:52:12 UTC"
#from numbers

20250409 %>% ymd()
## [1] "2025-04-09"

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

today() %>% as_datetime()
## [1] "2025-04-09 UTC"
now() %>% as_date
## [1] "2025-04-09"

Date-time components

Getting components

date_time <- ymd_hms("2025-04-09 18-05-00")
date_time
## [1] "2025-04-09 18:05:00 UTC"
year(date_time)
## [1] 2025
yday(date_time)
## [1] 99
mday(date_time)
## [1] 9
wday(date_time)
## [1] 4
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

flights_dt %>%
    mutate(week = floor_date(dep_time, "day")) %>%
    select(dep_time, week)
## # A tibble: 328,063 × 2
##    dep_time            week               
##    <dttm>              <dttm>             
##  1 2013-01-01 05:17:00 2013-01-01 00:00:00
##  2 2013-01-01 05:33:00 2013-01-01 00:00:00
##  3 2013-01-01 05:42:00 2013-01-01 00:00:00
##  4 2013-01-01 05:44:00 2013-01-01 00:00:00
##  5 2013-01-01 05:54:00 2013-01-01 00:00:00
##  6 2013-01-01 05:54:00 2013-01-01 00:00:00
##  7 2013-01-01 05:55:00 2013-01-01 00:00:00
##  8 2013-01-01 05:57:00 2013-01-01 00:00:00
##  9 2013-01-01 05:57:00 2013-01-01 00:00:00
## 10 2013-01-01 05:58:00 2013-01-01 00:00:00
## # ℹ 328,053 more rows
flights_dt %>%
    mutate(week = ceiling_date(dep_time, "month")) %>%
    select(dep_time, week)
## # A tibble: 328,063 × 2
##    dep_time            week               
##    <dttm>              <dttm>             
##  1 2013-01-01 05:17:00 2013-02-01 00:00:00
##  2 2013-01-01 05:33:00 2013-02-01 00:00:00
##  3 2013-01-01 05:42:00 2013-02-01 00:00:00
##  4 2013-01-01 05:44:00 2013-02-01 00:00:00
##  5 2013-01-01 05:54:00 2013-02-01 00:00:00
##  6 2013-01-01 05:54:00 2013-02-01 00:00:00
##  7 2013-01-01 05:55:00 2013-02-01 00:00:00
##  8 2013-01-01 05:57:00 2013-02-01 00:00:00
##  9 2013-01-01 05:57:00 2013-02-01 00:00:00
## 10 2013-01-01 05:58:00 2013-02-01 00:00:00
## # ℹ 328,053 more rows

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 2013-03-01 11:52:00 2013-01-01 11:52:00
##  2 2013-10-08 16:59:00 2013-01-01 16:59:00
##  3 2013-12-31 22:45:00 2013-01-01 22:45:00
##  4 2013-08-02 07:59:00 2013-01-01 07:59:00
##  5 2013-04-22 06:19:00 2013-01-01 06:19:00
##  6 2013-09-15 20:46:00 2013-01-01 20:46:00
##  7 2013-09-29 09:06:00 2013-01-01 09:06:00
##  8 2013-03-07 16:30:00 2013-01-01 16:30:00
##  9 2013-06-27 06:58:00 2013-01-01 06:58:00
## 10 2013-02-20 16:42:00 2013-01-01 16:42:00