knitr::opts_chunk$set(echo = TRUE,
                      message = FALSE,
                      warning = FALSE)

# Load package
library(tidyverse)
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.2.0     ✔ readr     2.1.6
## ✔ forcats   1.0.1     ✔ stringr   1.6.0
## ✔ ggplot2   4.0.2     ✔ tibble    3.3.1
## ✔ lubridate 1.9.5     ✔ tidyr     1.3.2
## ✔ purrr     1.2.1     
## ── 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(forcats)
library(lubridate)
library(nycflights13)

Chapter 15 Factors

Creating Factors

x1 <- c("Dec", "Apr", "Jan", "Mar")

x2 <- c("Dec", "Apr", "Jam", "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
sort(y1)
## [1] Jan Mar Apr Dec
## Levels: Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec
y2 <- factor(x2, levels = month_levels)
y2
## [1] Dec  Apr  <NA> Mar 
## Levels: Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec

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

Unordered Factor levels

# 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

# Plot
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 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")

Modifying Factor Levels

gss_cat %>% distinct(race)
## # A tibble: 3 × 1
##   race 
##   <fct>
## 1 White
## 2 Black
## 3 Other
# Re-code 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 into 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 Times

Introduction

Creating Dates/ Times

From Strings

today()
## [1] "2026-03-31"
# From Strings

"2026-03-31" %>% ymd() %>% 
    class()
## [1] "Date"
# From numbers

20220331 %>% ymd()
## [1] "2022-03-31"
"2026-03-31-4-41-30" %>% ymd_hms() %>%
    class()
## [1] "POSIXct" "POSIXt"

From 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() %>% class()
## [1] "POSIXct" "POSIXt"
now() %>% as_date() %>% class()
## [1] "Date"

Date-Time Components

Getting Components

date_time <- ymd_hms("2026-03-31-18-18-18")
date_time
## [1] "2026-03-31 18:18:18 UTC"
year(date_time)
## [1] 2026
month(date_time, label = TRUE, abbr = FALSE)
## [1] March
## 12 Levels: January < February < March < April < May < June < ... < December
yday(date_time)
## [1] 90
mday(date_time)
## [1] 31
wday(date_time, label = TRUE, abbr= FALSE)
## [1] Tuesday
## 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"))

#Plotting flights per day
flights_dt %>%
    transmute(wday = wday(dep_time, label = TRUE)) %>%
    
    ggplot(aes(wday)) +
    geom_bar()

#Plotting flights per minute

flights_dt %>%
    mutate(minute = minute(dep_time)) %>%
    group_by(minute) %>%
    summarise(
        avg_delay = mean(arr_delay, na.rm = TRUE), 
        n = n()
    ) %>%
    
    ggplot(aes(minute, avg_delay)) +
geom_line()

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 2013-09-12 14:29:00 2013-09-01 00:00:00
##  2 2013-09-07 20:22:00 2013-09-01 00:00:00
##  3 2013-02-26 09:56:00 2013-02-01 00:00:00
##  4 2013-09-18 11:15:00 2013-09-01 00:00:00
##  5 2013-11-19 20:35:00 2013-11-01 00:00:00
##  6 2013-07-28 22:59:00 2013-07-01 00:00:00
##  7 2013-01-17 06:58:00 2013-01-01 00:00:00
##  8 2013-03-24 08:21:00 2013-03-01 00:00:00
##  9 2013-09-07 18:21:00 2013-09-01 00:00:00
## 10 2013-01-22 15:30:00 2013-01-01 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 2013-09-24 08:29:00 2013-10-01 00:00:00
##  2 2013-05-20 15:58:00 2013-06-01 00:00:00
##  3 2013-03-03 14:26:00 2013-04-01 00:00:00
##  4 2013-07-01 11:55:00 2013-08-01 00:00:00
##  5 2013-10-25 14:14:00 2013-11-01 00:00:00
##  6 2013-02-22 06:33:00 2013-03-01 00:00:00
##  7 2013-02-20 10:38:00 2013-03-01 00:00:00
##  8 2013-07-30 19:57:00 2013-08-01 00:00:00
##  9 2013-12-13 08:09:00 2014-01-01 00:00:00
## 10 2013-07-18 05:57:00 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 2013-05-15 14:44:00 2013-01-01 14:44:00
##  2 2013-10-31 18:26:00 2013-01-01 18:26:00
##  3 2013-04-08 14:43:00 2013-01-01 14:43:00
##  4 2013-11-04 08:30:00 2013-01-01 08:30:00
##  5 2013-11-05 13:11:00 2013-01-01 13:11:00
##  6 2013-10-25 20:39:00 2013-01-01 20:39:00
##  7 2013-04-21 19:13:00 2013-01-01 19:13:00
##  8 2013-05-02 06:55:00 2013-01-01 06:55:00
##  9 2013-02-05 20:49:00 2013-01-01 20:49:00
## 10 2013-05-11 08:40:00 2013-01-01 08:40:00

Time Spans