code-along-10.knit

title: “Week 11: Code Along 10” subtitle: “R For Data Science: Chapter 15 & 16” author: “Declan Fogarty” date: “2025-06-17” output: html_document editor_options: chunk_output_type: console —

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

Unordered factor levels

# Transform data: calculate average tv hours by religion 
relig_summary <- gss_cat %>%
  group_by(relig) %>%
  summarise(
    age = mean(age, na.rm = TRUE),
    tvhours = mean(tvhours, na.rm = TRUE),
    n = n()
  )

ggplot(relig_summary, aes(tvhours, relig)) + geom_point()

Ordered factors level

ggplot(relig_summary, aes(tvhours, fct_reorder(relig, tvhours))) +
  geom_point()

Moving single level to the front

rincome_summary <- gss_cat %>%
  group_by(rincome) %>%
  summarise(
    age = mean(age, na.rm = TRUE),
    tvhours = mean(tvhours, na.rm = TRUE),
    n = n()
  )

ggplot(rincome_summary, aes(age, fct_reorder(rincome, age))) + 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"
  )) %>%
  count(partyid)

## # A tibble: 10 × 2
##    partyid                   n
##    <fct>                 <int>
##  1 No answer               154
##  2 Don't know                1
##  3 Other party             393
##  4 Republican, strong     2314
##  5 Republican, weak       3032
##  6 Independent, near rep  1791
##  7 Independent            4119
##  8 Independent, near dem  2499
##  9 Democrat, weak         3690
## 10 Democrat, strong       3490

#> # A tibble: 10 × 2
#>   partyid                   n
#>   <fct>                 <int>
#> 1 No answer               154
#> 2 Don't know                1
#> 3 Other party             393
#> 4 Republican, strong     2314
#> 5 Republican, weak       3032
#> 6 Independent, near rep  1791
#> # ℹ 4 more rows

Chapter 16 Introduction

Creating date/times

# From strings 
ymd("2017-01-31")

## [1] "2017-01-31"

#> [1] "2017-01-31"
mdy("January 31st, 2017")

## [1] "2017-01-31"

#> [1] "2017-01-31"
dmy("31-Jan-2017")

## [1] "2017-01-31"

#> [1] "2017-01-31"
ymd_hms("2017-01-31 20:11:59")

## [1] "2017-01-31 20:11:59 UTC"

#> [1] "2017-01-31 20:11:59 UTC"
mdy_hm("01/31/2017 08:01")

## [1] "2017-01-31 08:01:00 UTC"

#> [1] "2017-01-31 08:01:00 UTC"

From individual components

flights %>% 
  select(year, month, day, hour, minute) %>% 
  mutate(departure = make_datetime(year, month, day, hour, 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

#> # 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
#> # ℹ 336,770 more rows

From other types

as_datetime(today())

## [1] "2025-06-17 UTC"

#> [1] "2025-02-18 UTC"
as_date(now())

## [1] "2025-06-17"

#> [1] "2025-02-18"

Date-time components

Getting components

datetime <- ymd_hms("2016-07-08 12:34:56")

year(datetime)

## [1] 2016

#> [1] 2016
month(datetime)

## [1] 7

#> [1] 7
mday(datetime)

## [1] 8

#> [1] 8

yday(datetime)

## [1] 190

#> [1] 190
wday(datetime)

## [1] 6

#> [1] 6

Getting components

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

## # A tibble: 328,063 × 9
##    origin dest  dep_delay arr_delay dep_time            sched_dep_time     
##    <chr>  <chr>     <dbl>     <dbl> <dttm>              <dttm>             
##  1 EWR    IAH           2        11 2013-01-01 05:17:00 2013-01-01 05:15:00
##  2 LGA    IAH           4        20 2013-01-01 05:33:00 2013-01-01 05:29:00
##  3 JFK    MIA           2        33 2013-01-01 05:42:00 2013-01-01 05:40:00
##  4 JFK    BQN          -1       -18 2013-01-01 05:44:00 2013-01-01 05:45:00
##  5 LGA    ATL          -6       -25 2013-01-01 05:54:00 2013-01-01 06:00:00
##  6 EWR    ORD          -4        12 2013-01-01 05:54:00 2013-01-01 05:58:00
##  7 EWR    FLL          -5        19 2013-01-01 05:55:00 2013-01-01 06:00:00
##  8 LGA    IAD          -3       -14 2013-01-01 05:57:00 2013-01-01 06:00:00
##  9 JFK    MCO          -3        -8 2013-01-01 05:57:00 2013-01-01 06:00:00
## 10 LGA    ORD          -2         8 2013-01-01 05:58:00 2013-01-01 06:00:00
## # ℹ 328,053 more rows
## # ℹ 3 more variables: arr_time <dttm>, sched_arr_time <dttm>, air_time <dbl>

#> # A tibble: 328,063 × 9
#>   origin dest  dep_delay arr_delay dep_time            sched_dep_time     
#>   <chr>  <chr>     <dbl>     <dbl> <dttm>              <dttm>             
#> 1 EWR    IAH           2        11 2013-01-01 05:17:00 2013-01-01 05:15:00
#> 2 LGA    IAH           4        20 2013-01-01 05:33:00 2013-01-01 05:29:00
#> 3 JFK    MIA           2        33 2013-01-01 05:42:00 2013-01-01 05:40:00
#> 4 JFK    BQN          -1       -18 2013-01-01 05:44:00 2013-01-01 05:45:00
#> 5 LGA    ATL          -6       -25 2013-01-01 05:54:00 2013-01-01 06:00:00
#> 6 EWR    ORD          -4        12 2013-01-01 05:54:00 2013-01-01 05:58:00
#> # ℹ 328,057 more rows
#> # ℹ 3 more variables: arr_time <dttm>, sched_arr_time <dttm>, air_time <dbl>

flights_dt %>% 
  mutate(wday = wday(dep_time, label = TRUE)) %>% 
  ggplot(aes(x = wday)) +
    geom_bar()

Rounding

flights_dt %>% 
  count(week = floor_date(dep_time, "week")) %>% 
  ggplot(aes(week, n)) +
    geom_line()

Setting components

flights_dt %>% 
  mutate(dep_hour = update(dep_time, yday = 1)) %>% 
  ggplot(aes(dep_hour)) +
    geom_freqpoly(binwidth = 300)

Chapter 15

Introduction

Creating factors

General Social Survey

Modifying factor order

Modifying factor levels

Chapter 16

Introduction

Creating date/times

From individual components

From other types

Date-time components

Getting components

Getting components

Rounding

Setting components

Time spans