Week 6: Module 11 - Code Along 10

Chapter 15 - Factors

Introduction

# To create/see data summary.
skimr::skim(gss_cat)

Data summary
Name	gss_cat
Number of rows	21483
Number of columns	9
_______________________
Column type frequency:
factor	6
numeric	3
________________________
Group variables	None

Variable type: factor

skim_variable	complete_rate	ordered	n_unique	top_counts
marital	1	FALSE	6	Mar: 10117, Nev: 5416, Div: 3383, Wid: 1807
race	1	FALSE	3	Whi: 16395, Bla: 3129, Oth: 1959, Not: 0
rincome	1	FALSE	16	$25: 7363, Not: 7043, $20: 1283, $10: 1168
partyid	1	FALSE	10	Ind: 4119, Not: 3690, Str: 3490, Not: 3032
relig	1	FALSE	15	Pro: 10846, Cat: 5124, Non: 3523, Chr: 689
denom	1	FALSE	30	Not: 10072, Oth: 2534, No : 1683, Sou: 1536

Variable type: numeric

skim_variable	n_missing	complete_rate	mean	sd	p0	p25	p50	p75	p100	hist
year	0	1.00	2006.50	4.45	2000	2002	2006	2010	2014	▇▃▇▂▆
age	76	1.00	47.18	17.29	18	33	46	59	89	▇▇▇▅▂
tvhours	10146	0.53	2.98	2.59	0	1	2	4	24	▇▂▁▁▁

Creating Factors

# Two strings are created to show the problem. 

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

x2 <- c("Dec", "Apr", "Jam", "Mar")

# Create a list of the valid levels.

month_levels <- c(
  "Jan", "Feb", "Mar", "Apr", "May", "Jun", 
  "Jul", "Aug", "Sep", "Oct", "Nov", "Dec")

# Create factors for both strings.

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)

# Typos are automatically converted to NA. 
y2

## [1] Dec  Apr  <NA> Mar 
## Levels: Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec

# Use parse_factor to receive a warning that there is a problem.


y2 <- parse_factor(x2, levels = month_levels)

## Warning: 1 parsing failure.
## row col           expected actual
##   3  -- value in level set    Jam

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

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 TV Hours Watched")

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 TV Hours Watched")

Modifying Factor Levels

gss_cat %>% distinct(partyid)

## # A tibble: 10 × 1
##    partyid           
##    <fct>             
##  1 Ind,near rep      
##  2 Not str republican
##  3 Independent       
##  4 Not str democrat  
##  5 Strong democrat   
##  6 Ind,near dem      
##  7 Strong republican 
##  8 Other party       
##  9 No answer         
## 10 Don't know

gss_cat %>% count(partyid)

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

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, "POC" = "Black")) %>%
    select(race, race_rev) %>%
    filter(race == "Black")

## # A tibble: 3,129 × 2
##    race  race_rev
##    <fct> <fct>   
##  1 Black POC     
##  2 Black POC     
##  3 Black POC     
##  4 Black POC     
##  5 Black POC     
##  6 Black POC     
##  7 Black POC     
##  8 Black POC     
##  9 Black POC     
## 10 Black POC     
## # 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 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 Times

Introduction

Creating Dates/Times

From Strings

# To see class
"2024-06-19" %>% ymd() %>% class()

## [1] "Date"

# From Strings
"2024-06-19" %>% ymd()

## [1] "2024-06-19"

"2024/06/19" %>% ymd()

## [1] "2024-06-19"

# From Numbers
20240619 %>% ymd()

## [1] "2024-06-19"

# Time - POSIXct and POSIXt are also names for a date/time object.
"2024-06-19 07-18-51" %>% ymd_hms()

## [1] "2024-06-19 07:18:51 UTC"

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
as_datetime(today())

## [1] "2024-06-19 UTC"

today() %>% as_datetime()

## [1] "2024-06-19 UTC"

# From date-time to date
now() %>% as_date()

## [1] "2024-06-19"

Date-Time 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>

Getting Components

datetime <- ymd_hms ("2024-06-19 07:55:22")

year(datetime)

## [1] 2024

month(datetime)

## [1] 6

# Day of the month
mday(datetime)

## [1] 19

# Day of the year
yday(datetime)

## [1] 171

# Day of the week
wday(datetime)

## [1] 4

# To return abbreviated names.
month(datetime, label = TRUE)

## [1] Jun
## 12 Levels: Jan < Feb < Mar < Apr < May < Jun < Jul < Aug < Sep < ... < Dec

# To return full names
month(datetime, label = TRUE, abbr = FALSE)

## [1] June
## 12 Levels: January < February < March < April < May < June < ... < December

Rounding

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

Setting Components

(datetime <- ymd_hms("2024-06-19 08:21:56"))

## [1] "2024-06-19 08:21:56 UTC"

year(datetime) <- 2024
datetime

## [1] "2024-06-19 08:21:56 UTC"

month(datetime) <- 05
datetime

## [1] "2024-05-19 08:21:56 UTC"

hour(datetime) <- hour(datetime) + 1
datetime

## [1] "2024-05-19 09:21:56 UTC"

# To set multiple values at once.
update(datetime, year = 2024, month = 06, mday = 19, hour = 16)

## [1] "2024-06-19 16:21:56 UTC"

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

Time Spans

Durations

# To find age
h_age <- today() - ymd(20100511)
h_age

## Time difference of 5153 days

as.duration(h_age)

## [1] "445219200s (~14.11 years)"

# To add years
dyears(1) + dweeks(12) + dhours(15)

## [1] "38869200s (~1.23 years)"

# To multiply years
2 * dyears(1)

## [1] "63115200s (~2 years)"

# To add and subtract durations to and from days
tomorrow <- today() + ddays(1)

last_year <- today() - dyears(1)

Periods

one_pm <- ymd_hms("2024-06-19 17:00:00", tz = "America/New_York")
one_pm

## [1] "2024-06-19 17:00:00 EDT"

one_pm + days(1)

## [1] "2024-06-20 17:00:00 EDT"

# To multiply periods
10 * (months(6) + days(1))

## [1] "60m 10d 0H 0M 0S"

# To add periods
days(50) + hours(25) + minutes(2)

## [1] "50d 25H 2M 0S"

flights_dt %>% 
  filter(arr_time < dep_time)

## # A tibble: 10,633 × 9
##    origin dest  dep_delay arr_delay dep_time            sched_dep_time     
##    <chr>  <chr>     <dbl>     <dbl> <dttm>              <dttm>             
##  1 EWR    BQN           9        -4 2013-01-01 19:29:00 2013-01-01 19:20:00
##  2 JFK    DFW          59        NA 2013-01-01 19:39:00 2013-01-01 18:40:00
##  3 EWR    TPA          -2         9 2013-01-01 20:58:00 2013-01-01 21:00:00
##  4 EWR    SJU          -6       -12 2013-01-01 21:02:00 2013-01-01 21:08:00
##  5 EWR    SFO          11       -14 2013-01-01 21:08:00 2013-01-01 20:57:00
##  6 LGA    FLL         -10        -2 2013-01-01 21:20:00 2013-01-01 21:30:00
##  7 EWR    MCO          41        43 2013-01-01 21:21:00 2013-01-01 20:40:00
##  8 JFK    LAX          -7       -24 2013-01-01 21:28:00 2013-01-01 21:35:00
##  9 EWR    FLL          49        28 2013-01-01 21:34:00 2013-01-01 20:45:00
## 10 EWR    FLL          -9       -14 2013-01-01 21:36:00 2013-01-01 21:45:00
## # ℹ 10,623 more rows
## # ℹ 3 more variables: arr_time <dttm>, sched_arr_time <dttm>, air_time <dbl>

flights_dt <- flights_dt %>% 
  mutate(overnight = arr_time < dep_time, arr_time = arr_time + days(overnight * 1), sched_arr_time = sched_arr_time + days(overnight * 1))

flights_dt %>% 
  filter(overnight, arr_time < dep_time)

## # A tibble: 0 × 10
## # ℹ 10 variables: origin <chr>, dest <chr>, dep_delay <dbl>, arr_delay <dbl>,
## #   dep_time <dttm>, sched_dep_time <dttm>, arr_time <dttm>,
## #   sched_arr_time <dttm>, air_time <dbl>, overnight <lgl>

Intervals

# To find out how many days in a year. This answer is different than the one in the text because this is 2024.
next_year <- today() + years(1)

(today() %--% next_year) / ddays(1)

## [1] 365

Time Zones

# To find the current time zone.
Sys.timezone()

## [1] "America/New_York"

# To find out the time difference in another time zone.
(x1 <- ymd_hms("2015-06-19 12:00:00", tz = "America/New_York"))

## [1] "2015-06-19 12:00:00 EDT"

(x2 <- ymd_hms("2015-06-19 18:00:00", tz = "Europe/Dublin"))

## [1] "2015-06-19 18:00:00 IST"

x1 - x2

## Time difference of -1 hours

x2 - x1

## Time difference of 1 hours

Week 6: Module 11 - Code Along 10

R for Data Science: Chapter 15 & 16

Sara Donahue

2024-06-19

Chapter 15 - Factors

Introduction

Creating Factors

Modifying Factor Order

Unordered Factor Levels

Ordered Factor Levels

Moving a Single Level to the Front

Modifying Factor Levels

Chapter 16 - Dates and Times

Introduction

Creating Dates/Times

From Strings

From Individual Components

From Other Types

Date-Time Components

Getting Components

Rounding

Setting Components

Time Spans

Durations

Periods

Intervals

Time Zones