Chapter 15

Intro

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

unorderd factor levels

# Transform Data
tvhours_by_relig<-gss_cat%>%
    group_by(relig)%>%
    summarise(avg_tvhours= mean(tvhours, na.rm = TRUE))
# Plot
tvhours_by_relig%>%
    ggplot(aes(x= avg_tvhours, y= relig)) + 
    geom_point()

### orderd factor levels

tvhours_by_relig%>%
    ggplot(aes(x= avg_tvhours, y= fct_reorder(.f= relig,.x= avg_tvhours))) + 
    geom_point()+ 
    # Lable
    labs(y= NULL, x= "Mean Daily Hours Watching TV")

### moving 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()+
    
    # Lable
    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
# Recode
gss_cat%>%
    mutate(race_rev= fct_recode(race,"African American"= "Black"))%>%
    select(race, race_rev)%>%
    filter(race== "BLack")
## # A tibble: 0 × 2
## # ℹ 2 variables: race <fct>, race_rev <fct>
# Collapse Multiple Levels 
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
gss_cat%>%
    mutate(race_lump= fct_lump(race))%>%
    distinct(race_lump)
## # A tibble: 2 × 1
##   race_lump
##   <fct>    
## 1 White    
## 2 Other

Chapter 16

Intro

Creating Dates/Times

from strings

# From Strings
"2022-10-28"%>% ymd()
## [1] "2022-10-28"
"2022-10-28 4-41-30"%>% ymd_hms()
## [1] "2022-10-28 04:41:30 UTC"
# From numbers
20221028%>% ymd()
## [1] "2022-10-28"

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

# Date to date-time
today()%>% as_datetime()
## [1] "2025-11-11 UTC"
# date-time to Date
now()%>% as_date()
## [1] "2025-11-11"

Date/Time Components

getting components

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 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 2013-01-15 08:58:00 2013-01-01 00:00:00
##  2 2013-05-10 14:25:00 2013-05-01 00:00:00
##  3 2013-10-18 11:50:00 2013-10-01 00:00:00
##  4 2013-08-22 23:38:00 2013-08-01 00:00:00
##  5 2013-01-14 13:22:00 2013-01-01 00:00:00
##  6 2013-09-14 19:15:00 2013-09-01 00:00:00
##  7 2013-08-12 07:57:00 2013-08-01 00:00:00
##  8 2013-05-28 15:30:00 2013-05-01 00:00:00
##  9 2013-01-12 10:53:00 2013-01-01 00:00:00
## 10 2013-02-20 08:46:00 2013-02-01 00:00:00
# Ceiling_date rounding down
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 2013-05-12 09:02:00 2013-06-01 00:00:00
##  2 2013-11-13 17:08:00 2013-12-01 00:00:00
##  3 2013-02-18 12:26:00 2013-03-01 00:00:00
##  4 2013-08-04 11:58:00 2013-09-01 00:00:00
##  5 2013-08-02 08:09:00 2013-09-01 00:00:00
##  6 2013-04-16 06:39:00 2013-05-01 00:00:00
##  7 2013-07-13 15:45:00 2013-08-01 00:00:00
##  8 2013-05-17 20:59:00 2013-06-01 00:00:00
##  9 2013-05-20 10:49:00 2013-06-01 00:00:00
## 10 2013-02-26 15:54:00 2013-03-01 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 2013-02-21 09:51:00 2013-01-01 09:51:00
##  2 2013-10-02 19:31:00 2013-01-01 19:31:00
##  3 2013-01-12 08:10:00 2013-01-01 08:10:00
##  4 2013-08-04 18:51:00 2013-01-01 18:51:00
##  5 2013-09-05 11:49:00 2013-01-01 11:49:00
##  6 2013-03-18 14:29:00 2013-01-01 14:29:00
##  7 2013-03-21 19:32:00 2013-01-01 19:32:00
##  8 2013-05-05 14:51:00 2013-01-01 14:51:00
##  9 2013-04-04 09:02:00 2013-01-01 09:02:00
## 10 2013-10-01 18:52:00 2013-01-01 18:52:00

Time Spans