Week 11: Code along 10
R for Data Science: Chapter 15 and 16
2025-04-09
#Chapter 15 Factors
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 hours watching TV")
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 hours watching TV")## Warning: 1 unknown level in `f`: Don't Know
##modifying factor levels
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,"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 other levels
gss_cat %>% count(race)## # A tibble: 3 × 2
## race n
## <fct> <int>
## 1 Other 1959
## 2 Black 3129
## 3 White 16395gss_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 ##creating date/times
##from strings
#From strings
"2022-10-28" %>% ymd()## [1] "2022-10-28"#from numbers
20221028 %>% ymd()## [1] "2022-10-28""2022-10-28 4-41-30" %>% ymd_hms()## [1] "2022-10-28 04:41:30 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
today() %>% as_datetime()## [1] "2025-04-09 UTC"#from date-time to date
now() %>% as_date()## [1] "2025-04-09"date time components
##gettings components
date_time <-("2022-10-28 18-18-18")
date_time## [1] "2022-10-28 18-18-18"year(date_time)## [1] 2022month(date_time, label = TRUE, abbr = FALSE)## [1] October
## 12 Levels: January < February < March < April < May < June < ... < Decemberyday(date_time)## [1] 301mday(date_time)## [1] 28wday(date_time, label = TRUE, abbr = FALSE)## [1] Friday
## 7 Levels: Sunday < Monday < Tuesday < Wednesday < Thursday < ... < Saturdaymake_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 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 2013-11-08 14:51:00 2013-11-01 00:00:00
## 2 2013-03-31 20:22:00 2013-03-01 00:00:00
## 3 2013-10-16 12:50:00 2013-10-01 00:00:00
## 4 2013-04-28 16:57:00 2013-04-01 00:00:00
## 5 2013-04-18 09:58:00 2013-04-01 00:00:00
## 6 2013-01-13 09:11:00 2013-01-01 00:00:00
## 7 2013-07-31 09:29:00 2013-07-01 00:00:00
## 8 2013-03-01 08:37:00 2013-03-01 00:00:00
## 9 2013-06-03 09:54:00 2013-06-01 00:00:00
## 10 2013-07-03 18:22:00 2013-07-01 00:00:00#ceiling_date for rounding up
flights_dt %>%
mutate(week = ceiling_date(dep_time, "week")) %>%
select(dep_time, week) %>%
sample_n(10)## # A tibble: 10 × 2
## dep_time week
## <dttm> <dttm>
## 1 2013-01-22 19:48:00 2013-01-27 00:00:00
## 2 2013-10-31 07:51:00 2013-11-03 00:00:00
## 3 2013-08-13 16:06:00 2013-08-18 00:00:00
## 4 2013-01-25 08:40:00 2013-01-27 00:00:00
## 5 2013-07-15 08:12:00 2013-07-21 00:00:00
## 6 2013-09-07 14:55:00 2013-09-08 00:00:00
## 7 2013-08-14 05:42:00 2013-08-18 00:00:00
## 8 2013-12-08 19:18:00 2013-12-15 00:00:00
## 9 2013-03-08 11:43:00 2013-03-10 00:00:00
## 10 2013-08-03 10:10:00 2013-08-04 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 2013-02-02 14:51:00 2013-01-01 14:51:00
## 2 2013-09-19 14:49:00 2013-01-01 14:49:00
## 3 2013-09-08 06:54:00 2013-01-01 06:54:00
## 4 2013-11-27 13:40:00 2013-01-01 13:40:00
## 5 2013-11-15 21:06:00 2013-01-01 21:06:00
## 6 2013-10-09 21:00:00 2013-01-01 21:00:00
## 7 2013-06-15 06:55:00 2013-01-01 06:55:00
## 8 2013-03-19 20:18:00 2013-01-01 20:18:00
## 9 2013-03-29 21:33:00 2013-01-01 21:33:00
## 10 2013-03-25 05:51:00 2013-01-01 05:51:00##time spans