7.9 Groupby

by_day <- group_by(flights,
                   year, month, day)

summarize(by_day, delay = mean(dep_delay, na.rm = TRUE))
## # A tibble: 365 x 4
## # Groups:   year, month [?]
##     year month   day delay
##    <int> <int> <int> <dbl>
##  1  2013     1     1 11.5 
##  2  2013     1     2 13.9 
##  3  2013     1     3 11.0 
##  4  2013     1     4  8.95
##  5  2013     1     5  5.73
##  6  2013     1     6  7.15
##  7  2013     1     7  5.42
##  8  2013     1     8  2.55
##  9  2013     1     9  2.28
## 10  2013     1    10  2.84
## # ... with 355 more rows

Do a group by and perform multiple summarizations

by_month <- group_by(flights,
                   year, month)
by_month <- summarize(by_month,
          delay = mean(dep_delay, na.rm = TRUE),
          delay_std = sd(dep_delay, na.rm = TRUE)
          )
by_month
## # A tibble: 12 x 4
## # Groups:   year [?]
##     year month delay delay_std
##    <int> <int> <dbl>     <dbl>
##  1  2013     1 10.0       36.4
##  2  2013     2 10.8       36.3
##  3  2013     3 13.2       40.1
##  4  2013     4 13.9       43.0
##  5  2013     5 13.0       39.4
##  6  2013     6 20.8       51.5
##  7  2013     7 21.7       51.6
##  8  2013     8 12.6       37.7
##  9  2013     9  6.72      35.6
## 10  2013    10  6.24      29.7
## 11  2013    11  5.44      27.6
## 12  2013    12 16.6       41.9

The above code can be re-written using the pipe, %>%

# i'm pretty sure this is easier to read and understand
by_month <- group_by(flights,
                     year, month) %>%
    summarize(delay = mean(dep_delay, na.rm = TRUE),
              delay_std = sd(dep_delay, na.rm = TRUE))
by_month
## # A tibble: 12 x 4
## # Groups:   year [?]
##     year month delay delay_std
##    <int> <int> <dbl>     <dbl>
##  1  2013     1 10.0       36.4
##  2  2013     2 10.8       36.3
##  3  2013     3 13.2       40.1
##  4  2013     4 13.9       43.0
##  5  2013     5 13.0       39.4
##  6  2013     6 20.8       51.5
##  7  2013     7 21.7       51.6
##  8  2013     8 12.6       37.7
##  9  2013     9  6.72      35.6
## 10  2013    10  6.24      29.7
## 11  2013    11  5.44      27.6
## 12  2013    12 16.6       41.9

Otherwise you will have to create a temp variable, or write a nested expression

summarize(group_by(flights, year, month),
          delay = mean(dep_delay, na.rm = TRUE),
          delay_std = sd(dep_delay, na.rm = TRUE))
## # A tibble: 12 x 4
## # Groups:   year [?]
##     year month delay delay_std
##    <int> <int> <dbl>     <dbl>
##  1  2013     1 10.0       36.4
##  2  2013     2 10.8       36.3
##  3  2013     3 13.2       40.1
##  4  2013     4 13.9       43.0
##  5  2013     5 13.0       39.4
##  6  2013     6 20.8       51.5
##  7  2013     7 21.7       51.6
##  8  2013     8 12.6       37.7
##  9  2013     9  6.72      35.6
## 10  2013    10  6.24      29.7
## 11  2013    11  5.44      27.6
## 12  2013    12 16.6       41.9