R tricks

case_when.r

> library(dplyr)

> cars %>% 
  as_tibble %>% 
  mutate(case_code = case_when(
                              speed == 4 & dist == 2 ~ "this",
                              dist > 6 & dist == 10 ~ "is",
                              speed >=10 & dist >= 18 ~ "awesome"))
                   
 # A tibble: 50 × 3
   speed  dist case_code
   <dbl> <dbl> <chr>    
 1     4     2 this     
 2     4    10 is       
 3     7     4 NA       
 4     7    22 NA       
 5     8    16 NA       
 6     9    10 is       
 7    10    18 awesome  
 8    10    26 awesome  
 9    10    34 awesome  
10    11    17 NA       
# … with 40 more rows

diff_lag_lead.r

# diff minus the previous number in sequence
> a<- c(1,2,5,7,9,14)
> diff(a)
[1] 1 3 2 2 5

## the long way
> a
[1]  1  2  5  7  9 14
> lag(a, 1)
[1] NA  1  2  5  7  9
> a - lag(a,1)
[1] NA  1  3  2  2  5

>lead(a,1)
[1]  2  5  7  9 14 NA

max_by_group.r

> library(dplyr)

# find the max horse power(hp) by cly(Number of cylinders) and gear group(Number of forward gears):
# use ?mtcars to find more information of this built-in dataset

> mtcars %>% group_by(cyl, gear) %>% top_n(n =1, wt = hp)
# A tibble: 10 × 11
# Groups:   cyl, gear [8]
     mpg   cyl  disp    hp  drat    wt  qsec    vs    am  gear  carb
   <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
 1  21.4     6 258     110  3.08  3.22  19.4     1     0     3     1
 2  14.3     8 360     245  3.21  3.57  15.8     0     0     3     4
 3  19.2     6 168.    123  3.92  3.44  18.3     1     0     4     4
 4  17.8     6 168.    123  3.92  3.44  18.9     1     0     4     4
 5  21.5     4 120.     97  3.7   2.46  20.0     1     0     3     1
 6  13.3     8 350     245  3.73  3.84  15.4     0     0     3     4
 7  30.4     4  95.1   113  3.77  1.51  16.9     1     1     5     2
 8  19.7     6 145     175  3.62  2.77  15.5     0     1     5     6
 9  15       8 301     335  3.54  3.57  14.6     0     1     5     8
10  21.4     4 121     109  4.11  2.78  18.6     1     1     4     2

> mtcars %>% group_by(cyl, gear) %>% slice(which.max(hp))
# A tibble: 8 × 11
# Groups:   cyl, gear [8]
    mpg   cyl  disp    hp  drat    wt  qsec    vs    am  gear  carb
  <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
1  21.5     4 120.     97  3.7   2.46  20.0     1     0     3     1
2  21.4     4 121     109  4.11  2.78  18.6     1     1     4     2
3  30.4     4  95.1   113  3.77  1.51  16.9     1     1     5     2
4  21.4     6 258     110  3.08  3.22  19.4     1     0     3     1
5  19.2     6 168.    123  3.92  3.44  18.3     1     0     4     4
6  19.7     6 145     175  3.62  2.77  15.5     0     1     5     6
7  14.3     8 360     245  3.21  3.57  15.8     0     0     3     4
8  15       8 301     335  3.54  3.57  14.6     0     1     5     8

> mtcars %>% group_by(cyl, gear) %>% filter(hp == max(hp))
# A tibble: 10 × 11
# Groups:   cyl, gear [8]
     mpg   cyl  disp    hp  drat    wt  qsec    vs    am  gear  carb
   <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
 1  21.4     6 258     110  3.08  3.22  19.4     1     0     3     1
 2  14.3     8 360     245  3.21  3.57  15.8     0     0     3     4
 3  19.2     6 168.    123  3.92  3.44  18.3     1     0     4     4
 4  17.8     6 168.    123  3.92  3.44  18.9     1     0     4     4
 5  21.5     4 120.     97  3.7   2.46  20.0     1     0     3     1
 6  13.3     8 350     245  3.73  3.84  15.4     0     0     3     4
 7  30.4     4  95.1   113  3.77  1.51  16.9     1     1     5     2
 8  19.7     6 145     175  3.62  2.77  15.5     0     1     5     6
 9  15       8 301     335  3.54  3.57  14.6     0     1     5     8
10  21.4     4 121     109  4.11  2.78  18.6     1     1     4     2

## note the order of the rows are different, but they return the same rows.