Piping Operator %>% in dplyr

pipingOperator.r

# %>% OPERATOR ----------------------------------------------------------------------

# with %>% operator
hflights %>% 
  mutate(diff = TaxiOut - TaxiIn) %>% 
  filter(!is.na(diff)) %>% 
  summarise(avg = mean(diff))

# without %>% operator
# arguments get further and further apart
summarize(filter(mutate(hflights, diff = TaxiOut - TaxiIn),!is.na(diff)),
          avg = mean(diff))


# with %>% operator
d <- hflights %>% 
  select(Dest, UniqueCarrier, Distance, ActualElapsedTime) %>% 
  mutate(RealTime = ActualElapsedTime + 100, mph = Distance/RealTime*60)

# without %>% operator
d <- mutate(select(hflights, Dest, UniqueCarrier, Distance, ActualElapsedTime),
       RealTime = ActualElapsedTime + 100, mph = Distance/RealTime*60)

# Filter and summarise d
d %>% 
  filter(!is.na(mph), mph < 70) %>% 
  summarise(n_less = n(), n_dest = n_distinct(Dest), 
            min_dist = min(Distance), max_dist = max(Distance))

# Let's define preferable flights as flights that are 150% faster than driving, 
# i.e. that travel 105 mph or greater in real time. Also, assume that cancelled or 
# diverted flights are less preferable than driving. 


# ADVANCED PIPING EXERCISES
# Use one single piped call to print a summary with the following variables:
  
# n_non - the number of non-preferable flights in hflights,
# p_non - the percentage of non-preferable flights in hflights,
# n_dest - the number of destinations that non-preferable flights traveled to,
# min_dist - the minimum distance that non-preferable flights traveled,
# max_dist - the maximum distance that non-preferable flights traveled

hflights %>% 
  mutate(RealTime = ActualElapsedTime + 100, mph = Distance/RealTime*60) %>%
  filter(mph < 105 | Cancelled == 1 | Diverted == 1) %>%
  summarise(n_non = n(), p_non = 100*n_non/nrow(hflights), n_dest = n_distinct(Dest),
            min_dist = min(Distance), max_dist = max(Distance))

# Use summarise() to create a summary of hflights with a single variable, n, 
# that counts the number of overnight flights. These flights have an arrival 
# time that is earlier than their departure time. Only include flights that have 
# no NA values for both DepTime and ArrTime in your count.

hflights %>%
  mutate(overnight = (ArrTime < DepTime)) %>%
  filter(overnight == TRUE) %>%
  summarise(n = n())