group_by_miscellaneous.R

# Combine group_by with mutate-----

# First, discard flights whose arrival delay equals NA. Next, create a by-carrier 
# summary with a single variable: p_delay, the proportion of flights which are 
# delayed at arrival. Next, create a new variable rank in the summary which is a 
# rank according to p_delay. Finally, arrange the observations by this new rank
hflights %>% 
  filter(!is.na(ArrDelay)) %>% 
  group_by(UniqueCarrier) %>% 
  summarise(p_delay = sum(ArrDelay >0)/n()) %>% 
  mutate(rank = rank(p_delay)) %>% 
  arrange(rank) 

# n a similar fashion, keep flights that are delayed (ArrDelay > 0 and not NA). 
# Next, create a by-carrier summary with a single variable: avg, the average delay 
# of the delayed flights. Again add a new variable rank to the summary according to 
# avg. Finally, arrange by this rank variable.
hflights %>% 
  filter(!is.na(ArrDelay), ArrDelay > 0) %>% 
  group_by(UniqueCarrier) %>% 
  summarise(avg = mean(ArrDelay)) %>% 
  mutate(rank = rank(avg)) %>% 
  arrange(rank)

# Advanced group_by exercises-------------------------------------------------------

# Which plane (by tail number) flew out of Houston the most times? How many times?
# Name the column with this frequency n. Assign the result to adv1. To answer this 
# question precisely, you will have to filter() as a final step to end up with only 
# a single observation in adv1.
# Which plane (by tail number) flew out of Houston the most times? How many times? adv1
adv1 <- hflights %>% 
  group_by(TailNum) %>% 
  summarise(n = n()) %>%
  filter(n == max(n))

# How many airplanes only flew to one destination from Houston? adv2
# How many airplanes only flew to one destination from Houston? 
# Save the resulting dataset in adv2, that contains only a single column, 
# named nplanes and a single row.
adv2 <- hflights %>%
  group_by(TailNum) %>%
  summarise(n_dest = n_distinct(Dest)) %>%
  filter(n_dest == 1) %>%
  summarise(nplanes = n())

# Find the most visited destination for each carrier and save your solution to adv3. 
# Your solution should contain four columns:
# UniqueCarrier and Dest,
# n, how often a carrier visited a particular destination,
# rank, how each destination ranks per carrier. rank should be 1 for every row, 
# as you want to find the most visited destination for each carrier.

adv3 <- hflights %>%
  group_by(UniqueCarrier, Dest) %>%
  summarise(n = n()) %>%
  mutate(rank = rank(desc(n))) %>%
  filter(rank == 1)

# Find the carrier that travels to each destination the most: adv4
# For each destination, find the carrier that travels to that destination the most. 
# Store the result in adv4. Again, your solution should contain 4 columns: 
# Dest, UniqueCarrier, n and rank.

adv4 <- hflights %>%
  group_by(Dest, UniqueCarrier) %>%
  summarise(n = n()) %>%
  mutate(rank = rank(desc(n))) %>%
  filter(rank == 1)