anirudhjayaraman

hflights[c('ActualElapsedTime','ArrDelay','DepDelay')]
# Equivalently, using dplyr:
select(hflights, ActualElapsedTime, ArrDelay, DepDelay)

# Print out a tbl with the four columns of hflights related to delay
select(hflights, ActualElapsedTime, AirTime, ArrDelay, DepDelay)

# Print out hflights, nothing has changed!
hflights

anirudhjayaraman

# Helper functions used with dplyr

# Print out a tbl containing just ArrDelay and DepDelay
select(hflights, ArrDelay, DepDelay)
# Use a combination of helper functions and variable names to print out 
# only the UniqueCarrier, FlightNum, TailNum, Cancelled, and CancellationCode 
# columns of hflights
select(hflights, UniqueCarrier, FlightNum, contains("Tail"), contains("Cancel"))

# Find the most concise way to return the following columns with select and its 

anirudhjayaraman

# Some comparisons to basic R
# both hflights and dplyr are available

ex1r <- hflights[c("TaxiIn","TaxiOut","Distance")]
ex1d <- select(hflights, TaxiIn, TaxiOut, Distance) 

ex2r <- hflights[c("Year","Month","DayOfWeek","DepTime","ArrTime")]
ex2d <- select(hflights, Year:ArrTime, -DayofMonth)

ex3r <- hflights[c("TailNum","TaxiIn","TaxiOut")]

anirudhjayaraman

# Add the new variable ActualGroundTime to a copy of hflights and save the result as g1.
g1 <- mutate(hflights, ActualGroundTime = ActualElapsedTime - AirTime)

# Add the new variable GroundTime to a g1. Save the result as g2.
g2 <- mutate(g1, GroundTime = TaxiIn + TaxiOut)

# Add the new variable AverageSpeed to g2. Save the result as g3.
g3 <- mutate(g2, AverageSpeed = Distance / AirTime * 60)

# Print out g3

anirudhjayaraman

# Add a second variable loss_percent to the dataset: m1
m1 <- mutate(hflights, loss = ArrDelay - DepDelay, loss_percent = ((ArrDelay - DepDelay)/DepDelay)*100)

# mutate() allows you to use a new variable while creating a next variable in the same call
# Copy and adapt the previous command to reduce redendancy: m2
m2 <- mutate(hflights, loss = ArrDelay - DepDelay, loss_percent = (loss/DepDelay) * 100 )

# Add the three variables as described in the third instruction: m3
m3 <- mutate(hflights, TotalTaxi = TaxiIn + TaxiOut, ActualGroundTime = ActualElapsedTime - AirTime, Diff = TotalTaxi - ActualGroundTime)

anirudhjayaraman

# Print out all flights in hflights that traveled 3000 or more miles
filter(hflights, Distance > 3000)

# All flights flown by one of JetBlue, Southwest, or Delta
filter(hflights, UniqueCarrier %in% c('JetBlue', 'Southwest', 'Delta'))

# All flights where taxiing took longer than flying
filter(hflights, TaxiIn + TaxiOut > AirTime)

anirudhjayaraman

# Combining tests using boolean operators

# All flights that departed before 5am or arrived after 10pm
filter(hflights, DepTime < 500 | ArrTime > 2200 )

# All flights that departed late but arrived ahead of schedule
filter(hflights, DepDelay > 0 & ArrDelay < 0)

# All cancelled weekend flights
filter(hflights, DayOfWeek %in% c(6,7) & Cancelled == 1)

anirudhjayaraman

# Summarizing Exercise
# Select the flights that had JFK as their destination: c1
c1 <- filter(hflights, Dest == 'JFK')

# Combine the Year, Month and DayofMonth variables to create a Date column: c2
c2 <- mutate(c1, Date = paste(Year, Month, DayofMonth, sep = "-"))

# Print out a selection of columns of c2
select(c2, Date, DepTime, ArrTime, TailNum)

anirudhjayaraman

# Definition of dtc
dtc <- filter(hflights, Cancelled == 1, !is.na(DepDelay))

# Arrange dtc by departure delays
arrange(dtc, DepDelay)

# Arrange dtc so that cancellation reasons are grouped
arrange(dtc, CancellationCode)

# Arrange dtc according to carrier and departure delays

anirudhjayaraman

# Print out a summary with variables min_dist and max_dist
summarize(hflights, min_dist = min(Distance), max_dist = max(Distance))

# Print out a summary with variable max_div
summarize(filter(hflights, Diverted == 1), max_div = max(Distance))

# Remove rows that have NA ArrDelay: temp1
temp1 <- filter(hflights, !is.na(ArrDelay))

# Generate summary about ArrDelay column of temp1