#Dplyr In Class Exercise Produce a screen shot for every answer so we can go over towards the end or just keep the naswer in the r script file #Follow the below steps

#first create a new R file in Rstudio #then install the below package install.packages("hflights") #then load the dplyr library library("dplyr") # convert to local data frame flights <- hflights # test the filter using the below filter(flights, Month==1, DayofMonth==1)

#Question 1 # filter flights dataset by uniquecarrier equal to 'AA' or flightnum equal to 460 and Arrdelay > 5 # use | for OR condition

#Question 2 # select flights dataset the following variables year,month,dayofmonth and any other column that CONTAINS # the 'Taxi' and 'Delay' using the contains function

#Question 3 # Using pipe method to select UniqueCarrier and DepDelay columns and then filter for delays over 60 minutes

#Question 4 #Using pipe method to select UniqueCarrier and DepDelay columns and then sort by DepDelay

#Question 5 # using pipe method select distance and airtime, create a new variable Speed(calculation of Distance divided by Airtime *60) # Also filter where Airtime is Null 'NA'

#Question 6 #using nesting and pipe and summarise for each carrier, calculate the percentage of flights cancelled or diverted