Manipulating Data

### Install packages
install.packages("tidyverse")
install.packages("nycflights13")
library(tidyverse)
library(nycflights13)

flights

# 1. Display all the flights from the first day of  2013

filter(flights, month==1,day==1)

# 2. Store the values from  (1) in a variable called jan1
jan1<-filter(flights, month==1,day==1)
jan1

#3. Show all the flights that departed after May
filter(flights, month>5)

#4. Show all the flights that occured in Nov or Dec
filter(flights, month==11 | month==12)

#alternatively

filter(flights,month %in% c(11,12))

### Exercise
##Find Flights that:
# a. Had an arrival delay of two or more hours
filter(flights, arr_delay >= 120)

# b. Flew to Houston (IAH or HOU)
filter(flights, dest == "IAH" | dest == "HOU")

# c. Were operated by United, American, or Delta
filter(flights, dest %in% c("IAH", "HOU"))

# d. Departed in summer (July, August, and September)
filter(flights, month >= 7, month <= 9)

filter(flights, month %in% 7:9)

filter(flights, month == 7 | month == 8 | month == 9)

# e. Arrived more than two hours late, but didn’t leave late
filter(flights, arr_delay > 120, dep_delay <= 0)

# f. Were delayed by at least an hour, but made up over 30 minutes inflight
filter(flights, dep_delay >= 60, dep_delay - arr_delay > 30)

NA
NA
NA

#show all the flights and organize them by year, month and day.
arrange(flights, year, month, day)

# Sort the flights in decending order by arr_delay
arrange(flights,desc(arr_delay))

# Show the flight year month and day

select(flights, year, month, day)

#Show all the columns between year and day (inclusive) 
select(flights,year:day)

#Show all columns except those from year to day (inclusive)
select(flights,-(year:day))

#show the gain(i.e. arrival delay - departure delay) and speed of  planes together with the colums between year and day, distance and airtime as well as those that end with the words "delay"

select(flights, year:day, ends_with("delay"),distance,air_time)%>%
  mutate(gain=arr_delay-dep_delay, speed=distance/air_time*60)

# Create 3 new variables that show the gain, hours the plane was in the air and gain per hour. Only display these three variables

transmute(flights, gain=arr_delay-dep_delay, hours=air_time/60, gain_per_hour=gain/hours)

# What was the average flight delay time?

summarize(flights, delay=mean(dep_delay, na.rm=TRUE))

#What is the average delay by month?
group_by(flights,year, month)%>%
  summarize(delay=mean(dep_delay, na.rm=TRUE))

`summarise()` has grouped output by 'year'. You can override using the `.groups` argument.