Project One

display the min, max, average flight time and average distance traveled of all UA airlines flights dept. from JFK in March 2013

library(dplyr)

## Warning: package 'dplyr' was built under R version 3.4.2

## 
## Attaching package: 'dplyr'

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

library(magrittr)
library(nycflights13)
library(tibble)

flights.tbl <- tbl_df(flights)
flights.tbl

## # A tibble: 336,776 x 19
##     year month   day dep_time sched_dep_time dep_delay arr_time
##    <int> <int> <int>    <int>          <int>     <dbl>    <int>
##  1  2013     1     1      517            515         2      830
##  2  2013     1     1      533            529         4      850
##  3  2013     1     1      542            540         2      923
##  4  2013     1     1      544            545        -1     1004
##  5  2013     1     1      554            600        -6      812
##  6  2013     1     1      554            558        -4      740
##  7  2013     1     1      555            600        -5      913
##  8  2013     1     1      557            600        -3      709
##  9  2013     1     1      557            600        -3      838
## 10  2013     1     1      558            600        -2      753
## # ... with 336,766 more rows, and 12 more variables: sched_arr_time <int>,
## #   arr_delay <dbl>, carrier <chr>, flight <int>, tailnum <chr>,
## #   origin <chr>, dest <chr>, air_time <dbl>, distance <dbl>, hour <dbl>,
## #   minute <dbl>, time_hour <dttm>

pulling out information needed

new.flights <- filter(flights.tbl, origin=="JFK", carrier== "UA", month==3)
new.flights

## # A tibble: 378 x 19
##     year month   day dep_time sched_dep_time dep_delay arr_time
##    <int> <int> <int>    <int>          <int>     <dbl>    <int>
##  1  2013     3     1      600            600         0      906
##  2  2013     3     1      607            610        -3      832
##  3  2013     3     1      655            700        -5      954
##  4  2013     3     1      758            800        -2     1106
##  5  2013     3     1      836            840        -4     1111
##  6  2013     3     1     1103           1106        -3     1400
##  7  2013     3     1     1125           1130        -5     1350
##  8  2013     3     1     1423           1425        -2     1728
##  9  2013     3     1     1621           1530        51     1844
## 10  2013     3     1     1723           1729        -6     2010
## # ... with 368 more rows, and 12 more variables: sched_arr_time <int>,
## #   arr_delay <dbl>, carrier <chr>, flight <int>, tailnum <chr>,
## #   origin <chr>, dest <chr>, air_time <dbl>, distance <dbl>, hour <dbl>,
## #   minute <dbl>, time_hour <dttm>

newer.flights <- select(new.flights, origin, carrier, month, air_time, distance)
newer.flights

## # A tibble: 378 x 5
##    origin carrier month air_time distance
##     <chr>   <chr> <int>    <dbl>    <dbl>
##  1    JFK      UA     3      342     2586
##  2    JFK      UA     3      292     2475
##  3    JFK      UA     3      343     2586
##  4    JFK      UA     3      342     2586
##  5    JFK      UA     3      301     2475
##  6    JFK      UA     3      338     2586
##  7    JFK      UA     3      307     2475
##  8    JFK      UA     3      337     2586
##  9    JFK      UA     3      300     2475
## 10    JFK      UA     3      320     2586
## # ... with 368 more rows

minimum flight time

min.air_time<- min(newer.flights$air_time, na.rm = TRUE)
min.air_time

## [1] 281

Maximum flight time

max.air_time <- max(newer.flights$air_time, na.rm = TRUE)
max.air_time

## [1] 394

Average flight time

mean.air_time <- mean(newer.flights$air_time, na.rm = TRUE)
round.mean <- round(mean.air_time, digits = 2)
round.mean

## [1] 342.93

Average distance traveled

mean.distance <- mean(newer.flights$distance, na.rm = TRUE)
mean.distance

## [1] 2534.317

round.mean.distance <- round(mean.distance, digits = 2)
round.mean.distance

## [1] 2534.32

Project 2

display the min, max, and average dept. delays in minutes for June grouped by airport

pulling out data

departure.delays <- filter(flights.tbl, dep_delay>0, month==6)
departure.delays

## # A tibble: 12,655 x 19
##     year month   day dep_time sched_dep_time dep_delay arr_time
##    <int> <int> <int>    <int>          <int>     <dbl>    <int>
##  1  2013     6     1        2           2359         3      341
##  2  2013     6     1      607            600         7      853
##  3  2013     6     1      614            605         9      844
##  4  2013     6     1      614            600        14      829
##  5  2013     6     1      615            610         5      837
##  6  2013     6     1      624            600        24      727
##  7  2013     6     1      632            630         2      738
##  8  2013     6     1      638            635         3      855
##  9  2013     6     1      638            630         8      741
## 10  2013     6     1      644            642         2      824
## # ... with 12,645 more rows, and 12 more variables: sched_arr_time <int>,
## #   arr_delay <dbl>, carrier <chr>, flight <int>, tailnum <chr>,
## #   origin <chr>, dest <chr>, air_time <dbl>, distance <dbl>, hour <dbl>,
## #   minute <dbl>, time_hour <dttm>

new.departure.delays <- select(departure.delays, month, dep_delay, origin)
new.departure.delays

## # A tibble: 12,655 x 3
##    month dep_delay origin
##    <int>     <dbl>  <chr>
##  1     6         3    JFK
##  2     6         7    EWR
##  3     6         9    EWR
##  4     6        14    EWR
##  5     6         5    JFK
##  6     6        24    EWR
##  7     6         2    EWR
##  8     6         3    JFK
##  9     6         8    EWR
## 10     6         2    EWR
## # ... with 12,645 more rows

newest.departure.delays <- new.departure.delays %>%
  arrange(origin)
newest.departure.delays

## # A tibble: 12,655 x 3
##    month dep_delay origin
##    <int>     <dbl>  <chr>
##  1     6         7    EWR
##  2     6         9    EWR
##  3     6        14    EWR
##  4     6        24    EWR
##  5     6         2    EWR
##  6     6         8    EWR
##  7     6         2    EWR
##  8     6        21    EWR
##  9     6        36    EWR
## 10     6         1    EWR
## # ... with 12,645 more rows

final table

summarise.newest.departure.delays <- newest.departure.delays %>%
  group_by(origin) %>%
  summarise(min.dep_delay=min(dep_delay), 
            max.dep_delay=max(dep_delay), 
            mean.dep_delay=mean(dep_delay))
summarise.newest.departure.delays

## # A tibble: 3 x 4
##   origin min.dep_delay max.dep_delay mean.dep_delay
##    <chr>         <dbl>         <dbl>          <dbl>
## 1    EWR             1           502       47.92212
## 2    JFK             1          1137       47.98522
## 3    LGA             1           803       54.96745

Project 3 Start

display the min, max, and average miles traveled per hour for UA, and AA flights flying between all 3 airports and ORD in June, July and August

pulling out the data needed

flights.mph <- select(flights.tbl, distance, air_time, dest, origin, month, carrier)
flights.mph

## # A tibble: 336,776 x 6
##    distance air_time  dest origin month carrier
##       <dbl>    <dbl> <chr>  <chr> <int>   <chr>
##  1     1400      227   IAH    EWR     1      UA
##  2     1416      227   IAH    LGA     1      UA
##  3     1089      160   MIA    JFK     1      AA
##  4     1576      183   BQN    JFK     1      B6
##  5      762      116   ATL    LGA     1      DL
##  6      719      150   ORD    EWR     1      UA
##  7     1065      158   FLL    EWR     1      B6
##  8      229       53   IAD    LGA     1      EV
##  9      944      140   MCO    JFK     1      B6
## 10      733      138   ORD    LGA     1      AA
## # ... with 336,766 more rows

new.flights.mph <- filter(flights.mph, month %in% c(6,7,8), carrier %in% c("AA", "UA"), dest=="ORD")
new.flights.mph

## # A tibble: 3,500 x 6
##    distance air_time  dest origin month carrier
##       <dbl>    <dbl> <chr>  <chr> <int>   <chr>
##  1      733      108   ORD    LGA     6      AA
##  2      733      109   ORD    LGA     6      UA
##  3      733      110   ORD    LGA     6      AA
##  4      719      108   ORD    EWR     6      UA
##  5      733      109   ORD    LGA     6      AA
##  6      733      108   ORD    LGA     6      UA
##  7      733      112   ORD    LGA     6      AA
##  8      733      105   ORD    LGA     6      AA
##  9      719      110   ORD    EWR     6      UA
## 10      733      109   ORD    LGA     6      AA
## # ... with 3,490 more rows

mutating

finding air time in hours

creating miles per hour (mph) column

newer.flights.mph <- new.flights.mph %>%
  select(air_time, distance) %>%
  mutate(hour=air_time/60) %>%
  mutate(mph=distance/hour)
newer.flights.mph

## # A tibble: 3,500 x 4
##    air_time distance     hour      mph
##       <dbl>    <dbl>    <dbl>    <dbl>
##  1      108      733 1.800000 407.2222
##  2      109      733 1.816667 403.4862
##  3      110      733 1.833333 399.8182
##  4      108      719 1.800000 399.4444
##  5      109      733 1.816667 403.4862
##  6      108      733 1.800000 407.2222
##  7      112      733 1.866667 392.6786
##  8      105      733 1.750000 418.8571
##  9      110      719 1.833333 392.1818
## 10      109      733 1.816667 403.4862
## # ... with 3,490 more rows

final table

summarise.newer.flights.mph <- newer.flights.mph %>%
  summarise(min.mph=min(mph, na.rm = TRUE),
            max.mph=max(mph, na.rm = TRUE),
            mean.mph=mean(mph, na.rm = TRUE))
summarise.newer.flights.mph

## # A tibble: 1 x 3
##    min.mph  max.mph mean.mph
##      <dbl>    <dbl>    <dbl>
## 1 231.4737 495.8621 396.5095

class6practice

Jennifer Walters

10/8/2017

Project One

display the min, max, average flight time and average distance traveled of all UA airlines flights dept. from JFK in March 2013

pulling out information needed

minimum flight time

Maximum flight time

Average flight time

Average distance traveled

Project 2

display the min, max, and average dept. delays in minutes for June grouped by airport

pulling out data

final table

Project 3 Start

display the min, max, and average miles traveled per hour for UA, and AA flights flying between all 3 airports and ORD in June, July and August

pulling out the data needed

mutating

finding air time in hours

creating miles per hour (mph) column

final table