Project 1 = Dislpay the minimum, maximum, and average flight time and average distance traveled of all United Airline flights departing JFK during March 2013.
First the variables in the dataset. Variables = airtime, carrier, month, orgin, and distance.
library(nycflights13)
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(tibble)
library(magrittr)
flights
## # 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>
jfkflight<- filter(select(flights,carrier, origin, distance, air_time, month ))
jfkflight
## # A tibble: 336,776 x 5
## carrier origin distance air_time month
## <chr> <chr> <dbl> <dbl> <int>
## 1 UA EWR 1400 227 1
## 2 UA LGA 1416 227 1
## 3 AA JFK 1089 160 1
## 4 B6 JFK 1576 183 1
## 5 DL LGA 762 116 1
## 6 UA EWR 719 150 1
## 7 B6 EWR 1065 158 1
## 8 EV LGA 229 53 1
## 9 B6 JFK 944 140 1
## 10 AA LGA 733 138 1
## # ... with 336,766 more rows
Next step is to use filter for UA flights out of JFK in March 2013.
Variables = month, origin, carrier.
filter(jfkflight, carrier=="UA" & origin=="JFK" & month==3)
## # A tibble: 378 x 5
## carrier origin distance air_time month
## <chr> <chr> <dbl> <dbl> <int>
## 1 UA JFK 2586 342 3
## 2 UA JFK 2475 292 3
## 3 UA JFK 2586 343 3
## 4 UA JFK 2586 342 3
## 5 UA JFK 2475 301 3
## 6 UA JFK 2586 338 3
## 7 UA JFK 2475 307 3
## 8 UA JFK 2586 337 3
## 9 UA JFK 2475 300 3
## 10 UA JFK 2586 320 3
## # ... with 368 more rows
Next step is to display the minimum, maximum, and average flight time and average distance traveled of all United Airline flights departing JFK during March 2013.
Variables = month, origin, carrier.
uaflight<- filter(jfkflight, carrier=="UA" & origin=="JFK" & month==3)
summarise(uaflight, min_airtime = min(na.rm = TRUE,air_time),
max_airtime = max(na.rm = TRUE,air_time),
avg_airtime = mean(na.rm = TRUE,air_time),
avg_distance = mean(distance))
## # A tibble: 1 x 4
## min_airtime max_airtime avg_airtime avg_distance
## <dbl> <dbl> <dbl> <dbl>
## 1 281 394 342.9253 2534.317
Project 2
Display the Minimum, maximum, and average departure delays in minutes for June 2013 grouped by airport.
flight_dely <-filter(select(flights, dep_delay, month, origin))
june_delay<-filter(flight_dely,dep_delay >0 & month==6)
june_delay%>% group_by(origin)%>%
summarise(min_delay= min(dep_delay, na.rm = TRUE),
max_delay= (max(dep_delay, na.rm = TRUE)),
avg_delay= (mean(dep_delay, na.rm = TRUE)))
## # A tibble: 3 x 4
## origin min_delay max_delay avg_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 Display the minimum, maximum, and average miles traveled per hour for United Airlines (UA) and American Airlines (AA) flights flying between all three airports and Chicago’s O ’Hare International Airport (ORD) in June, July, andAugust 2013.
fltr_dataset<-filter(select(flights,carrier, origin, air_time, month, dest, distance ))
final<- filter(fltr_dataset, carrier==c("UA","AA") & dest=="ORD" & month %in% c("6","7","8"))
mph<- mutate(final,mph= distance/(air_time/60))
summarise(mph, min_mph = min(na.rm = TRUE,mph),
max_mph = max(na.rm = TRUE,mph),
avg_mph = mean(na.rm = TRUE,mph))
## # A tibble: 1 x 3
## min_mph max_mph avg_mph
## <dbl> <dbl> <dbl>
## 1 231.4737 495.8621 396.5622