install.packages("pacman")
## Installing package into '/usr/local/lib/R/site-library'
## (as 'lib' is unspecified)
library(pacman)
p_load(nycflights13, tidyverse)
data(flights)
data(airlines)
data(weather)
data(airports)
head(flights)
## # A tibble: 6 x 19
## year month day dep_time sched_dep_time dep_delay arr_time sched_arr_time
## <int> <int> <int> <int> <int> <dbl> <int> <int>
## 1 2013 1 1 517 515 2 830 819
## 2 2013 1 1 533 529 4 850 830
## 3 2013 1 1 542 540 2 923 850
## 4 2013 1 1 544 545 -1 1004 1022
## 5 2013 1 1 554 600 -6 812 837
## 6 2013 1 1 554 558 -4 740 728
## # … with 11 more variables: 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>
head(airlines)
## # A tibble: 6 x 2
## carrier name
## <chr> <chr>
## 1 9E Endeavor Air Inc.
## 2 AA American Airlines Inc.
## 3 AS Alaska Airlines Inc.
## 4 B6 JetBlue Airways
## 5 DL Delta Air Lines Inc.
## 6 EV ExpressJet Airlines Inc.
head(weather)
## # A tibble: 6 x 15
## origin year month day hour temp dewp humid wind_dir wind_speed wind_gust
## <chr> <int> <int> <int> <int> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 EWR 2013 1 1 1 39.0 26.1 59.4 270 10.4 NA
## 2 EWR 2013 1 1 2 39.0 27.0 61.6 250 8.06 NA
## 3 EWR 2013 1 1 3 39.0 28.0 64.4 240 11.5 NA
## 4 EWR 2013 1 1 4 39.9 28.0 62.2 250 12.7 NA
## 5 EWR 2013 1 1 5 39.0 28.0 64.4 260 12.7 NA
## 6 EWR 2013 1 1 6 37.9 28.0 67.2 240 11.5 NA
## # … with 4 more variables: precip <dbl>, pressure <dbl>, visib <dbl>,
## # time_hour <dttm>
Q1<-filter(flights,month==1,day==1)
Q1
## # A tibble: 842 x 19
## year month day dep_time sched_dep_time dep_delay arr_time sched_arr_time
## <int> <int> <int> <int> <int> <dbl> <int> <int>
## 1 2013 1 1 517 515 2 830 819
## 2 2013 1 1 533 529 4 850 830
## 3 2013 1 1 542 540 2 923 850
## 4 2013 1 1 544 545 -1 1004 1022
## 5 2013 1 1 554 600 -6 812 837
## 6 2013 1 1 554 558 -4 740 728
## 7 2013 1 1 555 600 -5 913 854
## 8 2013 1 1 557 600 -3 709 723
## 9 2013 1 1 557 600 -3 838 846
## 10 2013 1 1 558 600 -2 753 745
## # … with 832 more rows, and 11 more variables: 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>
Q2<-filter(flights,arr_delay >= 120) %>%
select(year:day, arr_delay, everything())
Q2
## # A tibble: 10,200 x 19
## year month day arr_delay dep_time sched_dep_time dep_delay arr_time
## <int> <int> <int> <dbl> <int> <int> <dbl> <int>
## 1 2013 1 1 137 811 630 101 1047
## 2 2013 1 1 851 848 1835 853 1001
## 3 2013 1 1 123 957 733 144 1056
## 4 2013 1 1 145 1114 900 134 1447
## 5 2013 1 1 127 1505 1310 115 1638
## 6 2013 1 1 125 1525 1340 105 1831
## 7 2013 1 1 136 1549 1445 64 1912
## 8 2013 1 1 123 1558 1359 119 1718
## 9 2013 1 1 123 1732 1630 62 2028
## 10 2013 1 1 138 1803 1620 103 2008
## # … with 10,190 more rows, and 11 more variables: sched_arr_time <int>,
## # carrier <chr>, flight <int>, tailnum <chr>, origin <chr>, dest <chr>,
## # air_time <dbl>, distance <dbl>, hour <dbl>, minute <dbl>, time_hour <dttm>
Q3<-arrange(Q2,desc(arr_delay))%>%
select(year:day, carrier, flight,arr_delay, everything())%>%
slice(1)
Q3
## # A tibble: 1 x 19
## year month day carrier flight arr_delay dep_time sched_dep_time dep_delay
## <int> <int> <int> <chr> <int> <dbl> <int> <int> <dbl>
## 1 2013 1 9 HA 51 1272 641 900 1301
## # … with 10 more variables: arr_time <int>, sched_arr_time <int>,
## # tailnum <chr>, origin <chr>, dest <chr>, air_time <dbl>, distance <dbl>,
## # hour <dbl>, minute <dbl>, time_hour <dttm>
Q4<-group_by(flights,arr_delay)%>%
arrange(arr_delay)
Q4
## # A tibble: 336,776 x 19
## # Groups: arr_delay [578]
## year month day dep_time sched_dep_time dep_delay arr_time sched_arr_time
## <int> <int> <int> <int> <int> <dbl> <int> <int>
## 1 2013 5 7 1715 1729 -14 1944 2110
## 2 2013 5 20 719 735 -16 951 1110
## 3 2013 5 2 1947 1949 -2 2209 2324
## 4 2013 5 6 1826 1830 -4 2045 2200
## 5 2013 5 4 1816 1820 -4 2017 2131
## 6 2013 5 2 1926 1929 -3 2157 2310
## 7 2013 5 6 1753 1755 -2 2004 2115
## 8 2013 5 7 2054 2055 -1 2317 28
## 9 2013 5 13 657 700 -3 908 1019
## 10 2013 1 4 1026 1030 -4 1305 1415
## # … with 336,766 more rows, and 11 more variables: 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>
Q5<-group_by(flights,arr_delay)%>%
arrange(hour)
Q5
## # A tibble: 336,776 x 19
## # Groups: arr_delay [578]
## year month day dep_time sched_dep_time dep_delay arr_time sched_arr_time
## <int> <int> <int> <int> <int> <dbl> <int> <int>
## 1 2013 7 27 NA 106 NA NA 245
## 2 2013 1 1 517 515 2 830 819
## 3 2013 1 1 533 529 4 850 830
## 4 2013 1 1 542 540 2 923 850
## 5 2013 1 1 544 545 -1 1004 1022
## 6 2013 1 1 554 558 -4 740 728
## 7 2013 1 1 559 559 0 702 706
## 8 2013 1 2 458 500 -2 703 650
## 9 2013 1 2 512 515 -3 809 819
## 10 2013 1 2 535 540 -5 831 850
## # … with 336,766 more rows, and 11 more variables: 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>
answer06<-select(flights,year:day, hour, origin, dest, tailnum, carrier)%>%
slice(1:100)
answer06
## # A tibble: 100 x 8
## year month day hour origin dest tailnum carrier
## <int> <int> <int> <dbl> <chr> <chr> <chr> <chr>
## 1 2013 1 1 5 EWR IAH N14228 UA
## 2 2013 1 1 5 LGA IAH N24211 UA
## 3 2013 1 1 5 JFK MIA N619AA AA
## 4 2013 1 1 5 JFK BQN N804JB B6
## 5 2013 1 1 6 LGA ATL N668DN DL
## 6 2013 1 1 5 EWR ORD N39463 UA
## 7 2013 1 1 6 EWR FLL N516JB B6
## 8 2013 1 1 6 LGA IAD N829AS EV
## 9 2013 1 1 6 JFK MCO N593JB B6
## 10 2013 1 1 6 LGA ORD N3ALAA AA
## # … with 90 more rows