Test-3
Jiayi Li
4 October, 2021
Part One
Task 1
Dataset 1: tornado.csv
Read csv file
csvData <- read.csv(file = "http://latul.be/mbaa_531/data/tornado.csv", header = TRUE)Show the first SIX rows of tornado.csv file
head (csvData)## yr mo dy date time tz st stf stn f
## 1 2007 1 4 2007-01-04 15:45:00 3 LA 22 1 EF-1
## 2 2007 1 4 2007-01-04 16:35:00 3 LA 22 2 EF-1
## 3 2007 1 5 2007-01-05 00:27:00 3 MS 28 1 EF-1
## 4 2007 1 5 2007-01-05 00:40:00 3 MS 28 2 EF-0
## 5 2007 1 5 2007-01-05 00:57:00 3 MS 28 3 EF-1
## 6 2007 1 5 2007-01-05 01:07:00 3 MS 28 4 EF-1Data manipulation
- Calculate the times of tornadoes occurred in Washington or Mississippi.
sum (csvData$st == "WA" | csvData$st == "MS")## [1] 530- Calculate the times of tornadoes occurred in Washington after 2012.
sum (csvData$st == "WA" & csvData$yr > 2012)## [1] 7- Display data of tornadoes occurred in Washington in 2012, 2013, and 2014.
index <- csvData$st == "WA" & csvData$yr %in% 2012:2014
csvData[ index, ]## yr mo dy date time tz st stf stn f
## 8217 2013 3 21 2013-03-21 18:00:00 3 WA 53 0 EF-0
## 8851 2013 9 30 2013-09-30 08:20:00 3 WA 53 0 EF-1
## 9150 2014 4 27 2014-04-27 18:30:00 3 WA 53 0 EF-0
## 9747 2014 8 13 2014-08-13 19:30:00 3 WA 53 0 EF-0
## 9884 2014 10 23 2014-10-23 14:40:00 3 WA 53 0 EF-1- Return data of tornadoes in Hawaii by month, year, F-scale.
index<- csvData$st == "HI"
csvData[ index, c(2, 1, 10)] ## mo yr f
## 2766 9 2008 EF-0
## 2842 12 2008 EF-0
## 2878 2 2009 EF-0
## 5371 2 2011 EF-0
## 7359 3 2012 EF-0
## 10093 4 2015 EF-0- List the tornadoes by date and time.
orderdate <- order( csvData$date)
tail(csvData[orderdate,])## yr mo dy date time tz st stf stn f
## 11136 2015 12 28 2015-12-28 02:53:00 3 LA 22 0 EF-1
## 11137 2015 12 28 2015-12-28 03:20:00 3 LA 22 0 EF-1
## 11138 2015 12 28 2015-12-28 04:46:00 3 AR 5 0 EF-2
## 11139 2015 12 28 2015-12-28 05:43:00 3 MS 28 0 EF-1
## 11140 2015 12 28 2015-12-28 08:30:00 3 FL 12 0 EF-1
## 11141 2015 12 28 2015-12-28 15:58:00 3 NC 37 0 EF-0According to the data, the latest tornado occured in NC (North Carolina).
- Calculate the numbers of tornadoes by months.
table(csvData$mo)##
## 1 2 3 4 5 6 7 8 9 10 11 12
## 355 463 751 2171 2500 1899 861 517 401 525 350 348Part Two
Task 2
Dataset 2: airline.csv
Read csv file
airlineData <- read.csv(file = "http://latul.be/mbaa_531/data/airline.csv", header = TRUE)Show the first SIX rows of airline.csv file
head (airlineData)## Year Month DayofMonth DayOfWeek DepTime CRSDepTime ArrTime CRSArrTime
## 1 2004 3 25 4 1118 1125 1231 1236
## 2 2004 3 25 4 810 815 1016 1033
## 3 2004 3 25 4 1529 1530 2101 2104
## 4 2004 3 25 4 1119 1125 1423 1441
## 5 2004 3 25 4 1156 1155 1452 1444
## 6 2004 3 25 4 903 905 1047 1054
## UniqueCarrier FlightNum TailNum ActualElapsedTime CRSElapsedTime AirTime
## 1 UA 425 N840UA 73 71 54
## 2 UA 425 N840UA 246 258 211
## 3 UA 426 N335UA 212 214 191
## 4 UA 426 N335UA 124 136 111
## 5 UA 427 N567UA 236 229 199
## 6 UA 427 N567UA 164 169 143
## ArrDelay DepDelay Origin Dest Distance TaxiIn TaxiOut Cancelled
## 1 -5 -7 DEN ABQ 349 3 16 0
## 2 -17 -5 PHL DEN 1557 5 30 0
## 3 -3 -1 DEN EWR 1605 7 14 0
## 4 -18 -6 SAN DEN 853 4 9 0
## 5 8 1 ORD PHX 1440 7 30 0
## 6 -7 -2 TPA ORD 1012 5 16 0
## CancellationCode Diverted CarrierDelay WeatherDelay NASDelay SecurityDelay
## 1 0 0 0 0 0
## 2 0 0 0 0 0
## 3 0 0 0 0 0
## 4 0 0 0 0 0
## 5 0 0 0 0 0
## 6 0 0 0 0 0
## LateAircraftDelay
## 1 0
## 2 0
## 3 0
## 4 0
## 5 0
## 6 0Data manipulation
a.Subset
i.Select the variables that meet the conditions: Departed (DepTime) after 10pm and flew (Dest) to Nashville (’BNA’).
select1 <- subset(airlineData, airlineData$DepTime > 2200 & airlineData$Dest == "BNA", select = c(9, 10, 17))
head(select1)## UniqueCarrier FlightNum Origin
## 7021 OH 5421 CVG
## 17401 AA 2435 ORD
## 19478 DH 7332 ORDThere are 3 observers satisfy the conditions.
ii.Select the variables that meet the conditions: Departed (DepTime) after 10pm, but Originated (Origin) from Nashville ’BNA’ or landed (Dest) in Memphis ’MEM’.
select2 <- subset(airlineData, airlineData$DepTime > 2200 & c(airlineData$Origin == "BNA" | airlineData$Dest == "MEM"), select = c(9, 10,17))
head(select2)## UniqueCarrier FlightNum Origin
## 2392 WN 1447 BNA
## 8169 OO 6838 ORD
## 10405 DL 579 ATL
## 19352 DH 6270 CVGThere are 4 observers satisfy the conditions.
- Select the variables that meet the conditions: Delayed (ArrDelay) by more two hours.
select3 <- subset(airlineData, airlineData$ArrDelay > 120, select = c(9, 10, 17))
print(select3)## UniqueCarrier FlightNum Origin
## 27 UA 441 ORD
## 65 UA 471 BUF
## 66 UA 471 ORD
## 78 UA 481 ORD
## 86 UA 489 CMH
## 126 UA 518 ORD
## 149 UA 538 ORD
## 154 UA 542 ORD
## 155 UA 543 BOS
## 158 UA 544 SNA
## 165 UA 548 SLC
## 175 UA 558 RNO
## 265 UA 626 ORD
## 268 UA 628 ORD
## 269 UA 628 SMF
## 297 UA 661 ORD
## 298 UA 663 EWR
## 324 UA 685 ORD
## 327 UA 687 LGA
## 358 UA 712 ORD
## 377 UA 727 ATL
## 388 UA 735 ORD
## 403 UA 750 ORD
## 404 UA 750 STL
## 463 UA 802 MSP
## 464 UA 802 ORD
## 480 UA 828 MSP
## 490 UA 843 CMH
## 509 UA 866 SAT
## 574 UA 940 MSP
## 601 UA 973 PIT
## 642 UA 1023 ORD
## 678 UA 1069 ORD
## 693 UA 1080 SJC
## 699 UA 1085 GSO
## 700 UA 1085 ORD
## 859 UA 1202 MSP
## 870 UA 1211 ROC
## 876 UA 1216 OAK
## 900 UA 1234 ORD
## 909 UA 1241 FLL
## 939 UA 1265 MSP
## 949 UA 1273 SFO
## 960 UA 1283 DEN
## 974 UA 1292 STL
## 1768 US 270 PIT
## 2078 US 1194 ORD
## 3365 WN 289 LAS
## 3442 WN 1206 LAX
## 3968 WN 2311 OAK
## 4004 WN 531 OAK
## 4426 WN 289 RNO
## 4440 WN 2676 RNO
## 4444 WN 2162 RNO
## 4446 WN 2311 RNO
## 4784 WN 1206 SMF
## 5030 NW 625 MSP
## 5207 NW 844 MSP
## 5368 NW 1071 BWI
## 5858 NW 1785 DTW
## 5884 NW 1816 MDW
## 5980 NW 1923 DTW
## 7507 OO 6041 LAX
## 7896 OO 6406 EUG
## 7945 OO 6461 SLC
## 8161 OO 6816 FWA
## 8162 OO 6822 ORD
## 8167 OO 6836 MEM
## 8169 OO 6838 ORD
## 8174 OO 6847 ROA
## 8175 OO 6848 ORD
## 8179 OO 6861 LNK
## 8181 OO 6865 ORD
## 8326 XE 3308 CVG
## 8333 XE 2425 EWR
## 8628 XE 2243 ORD
## 8637 XE 3358 CLE
## 9215 XE 3371 CLE
## 9245 XE 2302 CLE
## 9381 TZ 202 MDW
## 9425 TZ 267 MDW
## 9495 TZ 505 PIE
## 9508 TZ 591 RSW
## 9511 TZ 598 MDW
## 9534 TZ 675 MDW
## 9631 UA 65 SFO
## 9708 UA 150 SFO
## 9761 UA 212 SFO
## 9768 UA 220 SNA
## 9861 UA 314 SAN
## 9887 UA 336 PDX
## 9923 UA 358 ORD
## 9973 UA 392 ORD
## 10538 DL 728 ATL
## 10817 DL 1055 DFW
## 11220 DL 1603 MSP
## 11344 DL 1726 SAN
## 11416 DL 1802 SLC
## 11760 DL 2228 ATL
## 11872 DL 2530 MCO
## 12189 EV 4332 PNS
## 12995 FL 853 MSP
## 13351 HP 726 LAS
## 13360 HP 315 LAS
## 13452 HP 202 ONT
## 14338 MQ 3912 FSD
## 14348 MQ 3922 LNK
## 14391 MQ 3965 PIA
## 14401 MQ 3982 ICT
## 14404 MQ 3987 ORD
## 14406 MQ 3989 ORD
## 14407 MQ 3990 MSP
## 14413 MQ 4001 ORD
## 14428 MQ 4018 ORD
## 14433 MQ 4023 ORD
## 14455 MQ 4049 ORD
## 14475 MQ 4072 ORD
## 14480 MQ 4077 ORD
## 14482 MQ 4079 ORD
## 14493 MQ 4090 ORD
## 14496 MQ 4093 ORD
## 14499 MQ 4099 ORD
## 14531 MQ 4135 MSN
## 14552 MQ 4161 ORD
## 14554 MQ 4163 ORD
## 14562 MQ 4171 ORD
## 14565 MQ 4174 OMA
## 14569 MQ 4178 RIC
## 14580 MQ 4194 GRR
## 14621 MQ 4240 DSM
## 14623 MQ 4242 MSN
## 14647 MQ 4267 ORD
## 14651 MQ 4271 ORD
## 14659 MQ 4280 FWA
## 14676 MQ 4299 ORD
## 14681 MQ 4306 CVG
## 14685 MQ 4311 ORD
## 14696 MQ 4323 OKC
## 14700 MQ 4327 ORD
## 14716 MQ 4346 CMH
## 14719 MQ 4349 ORD
## 14735 MQ 4369 ORD
## 14746 MQ 4379 ORD
## 14747 MQ 4380 CVG
## 14751 MQ 4384 SDF
## 14757 MQ 4392 HSV
## 14771 MQ 4409 DSM
## 14772 MQ 4422 ORD
## 15116 NW 140 MSP
## 15132 NW 180 LAX
## 15184 NW 243 DTW
## 15309 NW 405 MSP
## 15691 AA 345 LGA
## 15819 AA 485 ORD
## 15833 AA 503 DTW
## 15834 AA 503 ORD
## 15848 AA 516 TUS
## 15852 AA 520 DEN
## 15871 AA 538 ORD
## 15872 AA 538 RNO
## 15889 AA 557 RDU
## 15907 AA 576 LAX
## 15931 AA 600 ORD
## 15933 AA 602 ORD
## 15940 AA 608 ORD
## 15943 AA 611 ORD
## 15946 AA 614 SEA
## 15971 AA 650 PHX
## 16044 AA 734 STL
## 16070 AA 772 MSP
## 16071 AA 772 ORD
## 16080 AA 787 MIA
## 16091 AA 801 FLL
## 16095 AA 806 SAN
## 16101 AA 818 ORD
## 16102 AA 818 SJC
## 16122 AA 844 ORD
## 16125 AA 849 MIA
## 16135 AA 860 MSY
## 16136 AA 860 ORD
## 16143 AA 873 ORD
## 16157 AA 892 ORD
## 16220 AA 1035 MCO
## 16265 AA 1081 ORD
## 16298 AA 1114 CLE
## 16365 AA 1178 DFW
## 16396 AA 1207 PVD
## 16402 AA 1212 IAH
## 16427 AA 1235 ORD
## 16458 AA 1263 ORD
## 16524 AA 1328 AUS
## 16542 AA 1344 ORD
## 16597 AA 1405 ORD
## 16627 AA 1432 MSY
## 16679 AA 1484 MCI
## 16728 AA 1530 XNA
## 16745 AA 1546 IAH
## 16746 AA 1546 ORD
## 16800 AA 1603 ORD
## 16809 AA 1612 LAX
## 16827 AA 1631 BOS
## 16847 AA 1652 ORD
## 16857 AA 1665 ORD
## 16882 AA 1692 SAT
## 16913 AA 1721 ORD
## 16926 AA 1733 EWR
## 16927 AA 1733 ORD
## 16946 AA 1754 TUL
## 17008 AA 1814 STL
## 17024 AA 1828 ORD
## 17045 AA 1852 ORD
## 17057 AA 1864 PHX
## 17058 AA 1864 STL
## 17083 AA 1891 ORD
## 17127 AA 1935 BWI
## 17135 AA 1941 EWR
## 17186 AA 1988 IAH
## 17187 AA 1988 ORD
## 17274 AA 2088 SNA
## 17278 AA 2093 STL
## 17315 AA 2252 JAC
## 17338 AA 2318 HDN
## 17360 AA 2353 ORD
## 17362 AA 2357 ORD
## 17363 AA 2360 DFW
## 17366 AA 2364 DFW
## 17368 AA 2368 DFW
## 17861 AS 526 SEA
## 17941 AS 680 RNO
## 18376 CO 246 IAH
## 18395 CO 1187 EWR
## 18415 CO 391 IAH
## 18534 CO 346 IAH
## 18672 CO 1185 EWR
## 18769 CO 1194 ORD
## 18986 CO 1647 ORD
## 19289 DH 6206 CVG
## 19299 DH 6213 CVG
## 19306 DH 6218 CVG
## 19352 DH 6270 CVG
## 19359 DH 6276 CVG
## 19385 DH 7228 FAR
## 19394 DH 7239 BOS
## 19413 DH 7260 IAD
## 19474 DH 7328 GSP
## 19478 DH 7332 ORD
## 19482 DH 7337 GRR
## 19493 DH 7348 ORD
## 19528 DH 7383 BNA
## 19543 DH 7400 TUL
## 19558 DH 7416 SBN
## 19562 DH 7421 ORD
## 19567 DH 7426 ORD
## 19568 DH 7427 JAX
## 19603 DH 7462 ORD
## 19609 DH 7468 ORD
## 19616 DH 7475 CAE
## 19627 DH 7486 ORD
## 19628 DH 7487 CHS
## 19632 DH 7491 BHM
## 19639 DH 7498 CLE
## 19646 DH 7506 MBS
## 19653 DH 7514 ORD
## 19655 DH 7516 GRR
## 19672 DH 7535 ORD
## 19678 DH 7545 CAK
## 19680 DH 7547 ABE
## 19683 DH 7556 ORD
## 19691 DH 7575 SYR
## 19697 DH 7587 SAV
## 19716 DH 7614 ORD
## 19718 DH 7617 HPN
## 19729 DH 7629 PWM
## 19753 DH 7696 ORD
## 19774 DH 7728 ICT
## 19775 DH 7729 ORD
## 19791 DH 7748 OKC
## 19807 DH 7766 TUL
## 19820 DH 7781 HPN
## 19845 DH 7807 ORDThere are 280 observers satisfy the conditions.
- Select the variables that meet the conditions: Arrived (ArrDelay) more than two hours late, but didn’t leave late (DepDelay).
select4 <- subset(airlineData, airlineData$ArrDelay > 120 & airlineData$DepDelay <= 0, select = c(9, 10, 17))
head(select4)## UniqueCarrier FlightNum Origin
## 9495 TZ 505 PIEThere is only 1 observer satisfies the conditions.
b.Arrange
- Sort flights to find the 5 most delayed (DepDelay) flights.
order1 <- order(-airlineData$DepDelay)
airlineData <- airlineData[order1, ]
head(airlineData[order1,], 5)## Year Month DayofMonth DayOfWeek DepTime CRSDepTime ArrTime CRSArrTime
## 18145 2004 3 25 4 1511 1510 1814 1805
## 1304 2004 3 25 4 658 700 852 918
## 14197 2004 3 25 4 546 550 701 739
## 1851 2004 3 25 4 1755 1800 1850 1849
## 18682 2004 3 25 4 1858 1903 2029 2000
## UniqueCarrier FlightNum TailNum ActualElapsedTime CRSElapsedTime AirTime
## 18145 B6 434 N564JB 183 175 152
## 1304 US 799 N724UW 114 138 101
## 14197 MQ 3640 N839MQ 135 169 121
## 1851 US 294 N779AU 55 49 38
## 18682 CO 740 N37252 91 57 50
## ArrDelay DepDelay Origin Dest Distance TaxiIn TaxiOut Cancelled
## 18145 9 1 MCO BOS 1121 15 16 0
## 1304 -26 -2 MHT CLT 737 2 11 0
## 14197 -38 -4 GSP DFW 862 5 9 0
## 1851 1 -5 BWI PHL 90 4 13 0
## 18682 29 -5 AUS IAH 140 11 30 0
## CancellationCode Diverted CarrierDelay WeatherDelay NASDelay
## 18145 0 0 0 0
## 1304 0 0 0 0
## 14197 0 0 0 0
## 1851 0 0 0 0
## 18682 0 0 0 29
## SecurityDelay LateAircraftDelay
## 18145 0 0
## 1304 0 0
## 14197 0 0
## 1851 0 0
## 18682 0 0ii.Sort flights to find the 5 least delayed (DepDelay) flights
order2 <- order(airlineData$DepDelay)
airlineData <- airlineData[order2, ]
head(airlineData[order2,], 5)## Year Month DayofMonth DayOfWeek DepTime CRSDepTime ArrTime CRSArrTime
## 5884 2004 3 25 4 745 1345 954 1607
## 11220 2004 3 25 4 2031 1507 2319 1759
## 14475 2004 3 25 4 2005 1501 2230 1717
## 15132 2004 3 25 4 1807 1306 2336 1830
## 4444 2004 3 25 4 2147 1745 2252 1835
## UniqueCarrier FlightNum TailNum ActualElapsedTime CRSElapsedTime AirTime
## 5884 NW 1816 N608NW 69 82 48
## 11220 DL 1603 N978DL 108 112 82
## 14475 MQ 4072 N514MQ 145 136 93
## 15132 NW 180 N352NW 209 204 188
## 4444 WN 2162 N341 65 50 48
## ArrDelay DepDelay Origin Dest Distance TaxiIn TaxiOut Cancelled
## 5884 1067 1080 MDW DTW 229 10 11 0
## 11220 320 324 MSP CVG 596 7 19 0
## 14475 313 304 ORD OKC 693 6 46 0
## 15132 306 301 LAX MEM 1619 7 14 0
## 4444 257 242 RNO OAK 180 2 15 0
## CancellationCode Diverted CarrierDelay WeatherDelay NASDelay
## 5884 0 1067 0 0
## 11220 0 0 0 0
## 14475 0 254 0 9
## 15132 0 301 0 5
## 4444 0 10 0 15
## SecurityDelay LateAircraftDelay
## 5884 0 0
## 11220 0 320
## 14475 0 50
## 15132 0 0
## 4444 0 232iii.Sort flights by destination (Dest) and break ties by descending arrival delay (ArrDelay).
order3 <- order(airlineData$Dest, -airlineData$ArrDelay)
airlineData <- airlineData[order3, ]
head(airlineData[order3, ])## Year Month DayofMonth DayOfWeek DepTime CRSDepTime ArrTime CRSArrTime
## 5597 2004 3 25 4 715 720 847 858
## 12622 2004 3 25 4 1212 1200 1344 1325
## 3861 2004 3 25 4 1045 1045 1150 1145
## 13095 2004 3 25 4 1534 1535 2256 2250
## 18959 2004 3 25 4 639 645 818 820
## 17064 2004 3 25 4 1141 1148 1441 1409
## UniqueCarrier FlightNum TailNum ActualElapsedTime CRSElapsedTime AirTime
## 5597 NW 1457 N754NW 92 98 68
## 12622 EV 4910 N712EV 212 205 171
## 3861 WN 694 N362 65 60 49
## 13095 HA 30 N589HA 322 315 430
## 18959 CO 1087 N57857 159 155 133
## 17064 AA 1870 N290AA 180 141 140
## ArrDelay DepDelay Origin Dest Distance TaxiIn TaxiOut Cancelled
## 5597 -11 -5 MSP STL 449 6 18 0
## 12622 19 12 DFW SNA 1205 15 26 0
## 3861 5 0 MSY BHM 321 3 13 0
## 13095 6 -1 OGG SEA 2640 4 8 0
## 18959 -2 -6 MCO IAH 853 12 14 0
## 17064 32 -7 MSY ORD 837 10 30 0
## CancellationCode Diverted CarrierDelay WeatherDelay NASDelay
## 5597 0 0 0 0
## 12622 0 12 0 7
## 3861 0 0 0 0
## 13095 0 0 0 0
## 18959 0 0 0 0
## 17064 0 0 0 32
## SecurityDelay LateAircraftDelay
## 5597 0 0
## 12622 0 0
## 3861 0 0
## 13095 0 0
## 18959 0 0
## 17064 0 0Part Three
Bonus Task
Dataset : airline.csv
Read csv file
airlineBonus <- read.csv(file = "http://latul.be/mbaa_531/data/airline.csv", header = TRUE)Show the first SIX rows of airline.csv file
head (airlineBonus)## Year Month DayofMonth DayOfWeek DepTime CRSDepTime ArrTime CRSArrTime
## 1 2004 3 25 4 1118 1125 1231 1236
## 2 2004 3 25 4 810 815 1016 1033
## 3 2004 3 25 4 1529 1530 2101 2104
## 4 2004 3 25 4 1119 1125 1423 1441
## 5 2004 3 25 4 1156 1155 1452 1444
## 6 2004 3 25 4 903 905 1047 1054
## UniqueCarrier FlightNum TailNum ActualElapsedTime CRSElapsedTime AirTime
## 1 UA 425 N840UA 73 71 54
## 2 UA 425 N840UA 246 258 211
## 3 UA 426 N335UA 212 214 191
## 4 UA 426 N335UA 124 136 111
## 5 UA 427 N567UA 236 229 199
## 6 UA 427 N567UA 164 169 143
## ArrDelay DepDelay Origin Dest Distance TaxiIn TaxiOut Cancelled
## 1 -5 -7 DEN ABQ 349 3 16 0
## 2 -17 -5 PHL DEN 1557 5 30 0
## 3 -3 -1 DEN EWR 1605 7 14 0
## 4 -18 -6 SAN DEN 853 4 9 0
## 5 8 1 ORD PHX 1440 7 30 0
## 6 -7 -2 TPA ORD 1012 5 16 0
## CancellationCode Diverted CarrierDelay WeatherDelay NASDelay SecurityDelay
## 1 0 0 0 0 0
## 2 0 0 0 0 0
## 3 0 0 0 0 0
## 4 0 0 0 0 0
## 5 0 0 0 0 0
## 6 0 0 0 0 0
## LateAircraftDelay
## 1 0
## 2 0
## 3 0
## 4 0
## 5 0
## 6 0Data manipulation
1.Transform using the Airline data: create a new data frame with only the columns ’DepDelay’, ’ArrDelay’, ’Origin’, ’Dest’, AirTime’, and ’Distance’. In addition keep only the observation for flights that were delayed (DepDelay) by more than 1 hour.
Bonus <- data.frame(airlineBonus[ airlineBonus$DepDelay > 60, c(16, 15, 17, 18, 14, 19)])
write.csv(Bonus, file = "Bonus.csv")
head(Bonus)## DepDelay ArrDelay Origin Dest AirTime Distance
## 8 112 102 DEN SNA 116 846
## 23 65 78 ORD ROC 72 528
## 44 73 72 IAH ORD 139 925
## 65 164 144 BUF ORD 79 473
## 66 130 138 ORD MSP 57 334
## 78 122 144 ORD SAN 238 1723- Add a new column reporting departure delays minus the mean departure delay to the new data frame.
First calculate mean of DepDelay
result.mean <- mean(Bonus$DepDelay, na.rm = TRUE)
print(result.mean)## [1] 105.9261Then display the variable meets the conditions.
Bonus$DepDelayMean <- Bonus$DepDelay- mean(Bonus$DepDelay, na.rm = TRUE)
options(digits = 2)
head(Bonus)## DepDelay ArrDelay Origin Dest AirTime Distance DepDelayMean
## 8 112 102 DEN SNA 116 846 6.1
## 23 65 78 ORD ROC 72 528 -40.9
## 44 73 72 IAH ORD 139 925 -32.9
## 65 164 144 BUF ORD 79 473 58.1
## 66 130 138 ORD MSP 57 334 24.1
## 78 122 144 ORD SAN 238 1723 16.1- Convert the departure and arrival delays columns from minutes into hours.
Bonus$DepDelay <- Bonus$DepDelay / 60
Bonus$ArrDelay <- Bonus$ArrDelay / 60
options(digits = 2)
head(Bonus)## DepDelay ArrDelay Origin Dest AirTime Distance DepDelayMean
## 8 1.9 1.7 DEN SNA 116 846 6.1
## 23 1.1 1.3 ORD ROC 72 528 -40.9
## 44 1.2 1.2 IAH ORD 139 925 -32.9
## 65 2.7 2.4 BUF ORD 79 473 58.1
## 66 2.2 2.3 ORD MSP 57 334 24.1
## 78 2.0 2.4 ORD SAN 238 1723 16.1- Add a column with the average flight speed (in mph).
Bonus$AirTime <- Bonus$AirTime / 60
Bonus$AveSpeed <- Bonus$Distance / Bonus$AirTime
head(Bonus)## DepDelay ArrDelay Origin Dest AirTime Distance DepDelayMean AveSpeed
## 8 1.9 1.7 DEN SNA 1.93 846 6.1 438
## 23 1.1 1.3 ORD ROC 1.20 528 -40.9 440
## 44 1.2 1.2 IAH ORD 2.32 925 -32.9 399
## 65 2.7 2.4 BUF ORD 1.32 473 58.1 359
## 66 2.2 2.3 ORD MSP 0.95 334 24.1 352
## 78 2.0 2.4 ORD SAN 3.97 1723 16.1 434- Report your new table using the function summary().
summary(Bonus)## DepDelay ArrDelay Origin Dest
## Min. : 1 Min. : 0 Length:968 Length:968
## 1st Qu.: 1 1st Qu.: 1 Class :character Class :character
## Median : 2 Median : 2 Mode :character Mode :character
## Mean : 2 Mean : 2
## 3rd Qu.: 2 3rd Qu.: 2
## Max. :18 Max. :18
## NA's :183 NA's :185
## AirTime Distance DepDelayMean AveSpeed
## Min. :-23 Min. : 56 Min. :-45 Min. :-11
## 1st Qu.: 1 1st Qu.: 316 1st Qu.:-32 1st Qu.:329
## Median : 2 Median : 590 Median :-11 Median :393
## Mean : 2 Mean : 678 Mean : 0 Mean :379
## 3rd Qu.: 2 3rd Qu.: 867 3rd Qu.: 18 3rd Qu.:443
## Max. : 6 Max. :2704 Max. :974 Max. :543
## NA's :185 NA's :183 NA's :183 NA's :185Codes based on R script
