library(dplyr)##
## Attaching package: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, unionlibrary(hflights)
data(hflights)
head(hflights)## Year Month DayofMonth DayOfWeek DepTime ArrTime UniqueCarrier
## 5424 2011 1 1 6 1400 1500 AA
## 5425 2011 1 2 7 1401 1501 AA
## 5426 2011 1 3 1 1352 1502 AA
## 5427 2011 1 4 2 1403 1513 AA
## 5428 2011 1 5 3 1405 1507 AA
## 5429 2011 1 6 4 1359 1503 AA
## FlightNum TailNum ActualElapsedTime AirTime ArrDelay DepDelay Origin
## 5424 428 N576AA 60 40 -10 0 IAH
## 5425 428 N557AA 60 45 -9 1 IAH
## 5426 428 N541AA 70 48 -8 -8 IAH
## 5427 428 N403AA 70 39 3 3 IAH
## 5428 428 N492AA 62 44 -3 5 IAH
## 5429 428 N262AA 64 45 -7 -1 IAH
## Dest Distance TaxiIn TaxiOut Cancelled CancellationCode Diverted
## 5424 DFW 224 7 13 0 0
## 5425 DFW 224 6 9 0 0
## 5426 DFW 224 5 17 0 0
## 5427 DFW 224 9 22 0 0
## 5428 DFW 224 9 9 0 0
## 5429 DFW 224 6 13 0 0tbl_df creates a “local frame” Local data frame is simply a wrapper for a data frame that prints nicely.
#convert to local data frame
flights <- tbl_df(hflights)
# printing only shows 10 rows and as many column as can fit on your screen
flights## # A tibble: 227,496 x 21
## Year Month DayofMonth DayOfWeek DepTime ArrTime UniqueCarrier FlightNum
## * <int> <int> <int> <int> <int> <int> <chr> <int>
## 1 2011 1 1 6 1400 1500 AA 428
## 2 2011 1 2 7 1401 1501 AA 428
## 3 2011 1 3 1 1352 1502 AA 428
## 4 2011 1 4 2 1403 1513 AA 428
## 5 2011 1 5 3 1405 1507 AA 428
## 6 2011 1 6 4 1359 1503 AA 428
## 7 2011 1 7 5 1359 1509 AA 428
## 8 2011 1 8 6 1355 1454 AA 428
## 9 2011 1 9 7 1443 1554 AA 428
## 10 2011 1 10 1 1443 1553 AA 428
## # ... with 227,486 more rows, and 13 more variables: TailNum <chr>,
## # ActualElapsedTime <int>, AirTime <int>, ArrDelay <int>,
## # DepDelay <int>, Origin <chr>, Dest <chr>, Distance <int>,
## # TaxiIn <int>, TaxiOut <int>, Cancelled <int>, CancellationCode <chr>,
## # Diverted <int># you can specify that you want to see more rows
print(flights, n =20)## # A tibble: 227,496 x 21
## Year Month DayofMonth DayOfWeek DepTime ArrTime UniqueCarrier FlightNum
## * <int> <int> <int> <int> <int> <int> <chr> <int>
## 1 2011 1 1 6 1400 1500 AA 428
## 2 2011 1 2 7 1401 1501 AA 428
## 3 2011 1 3 1 1352 1502 AA 428
## 4 2011 1 4 2 1403 1513 AA 428
## 5 2011 1 5 3 1405 1507 AA 428
## 6 2011 1 6 4 1359 1503 AA 428
## 7 2011 1 7 5 1359 1509 AA 428
## 8 2011 1 8 6 1355 1454 AA 428
## 9 2011 1 9 7 1443 1554 AA 428
## 10 2011 1 10 1 1443 1553 AA 428
## 11 2011 1 11 2 1429 1539 AA 428
## 12 2011 1 12 3 1419 1515 AA 428
## 13 2011 1 13 4 1358 1501 AA 428
## 14 2011 1 14 5 1357 1504 AA 428
## 15 2011 1 15 6 1359 1459 AA 428
## 16 2011 1 16 7 1359 1509 AA 428
## 17 2011 1 17 1 1530 1634 AA 428
## 18 2011 1 18 2 1408 1508 AA 428
## 19 2011 1 19 3 1356 1503 AA 428
## 20 2011 1 20 4 1507 1622 AA 428
## # ... with 2.275e+05 more rows, and 13 more variables: TailNum <chr>,
## # ActualElapsedTime <int>, AirTime <int>, ArrDelay <int>,
## # DepDelay <int>, Origin <chr>, Dest <chr>, Distance <int>,
## # TaxiIn <int>, TaxiOut <int>, Cancelled <int>, CancellationCode <chr>,
## # Diverted <int>#convert to a normal data frame to see all of the columns
data.frame(head(flights))## Year Month DayofMonth DayOfWeek DepTime ArrTime UniqueCarrier FlightNum
## 1 2011 1 1 6 1400 1500 AA 428
## 2 2011 1 2 7 1401 1501 AA 428
## 3 2011 1 3 1 1352 1502 AA 428
## 4 2011 1 4 2 1403 1513 AA 428
## 5 2011 1 5 3 1405 1507 AA 428
## 6 2011 1 6 4 1359 1503 AA 428
## TailNum ActualElapsedTime AirTime ArrDelay DepDelay Origin Dest Distance
## 1 N576AA 60 40 -10 0 IAH DFW 224
## 2 N557AA 60 45 -9 1 IAH DFW 224
## 3 N541AA 70 48 -8 -8 IAH DFW 224
## 4 N403AA 70 39 3 3 IAH DFW 224
## 5 N492AA 62 44 -3 5 IAH DFW 224
## 6 N262AA 64 45 -7 -1 IAH DFW 224
## TaxiIn TaxiOut Cancelled CancellationCode Diverted
## 1 7 13 0 0
## 2 6 9 0 0
## 3 5 17 0 0
## 4 9 22 0 0
## 5 9 9 0 0
## 6 6 13 0 0