Homework01
Khunshagai
10/15/2019
p6: E4
library(tidyverse)## -- Attaching packages ------------------------------------------- tidyverse 1.2.1 --## v ggplot2 3.2.1 v purrr 0.3.2
## v tibble 2.1.3 v dplyr 0.8.3
## v tidyr 1.0.0 v stringr 1.4.0
## v readr 1.3.1 v forcats 0.4.0## -- Conflicts ---------------------------------------------- tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()data(mpg)
mpg## # A tibble: 234 x 11
## manufacturer model displ year cyl trans drv cty hwy fl class
## <chr> <chr> <dbl> <int> <int> <chr> <chr> <int> <int> <chr> <chr>
## 1 audi a4 1.8 1999 4 auto~ f 18 29 p comp~
## 2 audi a4 1.8 1999 4 manu~ f 21 29 p comp~
## 3 audi a4 2 2008 4 manu~ f 20 31 p comp~
## 4 audi a4 2 2008 4 auto~ f 21 30 p comp~
## 5 audi a4 2.8 1999 6 auto~ f 16 26 p comp~
## 6 audi a4 2.8 1999 6 manu~ f 18 26 p comp~
## 7 audi a4 3.1 2008 6 auto~ f 18 27 p comp~
## 8 audi a4 q~ 1.8 1999 4 manu~ 4 18 26 p comp~
## 9 audi a4 q~ 1.8 1999 4 auto~ 4 16 25 p comp~
## 10 audi a4 q~ 2 2008 4 manu~ 4 20 28 p comp~
## # ... with 224 more rowsggplot(mpg, aes(x = hwy, y = cyl)) +
geom_point()
p12: E2
mpg## # A tibble: 234 x 11
## manufacturer model displ year cyl trans drv cty hwy fl class
## <chr> <chr> <dbl> <int> <int> <chr> <chr> <int> <int> <chr> <chr>
## 1 audi a4 1.8 1999 4 auto~ f 18 29 p comp~
## 2 audi a4 1.8 1999 4 manu~ f 21 29 p comp~
## 3 audi a4 2 2008 4 manu~ f 20 31 p comp~
## 4 audi a4 2 2008 4 auto~ f 21 30 p comp~
## 5 audi a4 2.8 1999 6 auto~ f 16 26 p comp~
## 6 audi a4 2.8 1999 6 manu~ f 18 26 p comp~
## 7 audi a4 3.1 2008 6 auto~ f 18 27 p comp~
## 8 audi a4 q~ 1.8 1999 4 manu~ 4 18 26 p comp~
## 9 audi a4 q~ 1.8 1999 4 auto~ 4 16 25 p comp~
## 10 audi a4 q~ 2 2008 4 manu~ 4 20 28 p comp~
## # ... with 224 more rowsglimpse(mpg)## Observations: 234
## Variables: 11
## $ manufacturer <chr> "audi", "audi", "audi", "audi", "audi", "audi", "...
## $ model <chr> "a4", "a4", "a4", "a4", "a4", "a4", "a4", "a4 qua...
## $ displ <dbl> 1.8, 1.8, 2.0, 2.0, 2.8, 2.8, 3.1, 1.8, 1.8, 2.0,...
## $ year <int> 1999, 1999, 2008, 2008, 1999, 1999, 2008, 1999, 1...
## $ cyl <int> 4, 4, 4, 4, 6, 6, 6, 4, 4, 4, 4, 6, 6, 6, 6, 6, 6...
## $ trans <chr> "auto(l5)", "manual(m5)", "manual(m6)", "auto(av)...
## $ drv <chr> "f", "f", "f", "f", "f", "f", "f", "4", "4", "4",...
## $ cty <int> 18, 21, 20, 21, 16, 18, 18, 18, 16, 20, 19, 15, 1...
## $ hwy <int> 29, 29, 31, 30, 26, 26, 27, 26, 25, 28, 27, 25, 2...
## $ fl <chr> "p", "p", "p", "p", "p", "p", "p", "p", "p", "p",...
## $ class <chr> "compact", "compact", "compact", "compact", "comp...p12: E3
ggplot(mpg, aes(x = displ, y = hwy, color = cyl)) +
geom_point()
## p20: E1
geom_line()## geom_line: na.rm = FALSE
## stat_identity: na.rm = FALSE
## position_identitygeom_boxplot()## geom_boxplot: outlier.colour = NULL, outlier.fill = NULL, outlier.shape = 19, outlier.size = 1.5, outlier.stroke = 0.5, outlier.alpha = NULL, notch = FALSE, notchwidth = 0.5, varwidth = FALSE, na.rm = FALSE
## stat_boxplot: na.rm = FALSE
## position_dodge2geom_histogram()## geom_bar: na.rm = FALSE
## stat_bin: binwidth = NULL, bins = NULL, na.rm = FALSE, pad = FALSE
## position_stackgeom_area()## geom_area: na.rm = FALSE
## stat_identity: na.rm = FALSE
## position_stackp21: E6
ggplot(mpg, aes(x = displ, y = hwy)) +
geom_point() +
geom_smooth(se = FALSE)## `geom_smooth()` using method = 'loess' and formula 'y ~ x'
ggplot(mpg, aes(x = displ, y = hwy)) +
geom_smooth(mapping = aes(group = drv), se = FALSE) +
geom_point()## `geom_smooth()` using method = 'loess' and formula 'y ~ x'
ggplot(mpg, aes(x = displ, y = hwy, colour = drv)) +
geom_point() +
geom_smooth(se = FALSE)## `geom_smooth()` using method = 'loess' and formula 'y ~ x'
ggplot(mpg, aes(x = displ, y = hwy)) +
geom_point(aes(colour = drv)) +
geom_smooth(se = FALSE)## `geom_smooth()` using method = 'loess' and formula 'y ~ x'
ggplot(mpg, aes(x = displ, y = hwy)) +
geom_point(aes(colour = drv)) +
geom_smooth(aes(linetype = drv), se = FALSE)## `geom_smooth()` using method = 'loess' and formula 'y ~ x'
ggplot(mpg, aes(x = displ, y = hwy)) +
geom_point(size = 4, color = "white") +
geom_point(aes(colour = drv))
## p49: E1
library("nycflights13")
library("tidyverse")
view(flights)
filter(flights, arr_delay >= 120)## # A tibble: 10,200 x 19
## year month day dep_time sched_dep_time dep_delay arr_time
## <int> <int> <int> <int> <int> <dbl> <int>
## 1 2013 1 1 811 630 101 1047
## 2 2013 1 1 848 1835 853 1001
## 3 2013 1 1 957 733 144 1056
## 4 2013 1 1 1114 900 134 1447
## 5 2013 1 1 1505 1310 115 1638
## 6 2013 1 1 1525 1340 105 1831
## 7 2013 1 1 1549 1445 64 1912
## 8 2013 1 1 1558 1359 119 1718
## 9 2013 1 1 1732 1630 62 2028
## 10 2013 1 1 1803 1620 103 2008
## # ... with 10,190 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>filter(flights, dest == "IAH" | dest == "HOU")## # A tibble: 9,313 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 1 623 627 -4 933
## 4 2013 1 1 728 732 -4 1041
## 5 2013 1 1 739 739 0 1104
## 6 2013 1 1 908 908 0 1228
## 7 2013 1 1 1028 1026 2 1350
## 8 2013 1 1 1044 1045 -1 1352
## 9 2013 1 1 1114 900 134 1447
## 10 2013 1 1 1205 1200 5 1503
## # ... with 9,303 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>filter(flights, dest %in% c("IAH", "HOU"))## # A tibble: 9,313 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 1 623 627 -4 933
## 4 2013 1 1 728 732 -4 1041
## 5 2013 1 1 739 739 0 1104
## 6 2013 1 1 908 908 0 1228
## 7 2013 1 1 1028 1026 2 1350
## 8 2013 1 1 1044 1045 -1 1352
## 9 2013 1 1 1114 900 134 1447
## 10 2013 1 1 1205 1200 5 1503
## # ... with 9,303 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>airlines## # A tibble: 16 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.
## 7 F9 Frontier Airlines Inc.
## 8 FL AirTran Airways Corporation
## 9 HA Hawaiian Airlines Inc.
## 10 MQ Envoy Air
## 11 OO SkyWest Airlines Inc.
## 12 UA United Air Lines Inc.
## 13 US US Airways Inc.
## 14 VX Virgin America
## 15 WN Southwest Airlines Co.
## 16 YV Mesa Airlines Inc.filter(flights, carrier %in% c("AA", "DL", "UA"))## # A tibble: 139,504 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 1 554 600 -6 812
## 5 2013 1 1 554 558 -4 740
## 6 2013 1 1 558 600 -2 753
## 7 2013 1 1 558 600 -2 924
## 8 2013 1 1 558 600 -2 923
## 9 2013 1 1 559 600 -1 941
## 10 2013 1 1 559 600 -1 854
## # ... with 139,494 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>filter(flights, month >= 7, month <= 9)## # A tibble: 86,326 x 19
## year month day dep_time sched_dep_time dep_delay arr_time
## <int> <int> <int> <int> <int> <dbl> <int>
## 1 2013 7 1 1 2029 212 236
## 2 2013 7 1 2 2359 3 344
## 3 2013 7 1 29 2245 104 151
## 4 2013 7 1 43 2130 193 322
## 5 2013 7 1 44 2150 174 300
## 6 2013 7 1 46 2051 235 304
## 7 2013 7 1 48 2001 287 308
## 8 2013 7 1 58 2155 183 335
## 9 2013 7 1 100 2146 194 327
## 10 2013 7 1 100 2245 135 337
## # ... with 86,316 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>filter(flights, month %in% 7:9)## # A tibble: 86,326 x 19
## year month day dep_time sched_dep_time dep_delay arr_time
## <int> <int> <int> <int> <int> <dbl> <int>
## 1 2013 7 1 1 2029 212 236
## 2 2013 7 1 2 2359 3 344
## 3 2013 7 1 29 2245 104 151
## 4 2013 7 1 43 2130 193 322
## 5 2013 7 1 44 2150 174 300
## 6 2013 7 1 46 2051 235 304
## 7 2013 7 1 48 2001 287 308
## 8 2013 7 1 58 2155 183 335
## 9 2013 7 1 100 2146 194 327
## 10 2013 7 1 100 2245 135 337
## # ... with 86,316 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>filter(flights, month == 7 | month == 8 | month == 9)## # A tibble: 86,326 x 19
## year month day dep_time sched_dep_time dep_delay arr_time
## <int> <int> <int> <int> <int> <dbl> <int>
## 1 2013 7 1 1 2029 212 236
## 2 2013 7 1 2 2359 3 344
## 3 2013 7 1 29 2245 104 151
## 4 2013 7 1 43 2130 193 322
## 5 2013 7 1 44 2150 174 300
## 6 2013 7 1 46 2051 235 304
## 7 2013 7 1 48 2001 287 308
## 8 2013 7 1 58 2155 183 335
## 9 2013 7 1 100 2146 194 327
## 10 2013 7 1 100 2245 135 337
## # ... with 86,316 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>filter(flights, arr_delay > 120, dep_delay <= 0)## # A tibble: 29 x 19
## year month day dep_time sched_dep_time dep_delay arr_time
## <int> <int> <int> <int> <int> <dbl> <int>
## 1 2013 1 27 1419 1420 -1 1754
## 2 2013 10 7 1350 1350 0 1736
## 3 2013 10 7 1357 1359 -2 1858
## 4 2013 10 16 657 700 -3 1258
## 5 2013 11 1 658 700 -2 1329
## 6 2013 3 18 1844 1847 -3 39
## 7 2013 4 17 1635 1640 -5 2049
## 8 2013 4 18 558 600 -2 1149
## 9 2013 4 18 655 700 -5 1213
## 10 2013 5 22 1827 1830 -3 2217
## # ... with 19 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>filter(flights, dep_delay >= 60, dep_delay - arr_delay > 30)## # A tibble: 1,844 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 2205 1720 285 46
## 2 2013 1 1 2326 2130 116 131
## 3 2013 1 3 1503 1221 162 1803
## 4 2013 1 3 1839 1700 99 2056
## 5 2013 1 3 1850 1745 65 2148
## 6 2013 1 3 1941 1759 102 2246
## 7 2013 1 3 1950 1845 65 2228
## 8 2013 1 3 2015 1915 60 2135
## 9 2013 1 3 2257 2000 177 45
## 10 2013 1 4 1917 1700 137 2135
## # ... with 1,834 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>summary(flights$dep_time)## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## 1 907 1401 1349 1744 2400 8255filter(flights, dep_time <= 600 | dep_time == 2400)## # A tibble: 9,373 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 9,363 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>c(600, 1200, 2400) %% 2400## [1] 600 1200 0filter(flights, dep_time %% 2400 <= 600)## # A tibble: 9,373 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 9,363 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>p50: E2
filter(flights, between(month, 7, 9))## # A tibble: 86,326 x 19
## year month day dep_time sched_dep_time dep_delay arr_time
## <int> <int> <int> <int> <int> <dbl> <int>
## 1 2013 7 1 1 2029 212 236
## 2 2013 7 1 2 2359 3 344
## 3 2013 7 1 29 2245 104 151
## 4 2013 7 1 43 2130 193 322
## 5 2013 7 1 44 2150 174 300
## 6 2013 7 1 46 2051 235 304
## 7 2013 7 1 48 2001 287 308
## 8 2013 7 1 58 2155 183 335
## 9 2013 7 1 100 2146 194 327
## 10 2013 7 1 100 2245 135 337
## # ... with 86,316 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>p50: E3
filter(flights, is.na(dep_time))## # A tibble: 8,255 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 NA 1630 NA NA
## 2 2013 1 1 NA 1935 NA NA
## 3 2013 1 1 NA 1500 NA NA
## 4 2013 1 1 NA 600 NA NA
## 5 2013 1 2 NA 1540 NA NA
## 6 2013 1 2 NA 1620 NA NA
## 7 2013 1 2 NA 1355 NA NA
## 8 2013 1 2 NA 1420 NA NA
## 9 2013 1 2 NA 1321 NA NA
## 10 2013 1 2 NA 1545 NA NA
## # ... with 8,245 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>p51: E1
arrange(flights, dep_time) %>%
tail()## # A tibble: 6 x 19
## year month day dep_time sched_dep_time dep_delay arr_time
## <int> <int> <int> <int> <int> <dbl> <int>
## 1 2013 9 30 NA 1842 NA NA
## 2 2013 9 30 NA 1455 NA NA
## 3 2013 9 30 NA 2200 NA NA
## 4 2013 9 30 NA 1210 NA NA
## 5 2013 9 30 NA 1159 NA NA
## 6 2013 9 30 NA 840 NA NA
## # ... with 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>arrange(flights, desc(dep_time))## # 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 10 30 2400 2359 1 327
## 2 2013 11 27 2400 2359 1 515
## 3 2013 12 5 2400 2359 1 427
## 4 2013 12 9 2400 2359 1 432
## 5 2013 12 9 2400 2250 70 59
## 6 2013 12 13 2400 2359 1 432
## 7 2013 12 19 2400 2359 1 434
## 8 2013 12 29 2400 1700 420 302
## 9 2013 2 7 2400 2359 1 432
## 10 2013 2 7 2400 2359 1 443
## # ... 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>arrange(flights, desc(is.na(dep_time)), dep_time)## # 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 NA 1630 NA NA
## 2 2013 1 1 NA 1935 NA NA
## 3 2013 1 1 NA 1500 NA NA
## 4 2013 1 1 NA 600 NA NA
## 5 2013 1 2 NA 1540 NA NA
## 6 2013 1 2 NA 1620 NA NA
## 7 2013 1 2 NA 1355 NA NA
## 8 2013 1 2 NA 1420 NA NA
## 9 2013 1 2 NA 1321 NA NA
## 10 2013 1 2 NA 1545 NA NA
## # ... 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>p51: E2
arrange(flights, desc(dep_delay))## # 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 9 641 900 1301 1242
## 2 2013 6 15 1432 1935 1137 1607
## 3 2013 1 10 1121 1635 1126 1239
## 4 2013 9 20 1139 1845 1014 1457
## 5 2013 7 22 845 1600 1005 1044
## 6 2013 4 10 1100 1900 960 1342
## 7 2013 3 17 2321 810 911 135
## 8 2013 6 27 959 1900 899 1236
## 9 2013 7 22 2257 759 898 121
## 10 2013 12 5 756 1700 896 1058
## # ... 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>arrange(flights, dep_delay)## # 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 12 7 2040 2123 -43 40
## 2 2013 2 3 2022 2055 -33 2240
## 3 2013 11 10 1408 1440 -32 1549
## 4 2013 1 11 1900 1930 -30 2233
## 5 2013 1 29 1703 1730 -27 1947
## 6 2013 8 9 729 755 -26 1002
## 7 2013 10 23 1907 1932 -25 2143
## 8 2013 3 30 2030 2055 -25 2213
## 9 2013 3 2 1431 1455 -24 1601
## 10 2013 5 5 934 958 -24 1225
## # ... 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>p51: E3
fastest_flights <- mutate(flights, mph = distance / air_time * 60)
fastest_flights <- select(
fastest_flights, mph, distance, air_time,
flight, origin, dest, year, month, day)
head(arrange(fastest_flights, desc(mph)))## # A tibble: 6 x 9
## mph distance air_time flight origin dest year month day
## <dbl> <dbl> <dbl> <int> <chr> <chr> <int> <int> <int>
## 1 703. 762 65 1499 LGA ATL 2013 5 25
## 2 650. 1008 93 4667 EWR MSP 2013 7 2
## 3 648 594 55 4292 EWR GSP 2013 5 13
## 4 641. 748 70 3805 EWR BNA 2013 3 23
## 5 591. 1035 105 1902 LGA PBI 2013 1 12
## 6 564 1598 170 315 JFK SJU 2013 11 17p51: E4
arrange(flights, desc(distance))## # 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 1 857 900 -3 1516
## 2 2013 1 2 909 900 9 1525
## 3 2013 1 3 914 900 14 1504
## 4 2013 1 4 900 900 0 1516
## 5 2013 1 5 858 900 -2 1519
## 6 2013 1 6 1019 900 79 1558
## 7 2013 1 7 1042 900 102 1620
## 8 2013 1 8 901 900 1 1504
## 9 2013 1 9 641 900 1301 1242
## 10 2013 1 10 859 900 -1 1449
## # ... 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>arrange(flights, distance)## # 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 7 27 NA 106 NA NA
## 2 2013 1 3 2127 2129 -2 2222
## 3 2013 1 4 1240 1200 40 1333
## 4 2013 1 4 1829 1615 134 1937
## 5 2013 1 4 2128 2129 -1 2218
## 6 2013 1 5 1155 1200 -5 1241
## 7 2013 1 6 2125 2129 -4 2224
## 8 2013 1 7 2124 2129 -5 2212
## 9 2013 1 8 2127 2130 -3 2304
## 10 2013 1 9 2126 2129 -3 2217
## # ... 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>arrange(flights, desc(air_time))## # 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 3 17 1337 1335 2 1937
## 2 2013 2 6 853 900 -7 1542
## 3 2013 3 15 1001 1000 1 1551
## 4 2013 3 17 1006 1000 6 1607
## 5 2013 3 16 1001 1000 1 1544
## 6 2013 2 5 900 900 0 1555
## 7 2013 11 12 936 930 6 1630
## 8 2013 3 14 958 1000 -2 1542
## 9 2013 11 20 1006 1000 6 1639
## 10 2013 3 15 1342 1335 7 1924
## # ... 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>arrange(flights, air_time)## # 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 16 1355 1315 40 1442
## 2 2013 4 13 537 527 10 622
## 3 2013 12 6 922 851 31 1021
## 4 2013 2 3 2153 2129 24 2247
## 5 2013 2 5 1303 1315 -12 1342
## 6 2013 2 12 2123 2130 -7 2211
## 7 2013 3 2 1450 1500 -10 1547
## 8 2013 3 8 2026 1935 51 2131
## 9 2013 3 18 1456 1329 87 1533
## 10 2013 3 19 2226 2145 41 2305
## # ... 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>p58: E4
rankme <- tibble(
x = c(10, 5, 1, 5, 5)
)
rankme <- mutate(rankme,
x_row_number = row_number(x),
x_min_rank = min_rank(x),
x_dense_rank = dense_rank(x)
)
arrange(rankme, x)## # A tibble: 5 x 4
## x x_row_number x_min_rank x_dense_rank
## <dbl> <int> <int> <int>
## 1 1 1 1 1
## 2 5 2 2 2
## 3 5 3 2 2
## 4 5 4 2 2
## 5 10 5 5 3flights_delayed <- mutate(flights,
dep_delay_min_rank = min_rank(desc(dep_delay)),
dep_delay_row_number = row_number(desc(dep_delay)),
dep_delay_dense_rank = dense_rank(desc(dep_delay))
)
flights_delayed <- filter(
flights_delayed,
!(dep_delay_min_rank > 10 | dep_delay_row_number > 10 |
dep_delay_dense_rank > 10)
)
flights_delayed <- arrange(flights_delayed, dep_delay_min_rank)
print(select(
flights_delayed, month, day, carrier, flight, dep_delay,
dep_delay_min_rank, dep_delay_row_number, dep_delay_dense_rank
),
n = Inf
)## # A tibble: 10 x 8
## month day carrier flight dep_delay dep_delay_min_r~ dep_delay_row_n~
## <int> <int> <chr> <int> <dbl> <int> <int>
## 1 1 9 HA 51 1301 1 1
## 2 6 15 MQ 3535 1137 2 2
## 3 1 10 MQ 3695 1126 3 3
## 4 9 20 AA 177 1014 4 4
## 5 7 22 MQ 3075 1005 5 5
## 6 4 10 DL 2391 960 6 6
## 7 3 17 DL 2119 911 7 7
## 8 6 27 DL 2007 899 8 8
## 9 7 22 DL 2047 898 9 9
## 10 12 5 AA 172 896 10 10
## # ... with 1 more variable: dep_delay_dense_rank <int>p73: E4
not_cancelled <- flights %>%
filter(!is.na(dep_delay), !is.na(arr_delay))
cancelled_per_day <- flights %>%
mutate(cancelled = (is.na(arr_delay) | is.na(dep_delay))) %>%
group_by(year, month, day) %>%
summarise(cancelled_num = sum(cancelled),flights_num = n())
ggplot(cancelled_per_day) +
geom_point(aes(x = flights_num, y = cancelled_num))
cancelled_and_delays <-
flights %>%
mutate(cancelled = (is.na(arr_delay) | is.na(dep_delay))) %>%
group_by(year, month, day) %>%
summarise(
cancelled_prop = mean(cancelled),
avg_dep_delay = mean(dep_delay, na.rm = TRUE),
avg_arr_delay = mean(arr_delay, na.rm = TRUE)
) %>%
ungroup()
ggplot(cancelled_and_delays) +
geom_point(aes(x = avg_dep_delay, y = cancelled_prop))
ggplot(cancelled_and_delays) +
geom_point(aes(x = avg_arr_delay, y = cancelled_prop))
## p73: E5
flights %>%
group_by(carrier) %>%
summarise(arr_delay = mean(arr_delay, na.rm = TRUE)) %>%
arrange(desc(arr_delay))## # A tibble: 16 x 2
## carrier arr_delay
## <chr> <dbl>
## 1 F9 21.9
## 2 FL 20.1
## 3 EV 15.8
## 4 YV 15.6
## 5 OO 11.9
## 6 MQ 10.8
## 7 WN 9.65
## 8 B6 9.46
## 9 9E 7.38
## 10 UA 3.56
## 11 US 2.13
## 12 VX 1.76
## 13 DL 1.64
## 14 AA 0.364
## 15 HA -6.92
## 16 AS -9.93filter(airlines, carrier == "F9")## # A tibble: 1 x 2
## carrier name
## <chr> <chr>
## 1 F9 Frontier Airlines Inc.flights %>%
filter(!is.na(arr_delay)) %>%
# Total delay by carrier within each origin, dest
group_by(origin, dest, carrier) %>%
summarise(
arr_delay = sum(arr_delay),
flights = n()
) %>%
# Total delay within each origin dest
group_by(origin, dest) %>%
mutate(
arr_delay_total = sum(arr_delay),
flights_total = sum(flights)
) %>%
# average delay of each carrier - average delay of other carriers
ungroup() %>%
mutate(
arr_delay_others = (arr_delay_total - arr_delay) /
(flights_total - flights),
arr_delay_mean = arr_delay / flights,
arr_delay_diff = arr_delay_mean - arr_delay_others
) %>%
# remove NaN values (when there is only one carrier)
filter(is.finite(arr_delay_diff)) %>%
# average over all airports it flies to
group_by(carrier) %>%
summarise(arr_delay_diff = mean(arr_delay_diff)) %>%
arrange(desc(arr_delay_diff))## # A tibble: 15 x 2
## carrier arr_delay_diff
## <chr> <dbl>
## 1 OO 27.3
## 2 F9 17.3
## 3 EV 11.0
## 4 B6 6.41
## 5 FL 2.57
## 6 VX -0.202
## 7 AA -0.970
## 8 WN -1.27
## 9 UA -1.86
## 10 MQ -2.48
## 11 YV -2.81
## 12 9E -3.54
## 13 US -4.14
## 14 DL -10.2
## 15 AS -15.8p75: E2
flights %>%
filter(!is.na(tailnum)) %>%
mutate(on_time = !is.na(arr_time) & (arr_delay <= 0)) %>%
group_by(tailnum) %>%
summarise(on_time = mean(on_time), n = n()) %>%
filter(min_rank(on_time) == 1)## # A tibble: 110 x 3
## tailnum on_time n
## <chr> <dbl> <int>
## 1 N121DE 0 2
## 2 N136DL 0 1
## 3 N143DA 0 1
## 4 N17627 0 2
## 5 N240AT 0 5
## 6 N26906 0 1
## 7 N295AT 0 4
## 8 N302AS 0 1
## 9 N303AS 0 1
## 10 N32626 0 1
## # ... with 100 more rowsquantile(count(flights, tailnum)$n)## 0% 25% 50% 75% 100%
## 1 23 54 110 2512flights %>%
filter(!is.na(tailnum)) %>%
mutate(on_time = !is.na(arr_time) & (arr_delay <= 0)) %>%
group_by(tailnum) %>%
summarise(on_time = mean(on_time), n = n()) %>%
filter(n >= 20) %>%
filter(min_rank(on_time) == 1)## # A tibble: 1 x 3
## tailnum on_time n
## <chr> <dbl> <int>
## 1 N988AT 0.189 37flights %>%
group_by(tailnum) %>%
summarise(arr_delay = mean(arr_delay), n = n()) %>%
filter(n >= 20) %>%
filter(min_rank(desc(arr_delay)) == 1)## # A tibble: 1 x 3
## tailnum arr_delay n
## <chr> <dbl> <int>
## 1 N203FR 59.1 41p75: E3
flights %>%
group_by(hour) %>%
summarise(arr_delay = mean(arr_delay, na.rm = TRUE)) %>%
arrange(arr_delay)## # A tibble: 20 x 2
## hour arr_delay
## <dbl> <dbl>
## 1 7 -5.30
## 2 5 -4.80
## 3 6 -3.38
## 4 9 -1.45
## 5 8 -1.11
## 6 10 0.954
## 7 11 1.48
## 8 12 3.49
## 9 13 6.54
## 10 14 9.20
## 11 23 11.8
## 12 15 12.3
## 13 16 12.6
## 14 18 14.8
## 15 22 16.0
## 16 17 16.0
## 17 19 16.7
## 18 20 16.7
## 19 21 18.4
## 20 1 NaNp75: E4
flights %>%
filter(arr_delay > 0) %>%
group_by(dest) %>%
mutate(
arr_delay_total = sum(arr_delay),
arr_delay_prop = arr_delay / arr_delay_total
) %>%
select(
dest, month, day, dep_time, carrier, flight,
arr_delay, arr_delay_prop
) %>%
arrange(dest, desc(arr_delay_prop))## # A tibble: 133,004 x 8
## # Groups: dest [103]
## dest month day dep_time carrier flight arr_delay arr_delay_prop
## <chr> <int> <int> <int> <chr> <int> <dbl> <dbl>
## 1 ABQ 7 22 2145 B6 1505 153 0.0341
## 2 ABQ 12 14 2223 B6 65 149 0.0332
## 3 ABQ 10 15 2146 B6 65 138 0.0308
## 4 ABQ 7 23 2206 B6 1505 137 0.0305
## 5 ABQ 12 17 2220 B6 65 136 0.0303
## 6 ABQ 7 10 2025 B6 1505 126 0.0281
## 7 ABQ 7 30 2212 B6 1505 118 0.0263
## 8 ABQ 7 28 2038 B6 1505 117 0.0261
## 9 ABQ 12 8 2049 B6 65 114 0.0254
## 10 ABQ 9 2 2212 B6 1505 109 0.0243
## # ... with 132,994 more rowsflights %>%
filter(arr_delay > 0) %>%
group_by(dest) %>%
mutate(
arr_delay_total = sum(arr_delay),
arr_delay_prop = arr_delay / arr_delay_total
) %>%
select(
dest, month, day, dep_time, carrier, flight,
arr_delay, arr_delay_prop
) %>%
arrange(dest, desc(arr_delay_prop))## # A tibble: 133,004 x 8
## # Groups: dest [103]
## dest month day dep_time carrier flight arr_delay arr_delay_prop
## <chr> <int> <int> <int> <chr> <int> <dbl> <dbl>
## 1 ABQ 7 22 2145 B6 1505 153 0.0341
## 2 ABQ 12 14 2223 B6 65 149 0.0332
## 3 ABQ 10 15 2146 B6 65 138 0.0308
## 4 ABQ 7 23 2206 B6 1505 137 0.0305
## 5 ABQ 12 17 2220 B6 65 136 0.0303
## 6 ABQ 7 10 2025 B6 1505 126 0.0281
## 7 ABQ 7 30 2212 B6 1505 118 0.0263
## 8 ABQ 7 28 2038 B6 1505 117 0.0261
## 9 ABQ 12 8 2049 B6 65 114 0.0254
## 10 ABQ 9 2 2212 B6 1505 109 0.0243
## # ... with 132,994 more rows