library(tidyverse)## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.2 ──
## ✔ ggplot2 3.3.6 ✔ purrr 0.3.4
## ✔ tibble 3.1.8 ✔ dplyr 1.0.10
## ✔ tidyr 1.2.1 ✔ stringr 1.4.1
## ✔ readr 2.1.2 ✔ forcats 0.5.2
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()library(lubridate)##
## Attaching package: 'lubridate'
##
## The following objects are masked from 'package:base':
##
## date, intersect, setdiff, unionlibrary(knitr)
library(skimr)Importing the data.
library(readr)
miFlights <- read_csv("Activity 7/miFlights2019-2021.csv")## Rows: 463818 Columns: 37
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (9): carrier, tailnum, origin, dest, carrier_name, plane_type, plane_m...
## dbl (27): year, month, day, dep_time, sched_dep_time, dep_delay, arr_time, ...
## dttm (1): time_hour
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.Exploratory Data Analysis.
skim(miFlights)| Name | miFlights |
| Number of rows | 463818 |
| Number of columns | 37 |
| _______________________ | |
| Column type frequency: | |
| character | 9 |
| numeric | 27 |
| POSIXct | 1 |
| ________________________ | |
| Group variables | None |
Variable type: character
| skim_variable | n_missing | complete_rate | min | max | empty | n_unique | whitespace |
|---|---|---|---|---|---|---|---|
| carrier | 0 | 1.00 | 2 | 2 | 0 | 16 | 0 |
| tailnum | 2189 | 1.00 | 3 | 6 | 0 | 5250 | 0 |
| origin | 0 | 1.00 | 3 | 3 | 0 | 4 | 0 |
| dest | 0 | 1.00 | 3 | 3 | 0 | 130 | 0 |
| carrier_name | 0 | 1.00 | 9 | 34 | 0 | 16 | 0 |
| plane_type | 11140 | 0.98 | 23 | 23 | 0 | 1 | 0 |
| plane_manufacturer | 11140 | 0.98 | 6 | 29 | 0 | 16 | 0 |
| plane_model | 11140 | 0.98 | 5 | 15 | 0 | 93 | 0 |
| plane_engine | 11140 | 0.98 | 9 | 9 | 0 | 2 | 0 |
Variable type: numeric
| skim_variable | n_missing | complete_rate | mean | sd | p0 | p25 | p50 | p75 | p100 | hist |
|---|---|---|---|---|---|---|---|---|---|---|
| year | 0 | 1.00 | 2019.92 | 0.85 | 2019.00 | 2019.00 | 2020.00 | 2021.00 | 2021.00 | ▇▁▆▁▆ |
| month | 0 | 1.00 | 6.53 | 3.48 | 1.00 | 3.00 | 7.00 | 10.00 | 12.00 | ▇▅▅▅▇ |
| day | 0 | 1.00 | 15.74 | 8.76 | 1.00 | 8.00 | 16.00 | 23.00 | 31.00 | ▇▇▇▇▆ |
| dep_time | 9060 | 0.98 | 1372.26 | 490.52 | 1.00 | 950.00 | 1355.00 | 1754.00 | 2400.00 | ▁▇▇▇▆ |
| sched_dep_time | 0 | 1.00 | 1368.40 | 481.75 | 49.00 | 948.00 | 1355.00 | 1750.00 | 2336.00 | ▁▇▇▇▆ |
| dep_delay | 9063 | 0.98 | 7.11 | 44.97 | -54.00 | -5.00 | -3.00 | 0.00 | 2672.00 | ▇▁▁▁▁ |
| arr_time | 9324 | 0.98 | 1481.01 | 506.74 | 1.00 | 1053.00 | 1502.00 | 1905.00 | 2400.00 | ▁▅▇▇▆ |
| sched_arr_time | 0 | 1.00 | 1496.79 | 495.16 | 1.00 | 1103.00 | 1510.00 | 1910.00 | 2359.00 | ▁▃▇▇▇ |
| arr_delay | 10239 | 0.98 | 0.16 | 47.21 | -85.00 | -17.00 | -9.00 | 2.00 | 2649.00 | ▇▁▁▁▁ |
| flight | 0 | 1.00 | 413.37 | 269.57 | 1.00 | 189.00 | 387.00 | 600.00 | 1322.00 | ▇▇▆▂▁ |
| air_time | 10239 | 0.98 | 94.59 | 63.12 | 15.00 | 50.00 | 74.00 | 130.00 | 581.00 | ▇▂▁▁▁ |
| distance | 0 | 1.00 | 641.00 | 488.23 | 74.00 | 296.00 | 500.00 | 957.00 | 4475.00 | ▇▂▁▁▁ |
| hour | 0 | 1.00 | 13.41 | 4.79 | 0.00 | 9.00 | 13.00 | 17.00 | 23.00 | ▁▇▇▇▆ |
| minute | 0 | 1.00 | 27.49 | 17.94 | 0.00 | 11.00 | 27.00 | 44.00 | 59.00 | ▇▆▇▆▆ |
| temp | 441760 | 0.05 | 42.16 | 15.40 | -4.00 | 32.00 | 37.90 | 48.90 | 90.00 | ▁▆▇▂▁ |
| dewp | 441762 | 0.05 | 31.91 | 13.42 | -9.00 | 23.00 | 28.90 | 39.90 | 75.90 | ▁▆▇▃▁ |
| humid | 441773 | 0.05 | 68.87 | 15.10 | 25.87 | 57.93 | 71.82 | 80.66 | 100.00 | ▁▃▅▇▃ |
| wind_dir | 9205 | 0.98 | 181.02 | 109.46 | 0.00 | 80.00 | 200.00 | 270.00 | 360.00 | ▇▃▆▇▆ |
| wind_speed | 4367 | 0.99 | 8.59 | 5.64 | 0.00 | 4.60 | 8.06 | 11.51 | 42.58 | ▇▆▁▁▁ |
| wind_gust | 4367 | 0.99 | 9.88 | 6.50 | 0.00 | 5.30 | 9.27 | 13.24 | 49.00 | ▇▆▁▁▁ |
| precip | 430846 | 0.07 | 0.01 | 0.02 | 0.00 | 0.00 | 0.00 | 0.01 | 0.44 | ▇▁▁▁▁ |
| pressure | 447131 | 0.04 | 1018.83 | 7.60 | 990.40 | 1014.10 | 1019.00 | 1023.40 | 1038.50 | ▁▂▇▇▂ |
| visib | 1934 | 1.00 | 8.18 | 2.56 | 0.06 | 7.00 | 10.00 | 10.00 | 10.00 | ▁▁▁▂▇ |
| plane_year | 21647 | 0.95 | 2008.12 | 7.15 | 1987.00 | 2003.00 | 2007.00 | 2015.00 | 2021.00 | ▁▂▇▃▅ |
| plane_engines | 11140 | 0.98 | 2.00 | 0.02 | 2.00 | 2.00 | 2.00 | 2.00 | 3.00 | ▇▁▁▁▁ |
| plane_seats | 11140 | 0.98 | 127.86 | 66.68 | 20.00 | 80.00 | 95.00 | 182.00 | 451.00 | ▇▃▂▁▁ |
| plane_speed | 11140 | 0.98 | 0.01 | 1.72 | 0.00 | 0.00 | 0.00 | 0.00 | 438.00 | ▇▁▁▁▁ |
Variable type: POSIXct
| skim_variable | n_missing | complete_rate | min | max | median | n_unique |
|---|---|---|---|---|---|---|
| time_hour | 0 | 1 | 2019-01-01 05:00:00 | 2021-12-31 22:00:00 | 2020-03-26 06:00:00 | 19059 |
glimpse(miFlights)## Rows: 463,818
## Columns: 37
## $ year <dbl> 2019, 2019, 2019, 2019, 2019, 2019, 2019, 2019, 201…
## $ month <dbl> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, …
## $ day <dbl> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, …
## $ dep_time <dbl> 55, 455, 506, 531, 534, 550, 555, 555, 555, 600, 60…
## $ sched_dep_time <dbl> 2115, 500, 511, 535, 545, 600, 600, 555, 600, 600, …
## $ dep_delay <dbl> 220, -5, -5, -4, -11, -10, -5, 0, -5, 0, -2, 3, 4, …
## $ arr_time <dbl> 426, 830, 710, 647, 750, 712, 822, 709, 755, 559, 9…
## $ sched_arr_time <dbl> 2323, 834, 730, 710, 742, 748, 834, 715, 817, 615, …
## $ arr_delay <dbl> 303, -4, -20, -23, 8, -36, -12, -6, -22, -16, 3, -7…
## $ carrier <chr> "OH", "YX", "AA", "WN", "B6", "YX", "OO", "WN", "DL…
## $ flight <dbl> 1019, 954, 185, 203, 310, 790, 803, 295, 348, 218, …
## $ tailnum <chr> "N567NN", "N433YX", "N853NN", "N227WN", "N203JB", "…
## $ origin <chr> "DTW", "GRR", "DTW", "DTW", "DTW", "DTW", "FNT", "D…
## $ dest <chr> "CLT", "MIA", "DFW", "BWI", "BOS", "EWR", "ATL", "D…
## $ air_time <dbl> 88, 187, 162, 64, 71, 61, 125, 174, 105, 45, 179, 1…
## $ distance <dbl> 500, 1214, 986, 409, 632, 488, 645, 1123, 640, 228,…
## $ hour <dbl> 21, 5, 5, 5, 5, 6, 6, 5, 6, 6, 6, 6, 6, 6, 6, 6, 6,…
## $ minute <dbl> 15, 0, 11, 35, 45, 0, 0, 55, 0, 0, 3, 0, 0, 5, 0, 1…
## $ time_hour <dttm> 2019-01-01 21:00:00, 2019-01-01 05:00:00, 2019-01-…
## $ temp <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,…
## $ dewp <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,…
## $ humid <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,…
## $ wind_dir <dbl> 10, 320, 290, 290, 290, 290, 330, 290, 290, 290, 29…
## $ wind_speed <dbl> 8.05546, 9.20624, 19.56326, 19.56326, 19.56326, 13.…
## $ wind_gust <dbl> 9.270062, 10.594357, 22.513008, 22.513008, 22.51300…
## $ precip <dbl> NA, 1e-04, NA, NA, NA, NA, 1e-04, NA, NA, NA, NA, N…
## $ pressure <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,…
## $ visib <dbl> 1.25, 9.00, 7.00, 7.00, 7.00, 4.00, 9.00, 7.00, 10.…
## $ carrier_name <chr> "PSA Airlines Inc.", "Republic Airline", "American …
## $ plane_year <dbl> 2015, 2014, 2010, 2005, 2006, 2016, 2006, 1999, 200…
## $ plane_type <chr> "Fixed wing multi engine", "Fixed wing multi engine…
## $ plane_manufacturer <chr> "BOMBARDIER INC", "EMBRAER S A", "BOEING", "BOEING"…
## $ plane_model <chr> "CL-600-2D24", "ERJ 170-200 LR", "737-823", "737-7H…
## $ plane_engines <dbl> 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, …
## $ plane_seats <dbl> 95, 88, 162, 140, 20, 88, 95, 149, 100, 140, 162, 1…
## $ plane_speed <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ plane_engine <chr> "Turbo-fan", "Turbo-fan", "Turbo-fan", "Turbo-fan",…The weather values are the most missing. There’s a surprisingly large amount of departure delay times missing. There’s a lot of missing data on the conditions of the day such as weather and precipitation.
Bar Charts.
‘geom_bar()’ is when you have a categorical variable in your data set and it tallies them up for you automatically.
miFlights %>% ggplot(aes( x = origin)) + geom_bar()
This one requires you to set the variable that represents the height of your bars.
miFlights %>% count(origin) %>% ggplot(aes(x = fct_reorder(origin, -n),
y = n)) +
geom_col() +
labs( title = "Michigan flights by airport, 2019-2021",
x = "Airport",
y = "Number of flights",
caption = "Data source: anyFlights R package") +
theme_bw()
Subsetting rows using filter()
janflights <- miFlights %>% filter(month == 1,
day == 1)
dec25 <- miFlights %>% filter(month == 12,
day == 25)novDec <- miFlights %>% filter(month == 11 | month == 12)novDec <- miFlights %>% filter(month %in% 11 : 12)notNovDec <- miFlights %>% filter(!(month %in% 11 : 12))Missing values.
# all departure times are non-missing
miFlightsComplete <- miFlights %>% filter(!is.na(dep_time))
miFlightsMiss <- miFlights %>% filter(is.na(dep_time))Sorting rows with arrange.
# Sort miFlights by the day of the flight (smallest to largest), and print the first 4 columns and 5 rows of the resulting data set using the slice_head() function.
miFlights %>% arrange(day) %>% select(year:sched_dep_time) %>% slice_head(n = 5)## # A tibble: 5 × 5
## year month day dep_time sched_dep_time
## <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 2019 1 1 55 2115
## 2 2019 1 1 455 500
## 3 2019 1 1 506 511
## 4 2019 1 1 531 535
## 5 2019 1 1 534 545# Equivalent code with slice_min()
miFlights %>% select(year:dep_time) %>%
slice_min(day, n = 5, with_ties = FALSE)## # A tibble: 5 × 4
## year month day dep_time
## <dbl> <dbl> <dbl> <dbl>
## 1 2019 1 1 55
## 2 2019 1 1 455
## 3 2019 1 1 506
## 4 2019 1 1 531
## 5 2019 1 1 534miFlights %>% arrange(desc(day)) %>% select(year:sched_dep_time) %>%
slice_head(n = 5)## # A tibble: 5 × 5
## year month day dep_time sched_dep_time
## <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 2019 1 31 59 2225
## 2 2019 1 31 535 545
## 3 2019 1 31 540 530
## 4 2019 1 31 548 527
## 5 2019 1 31 549 549# Equivalent code with slice_max()
miFlights %>% select(year:dep_time) %>%
slice_max(day, n = 5, with_ties = FALSE)## # A tibble: 5 × 4
## year month day dep_time
## <dbl> <dbl> <dbl> <dbl>
## 1 2019 1 31 59
## 2 2019 1 31 535
## 3 2019 1 31 540
## 4 2019 1 31 548
## 5 2019 1 31 549# Sort by year, month, and then day of the flight.
miFlights %>% arrange(year, month, day)## # A tibble: 463,818 × 37
## year month day dep_time sched_de…¹ dep_d…² arr_t…³ sched…⁴ arr_d…⁵ carrier
## <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <chr>
## 1 2019 1 1 55 2115 220 426 2323 303 OH
## 2 2019 1 1 455 500 -5 830 834 -4 YX
## 3 2019 1 1 506 511 -5 710 730 -20 AA
## 4 2019 1 1 531 535 -4 647 710 -23 WN
## 5 2019 1 1 534 545 -11 750 742 8 B6
## 6 2019 1 1 550 600 -10 712 748 -36 YX
## 7 2019 1 1 555 600 -5 822 834 -12 OO
## 8 2019 1 1 555 555 0 709 715 -6 WN
## 9 2019 1 1 555 600 -5 755 817 -22 DL
## 10 2019 1 1 600 600 0 559 615 -16 WN
## # … with 463,808 more rows, 27 more variables: flight <dbl>, tailnum <chr>,
## # origin <chr>, dest <chr>, air_time <dbl>, distance <dbl>, hour <dbl>,
## # minute <dbl>, time_hour <dttm>, temp <dbl>, dewp <dbl>, humid <dbl>,
## # wind_dir <dbl>, wind_speed <dbl>, wind_gust <dbl>, precip <dbl>,
## # pressure <dbl>, visib <dbl>, carrier_name <chr>, plane_year <dbl>,
## # plane_type <chr>, plane_manufacturer <chr>, plane_model <chr>,
## # plane_engines <dbl>, plane_seats <dbl>, plane_speed <dbl>, …miFlights %>% arrange(desc(arr_delay), dep_delay) %>% select(arr_delay, dep_delay) %>%
slice_head(n=3)## # A tibble: 3 × 2
## arr_delay dep_delay
## <dbl> <dbl>
## 1 2649 2672
## 2 1961 1948
## 3 1792 1840miFlights %>%arrange(desc(arr_delay)) %>% slice_head(n=3)## # A tibble: 3 × 37
## year month day dep_time sched_dep…¹ dep_d…² arr_t…³ sched…⁴ arr_d…⁵ carrier
## <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <chr>
## 1 2019 2 17 1400 1728 2672 1531 1922 2649 MQ
## 2 2021 7 12 1643 815 1948 1754 913 1961 G4
## 3 2019 12 19 1402 722 1840 1556 1004 1792 AA
## # … with 27 more variables: flight <dbl>, tailnum <chr>, origin <chr>,
## # dest <chr>, air_time <dbl>, distance <dbl>, hour <dbl>, minute <dbl>,
## # time_hour <dttm>, temp <dbl>, dewp <dbl>, humid <dbl>, wind_dir <dbl>,
## # wind_speed <dbl>, wind_gust <dbl>, precip <dbl>, pressure <dbl>,
## # visib <dbl>, carrier_name <chr>, plane_year <dbl>, plane_type <chr>,
## # plane_manufacturer <chr>, plane_model <chr>, plane_engines <dbl>,
## # plane_seats <dbl>, plane_speed <dbl>, plane_engine <chr>, and abbreviated …miFlights %>% slice_max(arr_delay, n = 3, with_ties = FALSE)## # A tibble: 3 × 37
## year month day dep_time sched_dep…¹ dep_d…² arr_t…³ sched…⁴ arr_d…⁵ carrier
## <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <chr>
## 1 2019 2 17 1400 1728 2672 1531 1922 2649 MQ
## 2 2021 7 12 1643 815 1948 1754 913 1961 G4
## 3 2019 12 19 1402 722 1840 1556 1004 1792 AA
## # … with 27 more variables: flight <dbl>, tailnum <chr>, origin <chr>,
## # dest <chr>, air_time <dbl>, distance <dbl>, hour <dbl>, minute <dbl>,
## # time_hour <dttm>, temp <dbl>, dewp <dbl>, humid <dbl>, wind_dir <dbl>,
## # wind_speed <dbl>, wind_gust <dbl>, precip <dbl>, pressure <dbl>,
## # visib <dbl>, carrier_name <chr>, plane_year <dbl>, plane_type <chr>,
## # plane_manufacturer <chr>, plane_model <chr>, plane_engines <dbl>,
## # plane_seats <dbl>, plane_speed <dbl>, plane_engine <chr>, and abbreviated …miFlights %>%arrange(arr_delay) %>% slice_head(n=3)## # A tibble: 3 × 37
## year month day dep_time sched_dep…¹ dep_d…² arr_t…³ sched…⁴ arr_d…⁵ carrier
## <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <chr>
## 1 2019 1 13 1001 1000 1 1129 1254 -85 DL
## 2 2019 1 26 1255 1257 -2 1445 1606 -81 DL
## 3 2021 1 11 848 855 -7 951 1110 -79 DL
## # … with 27 more variables: flight <dbl>, tailnum <chr>, origin <chr>,
## # dest <chr>, air_time <dbl>, distance <dbl>, hour <dbl>, minute <dbl>,
## # time_hour <dttm>, temp <dbl>, dewp <dbl>, humid <dbl>, wind_dir <dbl>,
## # wind_speed <dbl>, wind_gust <dbl>, precip <dbl>, pressure <dbl>,
## # visib <dbl>, carrier_name <chr>, plane_year <dbl>, plane_type <chr>,
## # plane_manufacturer <chr>, plane_model <chr>, plane_engines <dbl>,
## # plane_seats <dbl>, plane_speed <dbl>, plane_engine <chr>, and abbreviated …miFlights %>% slice_min(arr_delay, n = 3, with_ties = FALSE)## # A tibble: 3 × 37
## year month day dep_time sched_dep…¹ dep_d…² arr_t…³ sched…⁴ arr_d…⁵ carrier
## <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <chr>
## 1 2019 1 13 1001 1000 1 1129 1254 -85 DL
## 2 2019 1 26 1255 1257 -2 1445 1606 -81 DL
## 3 2021 1 11 848 855 -7 951 1110 -79 DL
## # … with 27 more variables: flight <dbl>, tailnum <chr>, origin <chr>,
## # dest <chr>, air_time <dbl>, distance <dbl>, hour <dbl>, minute <dbl>,
## # time_hour <dttm>, temp <dbl>, dewp <dbl>, humid <dbl>, wind_dir <dbl>,
## # wind_speed <dbl>, wind_gust <dbl>, precip <dbl>, pressure <dbl>,
## # visib <dbl>, carrier_name <chr>, plane_year <dbl>, plane_type <chr>,
## # plane_manufacturer <chr>, plane_model <chr>, plane_engines <dbl>,
## # plane_seats <dbl>, plane_speed <dbl>, plane_engine <chr>, and abbreviated …miFlights %>% slice_max(distance / air_time, n = 3, with_ties = FALSE)## # A tibble: 3 × 37
## year month day dep_time sched_dep…¹ dep_d…² arr_t…³ sched…⁴ arr_d…⁵ carrier
## <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <chr>
## 1 2019 7 14 1230 1215 15 1339 1326 13 OO
## 2 2020 8 21 1645 1605 40 1621 1626 -5 OO
## 3 2021 11 21 1000 1000 0 1119 1132 -13 OO
## # … with 27 more variables: flight <dbl>, tailnum <chr>, origin <chr>,
## # dest <chr>, air_time <dbl>, distance <dbl>, hour <dbl>, minute <dbl>,
## # time_hour <dttm>, temp <dbl>, dewp <dbl>, humid <dbl>, wind_dir <dbl>,
## # wind_speed <dbl>, wind_gust <dbl>, precip <dbl>, pressure <dbl>,
## # visib <dbl>, carrier_name <chr>, plane_year <dbl>, plane_type <chr>,
## # plane_manufacturer <chr>, plane_model <chr>, plane_engines <dbl>,
## # plane_seats <dbl>, plane_speed <dbl>, plane_engine <chr>, and abbreviated …miFlights %>% select(-year, -month)## # A tibble: 463,818 × 35
## day dep_time sched…¹ dep_d…² arr_t…³ sched…⁴ arr_d…⁵ carrier flight tailnum
## <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <chr> <dbl> <chr>
## 1 1 55 2115 220 426 2323 303 OH 1019 N567NN
## 2 1 455 500 -5 830 834 -4 YX 954 N433YX
## 3 1 506 511 -5 710 730 -20 AA 185 N853NN
## 4 1 531 535 -4 647 710 -23 WN 203 N227WN
## 5 1 534 545 -11 750 742 8 B6 310 N203JB
## 6 1 550 600 -10 712 748 -36 YX 790 N739YX
## 7 1 555 600 -5 822 834 -12 OO 803 N817SK
## 8 1 555 555 0 709 715 -6 WN 295 N7818L
## 9 1 555 600 -5 755 817 -22 DL 348 N899AT
## 10 1 600 600 0 559 615 -16 WN 218 N906WN
## # … with 463,808 more rows, 25 more variables: origin <chr>, dest <chr>,
## # air_time <dbl>, distance <dbl>, hour <dbl>, minute <dbl>, time_hour <dttm>,
## # temp <dbl>, dewp <dbl>, humid <dbl>, wind_dir <dbl>, wind_speed <dbl>,
## # wind_gust <dbl>, precip <dbl>, pressure <dbl>, visib <dbl>,
## # carrier_name <chr>, plane_year <dbl>, plane_type <chr>,
## # plane_manufacturer <chr>, plane_model <chr>, plane_engines <dbl>,
## # plane_seats <dbl>, plane_speed <dbl>, plane_engine <chr>, and abbreviated …miFlights %>% select(time_hour, air_time, everything(), -day)## # A tibble: 463,818 × 36
## time_hour air_time year month dep_time sched_dep…¹ dep_d…² arr_t…³
## <dttm> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 2019-01-01 21:00:00 88 2019 1 55 2115 220 426
## 2 2019-01-01 05:00:00 187 2019 1 455 500 -5 830
## 3 2019-01-01 05:00:00 162 2019 1 506 511 -5 710
## 4 2019-01-01 05:00:00 64 2019 1 531 535 -4 647
## 5 2019-01-01 05:00:00 71 2019 1 534 545 -11 750
## 6 2019-01-01 06:00:00 61 2019 1 550 600 -10 712
## 7 2019-01-01 06:00:00 125 2019 1 555 600 -5 822
## 8 2019-01-01 05:00:00 174 2019 1 555 555 0 709
## 9 2019-01-01 06:00:00 105 2019 1 555 600 -5 755
## 10 2019-01-01 06:00:00 45 2019 1 600 600 0 559
## # … with 463,808 more rows, 28 more variables: sched_arr_time <dbl>,
## # arr_delay <dbl>, carrier <chr>, flight <dbl>, tailnum <chr>, origin <chr>,
## # dest <chr>, distance <dbl>, hour <dbl>, minute <dbl>, temp <dbl>,
## # dewp <dbl>, humid <dbl>, wind_dir <dbl>, wind_speed <dbl>, wind_gust <dbl>,
## # precip <dbl>, pressure <dbl>, visib <dbl>, carrier_name <chr>,
## # plane_year <dbl>, plane_type <chr>, plane_manufacturer <chr>,
## # plane_model <chr>, plane_engines <dbl>, plane_seats <dbl>, …#Create a subset of the miFlights data set called timeFlights that only contains variables that end with the word "time".
timeFlights <- miFlights %>% select(ends_with("time"))
timeFlights %>% slice_head(n=5)## # A tibble: 5 × 5
## dep_time sched_dep_time arr_time sched_arr_time air_time
## <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 55 2115 426 2323 88
## 2 455 500 830 834 187
## 3 506 511 710 730 162
## 4 531 535 647 710 64
## 5 534 545 750 742 71departureInfo <- miFlights %>% select(starts_with("dep"))
departureInfo %>% slice_head(n=5)## # A tibble: 5 × 2
## dep_time dep_delay
## <dbl> <dbl>
## 1 55 220
## 2 455 -5
## 3 506 -5
## 4 531 -4
## 5 534 -11newFlights <- miFlights %>% select(flight, origin, dest, everything(),
-tailnum)Mutate Function.
flights_sml <- miFlights %>% select(ends_with("delay"), distance, air_time)
flights_sml %>% mutate(gain = dep_delay - arr_delay) %>%
slice_head(n = 5)## # A tibble: 5 × 5
## dep_delay arr_delay distance air_time gain
## <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 220 303 500 88 -83
## 2 -5 -4 1214 187 -1
## 3 -5 -20 986 162 15
## 4 -4 -23 409 64 19
## 5 -11 8 632 71 -19flightSpeeds <- miFlights %>% select(ends_with("delay"), distance, air_time) %>% mutate(gain = dep_delay - arr_delay,
speed = distance / air_time*60)
flightSpeeds %>% slice_head(n=5)## # A tibble: 5 × 6
## dep_delay arr_delay distance air_time gain speed
## <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 220 303 500 88 -83 341.
## 2 -5 -4 1214 187 -1 390.
## 3 -5 -20 986 162 15 365.
## 4 -4 -23 409 64 19 383.
## 5 -11 8 632 71 -19 534.flightSpeeds %>% ggplot(aes( x = speed,
y = gain,
color = distance)) +
geom_point(alpha = 0.1) +
labs(title = "Michigan flights, 2019-2021",
x = "Speed (mph)",
y = "Gain (minutes)",
caption = "Data source: anyFlights R package",
color = "Distance(miles)") +
theme_bw()+
theme(legend.position = "bottom")## Warning: Removed 10239 rows containing missing values (geom_point).
miFlights %>% group_by(year, month, day) %>%
summarize(delay = mean(dep_delay, na.rm = TRUE)) %>%
slice_head(n = 5)## `summarise()` has grouped output by 'year', 'month'. You can override using the
## `.groups` argument.## # A tibble: 180 × 4
## # Groups: year, month [36]
## year month day delay
## <dbl> <dbl> <dbl> <dbl>
## 1 2019 1 1 8.58
## 2 2019 1 2 12.5
## 3 2019 1 3 0.721
## 4 2019 1 4 -0.477
## 5 2019 1 5 2.17
## 6 2019 2 1 27.8
## 7 2019 2 2 13.0
## 8 2019 2 3 1.49
## 9 2019 2 4 7.91
## 10 2019 2 5 1.91
## # … with 170 more rowsdelaySummary <- miFlights %>% group_by(carrier_name) %>%
summarize(Delay = mean(arr_delay, na.rm = T))
delaySummary %>% ggplot(aes( x= fct_reorder(carrier_name, Delay),
y = Delay, fill = Delay > 0)) +
geom_col() +
labs (title = "Average flight delays by carrier",
subtitle = "Michigan Flights, 2019-2021",
x = "Carrier",
y = "Delay (minutes)",
caption = "Data source: anyflights R package") +
scale_fill_manual(values = c("#D55E00", "#0072B2")) +
theme_bw() +
theme(axis.text.x = element_text(angle = 45,
vjust = 0.7),
legend.position = "none")
miFlights %>% group_by(month, origin) %>%
summarize(Delay = median(arr_delay, na.rm = TRUE)) %>%
ggplot(aes(x = month, y = Delay, color = origin)) +
geom_line() +
labs (title = "Average flight delays by month",
subtitle = "Michigan Flights, 2019-2021",
x = "Month",
y = "Delay (minutes)",
caption = "Data source: anyflights R package") +
scale_x_continuous(breaks = 1:12) +
theme_bw()## `summarise()` has grouped output by 'month'. You can override using the
## `.groups` argument.