Untitled
Nate Jack
3/1/2022
library(tidyverse)## -- Attaching packages --------------------------------------- tidyverse 1.3.1 --## v ggplot2 3.3.5 v purrr 0.3.4
## v tibble 3.1.6 v dplyr 1.0.7
## v tidyr 1.1.4 v stringr 1.4.0
## v readr 2.1.1 v forcats 0.5.1## -- Conflicts ------------------------------------------ tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()library(nycflights13)
library(psych)##
## Attaching package: 'psych'## The following objects are masked from 'package:ggplot2':
##
## %+%, alpha#view(flights)
describe(flights)## Warning in FUN(newX[, i], ...): no non-missing arguments to min; returning Inf## Warning in FUN(newX[, i], ...): no non-missing arguments to max; returning -Inf## vars n mean sd median trimmed mad min max
## year 1 336776 2013.00 0.00 2013 2013.00 0.00 2013 2013
## month 2 336776 6.55 3.41 7 6.56 4.45 1 12
## day 3 336776 15.71 8.77 16 15.70 11.86 1 31
## dep_time 4 328521 1349.11 488.28 1401 1346.82 634.55 1 2400
## sched_dep_time 5 336776 1344.25 467.34 1359 1341.60 613.80 106 2359
## dep_delay 6 328521 12.64 40.21 -2 3.32 5.93 -43 1301
## arr_time 7 328063 1502.05 533.26 1535 1526.42 619.73 1 2400
## sched_arr_time 8 336776 1536.38 497.46 1556 1550.67 618.24 1 2359
## arr_delay 9 327346 6.90 44.63 -5 -1.03 20.76 -86 1272
## carrier* 10 336776 7.14 4.14 6 7.00 5.93 1 16
## flight 11 336776 1971.92 1632.47 1496 1830.51 1608.62 1 8500
## tailnum* 12 334264 1814.32 1199.75 1798 1778.21 1587.86 1 4043
## origin* 13 336776 1.95 0.82 2 1.94 1.48 1 3
## dest* 14 336776 50.03 28.12 50 49.56 32.62 1 105
## air_time 15 327346 150.69 93.69 129 140.03 75.61 20 695
## distance 16 336776 1039.91 733.23 872 955.27 569.32 17 4983
## hour 17 336776 13.18 4.66 13 13.15 5.93 1 23
## minute 18 336776 26.23 19.30 29 25.64 23.72 0 59
## time_hour 19 336776 NaN NA NA NaN NA Inf -Inf
## range skew kurtosis se
## year 0 NaN NaN 0.00
## month 11 -0.01 -1.19 0.01
## day 30 0.01 -1.19 0.02
## dep_time 2399 -0.02 -1.09 0.85
## sched_dep_time 2253 -0.01 -1.20 0.81
## dep_delay 1344 4.80 43.95 0.07
## arr_time 2399 -0.47 -0.19 0.93
## sched_arr_time 2358 -0.35 -0.38 0.86
## arr_delay 1358 3.72 29.23 0.08
## carrier* 15 0.36 -1.21 0.01
## flight 8499 0.66 -0.85 2.81
## tailnum* 4042 0.17 -1.24 2.08
## origin* 2 0.09 -1.50 0.00
## dest* 104 0.13 -1.08 0.05
## air_time 675 1.07 0.86 0.16
## distance 4966 1.13 1.19 1.26
## hour 22 0.00 -1.21 0.01
## minute 59 0.09 -1.24 0.03
## time_hour -Inf NA NA NALAX_flights <- flights %>%
filter(dest == "LAX")If want departure delays of flights going to LAX, so I filtered the data for flights headed to LAX by doing (dest == “LAX”) Below is+6 a histogram of only departure delays of only those flights.
ggplot(data = LAX_flights, aes(x = dep_delay)) +
geom_histogram()## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.## Warning: Removed 98 rows containing non-finite values (stat_bin).
LAX_feb_flights <- flights %>%
filter(dest == "LAX", month == 2)I want to look at those flights going to LAX in February:
ggplot(data=LAX_feb_flights, aes(x=arr_delay)) + geom_histogram(bins = 50)## Warning: Removed 43 rows containing non-finite values (stat_bin).
I want to look at every origin of planes going to LAX in February (Only EWR and JFK go to LAX in February)
ggplot(data=LAX_feb_flights, aes(x= origin, y=arr_delay)) + geom_boxplot()## Warning: Removed 43 rows containing non-finite values (stat_boxplot).
arrival_more_than_one_hour_delayed <- filter(LAX_feb_flights, arr_delay >60)
summary(LAX_feb_flights$arr_delay)## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## -68.000 -24.000 -11.000 -7.602 2.000 210.000 43I want to look at every origin of planes going to LAX in February (Only EWR and JFK go to LAX in February) and their arrival delay that is more than 1 hour.
ggplot(data=arrival_more_than_one_hour_delayed, aes(x= origin, y=arr_delay)) + geom_boxplot()
### This shows the dataset flights, I mutated a new variable called “avg_speed”. I figured that average speed is distance diveded by the ait time. This means the distance traveled and the amount of time the plane in is the air.
flights <- flights %>%
mutate(avg_speed = distance / (air_time/60))distance_2 <- filter(flights, distance < 3000)The x variable is distance and the y variable is avg_speed from dataset “flights”
filter(flights, distance < 3000)%>%
ggplot(data = distance_2, mapping = aes(distance,avg_speed, color = origin)) +
geom_point()## Warning: Removed 9424 rows containing missing values (geom_point).
flights_nona <- flights %>%
filter(!is.na(distance) & !is.na(arr_delay) & !is.na(dep_delay)) Create a dataframe that is composed of summary statistics
delays <- flights_nona %>% # create a delays dataframe by:
group_by (origin, month) %>% # grouping by point of destination
summarize (count = n(), # creating variables: number of flights to each destination,
dist = mean (distance), # the mean distance flown to each destination,
avg_arr_delay = mean (arr_delay), # the mean delay of arrival to each destination,
avg_dep_delay = mean (dep_delay))## `summarise()` has grouped output by 'origin'. You can override using the `.groups` argument.ggplot(data = delays, aes(x = month, avg_arr_delay, color = origin)) +
geom_point()+
geom_line(lwd = 3) +xlab("month") +ylab("Average Arrival Delay")+
ggtitle("Average Arrival Delays for Each Origin")