Load the libraries and view the “flights” dataset
library(tidyverse)
## Warning: package 'tidyverse' was built under R version 3.6.3
## -- Attaching packages ---------------------------------------------------------------------------------------------------------------------------------------------- tidyverse 1.3.0 --
## v ggplot2 3.2.1 v purrr 0.3.4
## v tibble 3.0.3 v dplyr 1.0.1
## v tidyr 1.1.1 v stringr 1.4.0
## v readr 1.3.1 v forcats 0.5.0
## Warning: package 'ggplot2' was built under R version 3.6.2
## Warning: package 'tibble' was built under R version 3.6.3
## Warning: package 'tidyr' was built under R version 3.6.3
## Warning: package 'readr' was built under R version 3.6.3
## Warning: package 'purrr' was built under R version 3.6.3
## Warning: package 'dplyr' was built under R version 3.6.3
## Warning: package 'forcats' was built under R version 3.6.3
## -- Conflicts ------------------------------------------------------------------------------------------------------------------------------------------------- tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()
library(nycflights13)
## Warning: package 'nycflights13' was built under R version 3.6.3
library(psych)
##
## Attaching package: 'psych'
## The following objects are masked from 'package:ggplot2':
##
## %+%, alpha
view(flights)
library(dplyr)
flights_df <- data.frame(flights)
str(flights_df)
## 'data.frame': 336776 obs. of 19 variables:
## $ year : int 2013 2013 2013 2013 2013 2013 2013 2013 2013 2013 ...
## $ month : int 1 1 1 1 1 1 1 1 1 1 ...
## $ day : int 1 1 1 1 1 1 1 1 1 1 ...
## $ dep_time : int 517 533 542 544 554 554 555 557 557 558 ...
## $ sched_dep_time: int 515 529 540 545 600 558 600 600 600 600 ...
## $ dep_delay : num 2 4 2 -1 -6 -4 -5 -3 -3 -2 ...
## $ arr_time : int 830 850 923 1004 812 740 913 709 838 753 ...
## $ sched_arr_time: int 819 830 850 1022 837 728 854 723 846 745 ...
## $ arr_delay : num 11 20 33 -18 -25 12 19 -14 -8 8 ...
## $ carrier : chr "UA" "UA" "AA" "B6" ...
## $ flight : int 1545 1714 1141 725 461 1696 507 5708 79 301 ...
## $ tailnum : chr "N14228" "N24211" "N619AA" "N804JB" ...
## $ origin : chr "EWR" "LGA" "JFK" "JFK" ...
## $ dest : chr "IAH" "IAH" "MIA" "BQN" ...
## $ air_time : num 227 227 160 183 116 150 158 53 140 138 ...
## $ distance : num 1400 1416 1089 1576 762 ...
## $ hour : num 5 5 5 5 6 5 6 6 6 6 ...
## $ minute : num 15 29 40 45 0 58 0 0 0 0 ...
## $ time_hour : POSIXct, format: "2013-01-01 05:00:00" "2013-01-01 05:00:00" ...
typeof(flights_df)
## [1] "list"
flights_df$month <- as.factor(flights_df$month)
flights_df$month <- month.abb[flights_df$month]
plot1 <- flights_df %>% filter(month == "Dec" | month == "Jan" | month == "Feb" | month == "Jun" | month == "Jul" | month == "Aug" ) %>% ggplot(mapping = aes(x = dep_delay, y = arr_delay, colour = air_time)) +
geom_point(alpha = 0.3) + facet_wrap(~ month) + scale_colour_gradient2()
print(plot1 + ggtitle("Arrival Delays and Departure Delays for Winter and Summer Months")
+ labs(y = "Arrival Delays (in Seconds)", x = "Departure Delays (in Seconds)"))
## Warning: Removed 5932 rows containing missing values (geom_point).
## Now create one data visualization with this dataset
##Your assignment is to create one plot to visualize one aspect of this dataset. The plot may be any type we have covered so far in this class (bargraphs, scatterplots, boxplots, histograms, treemaps, heatmaps, streamgraphs, or alluvials)
#### Requirements for the plot:
##1. Include at least one dplyr command (filter, sort, summarize, group_by, select, mutate, ….)
##2. Include labels for the x- and y-axes
##3. Include a title
##4. Your plot must incorporate at least 2 colors
##5. Include a legend that indicates what the colors represent