https://datacatalog.worldbank.org/search/dataset/0038117/Global-Airports
##1. import libraries
library(tidyverse)
## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.2 ──
## ✔ ggplot2 3.3.6 ✔ purrr 0.3.4
## ✔ tibble 3.1.8 ✔ dplyr 1.0.9
## ✔ tidyr 1.2.0 ✔ 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(dplyr)
library(ggplot2)
##2. import data
airport <- read_csv("airport_volume_airport_locations.csv")
## Rows: 2173 Columns: 6
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (3): Orig, Name, Country Name
## dbl (3): TotalSeats, Airport1Latitude, Airport1Longitude
##
## 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.
##3. how many total seats does every country have?
totalseats <- data.frame(airport$`Country Name`, airport$TotalSeats)
options(scipen = 999)
countrytotalseats <- totalseats%>% group_by(airport..Country.Name.)%>%summarise_if(is.numeric, sum, names=TRUE)
countrytotalseats
## # A tibble: 224 × 2
## airport..Country.Name. airport.TotalSeats
## <chr> <dbl>
## 1 Afghanistan 1175319.
## 2 Albania 2063324.
## 3 Algeria 5796918.
## 4 Angola 1235517.
## 5 Anguilla 28512.
## 6 Antigua and Barbuda 631488.
## 7 Argentina 9154321.
## 8 Armenia 1947468.
## 9 Aruba 3390249.
## 10 Australia 27365886.
## # … with 214 more rows
##4. create a histogram to show total seats in every countries’ airports
countrytotalseats01 <- ggplot(countrytotalseats, aes(x=airport..Country.Name., y=airport.TotalSeats)) + geom_bar(stat="identity",col="#8D25D1") + labs(title = "Total seats in every countries' airports", x = "Countries", y ="Count")
countrytotalseats01