library(tidyverse)
## -- Attaching packages --------------------------------------- tidyverse 1.3.0 --
## v ggplot2 3.3.3 v purrr 0.3.4
## v tibble 3.0.6 v dplyr 1.0.3
## v tidyr 1.1.2 v stringr 1.4.0
## v readr 1.4.0 v forcats 0.5.1
## -- Conflicts ------------------------------------------ tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()
setwd("C:/Users/noahz/Desktop/Data 110 R/Datasets/Hate crime data sets")
nations <- read_csv("nations.csv")
##
## -- Column specification --------------------------------------------------------
## cols(
## iso2c = col_character(),
## iso3c = col_character(),
## country = col_character(),
## year = col_double(),
## gdp_percap = col_double(),
## population = col_double(),
## birth_rate = col_double(),
## neonat_mortal_rate = col_double(),
## region = col_character(),
## income = col_character()
## )
nations_GDP <- nations%>%
mutate(GDP = (gdp_percap * population)/1000000000000) %>%
filter(iso3c == "ARE" | iso3c == "GBR" | iso3c == "FRA" | iso3c == "DEU")
nations_GDP
## # A tibble: 100 x 11
## iso2c iso3c country year gdp_percap population birth_rate neonat_mortal_r~
## <chr> <chr> <chr> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 AE ARE United~ 1991 73037. 1913190 24.6 7.9
## 2 AE ARE United~ 1993 71960. 2127863 22.4 7.3
## 3 AE ARE United~ 2001 83534. 3217865 15.8 5.5
## 4 AE ARE United~ 1992 73154. 2019014 23.5 7.6
## 5 AE ARE United~ 1994 74684. 2238281 21.3 6.9
## 6 AE ARE United~ 2007 75427. 6010100 12.8 4.7
## 7 AE ARE United~ 2004 87844. 3975945 14.2 5.1
## 8 AE ARE United~ 1996 79480. 2467726 19.3 6.4
## 9 AE ARE United~ 2006 82754. 5171255 13.3 4.9
## 10 AE ARE United~ 2000 84975. 3050128 16.4 5.6
## # ... with 90 more rows, and 3 more variables: region <chr>, income <chr>,
## # GDP <dbl>
summary(nations_GDP)
## iso2c iso3c country year
## Length:100 Length:100 Length:100 Min. :1990
## Class :character Class :character Class :character 1st Qu.:1996
## Mode :character Mode :character Mode :character Median :2002
## Mean :2002
## 3rd Qu.:2008
## Max. :2014
## gdp_percap population birth_rate neonat_mortal_rate
## Min. :17446 Min. : 1811458 Min. : 8.10 Min. :2.200
## 1st Qu.:24233 1st Qu.:45207224 1st Qu.:10.99 1st Qu.:2.700
## Median :34657 Median :60448960 Median :12.60 Median :3.200
## Mean :40656 Mean :52109693 Mean :12.67 Mean :3.657
## 3rd Qu.:48857 3rd Qu.:69730212 3rd Qu.:13.10 3rd Qu.:4.225
## Max. :87844 Max. :82534176 Max. :25.77 Max. :8.200
## region income GDP
## Length:100 Length:100 Min. :0.1341
## Class :character Class :character 1st Qu.:0.9034
## Mode :character Mode :character Median :1.6934
## Mean :1.5896
## 3rd Qu.:2.2692
## Max. :3.7571
GDPs <- ggplot(nations_GDP, aes(x = year, y = GDP)) +
labs(title = "GDP of 5 Countries") +
xlab("Year") +
ylab("GDP ($trillions)") +
theme_minimal(base_size = 13)
GDPs +
geom_line(aes(color = country)) +
geom_point(aes(color = country)) +
scale_color_brewer(palette = "Set1")
nations_test <- nations %>%
mutate(GDP = (gdp_percap * population)/1000000000000) %>%
group_by(region, year) %>%
summarise(GDP = sum(GDP, na.rm = TRUE))
## `summarise()` has grouped output by 'region'. You can override using the `.groups` argument.
GDP_area <- ggplot(nations_test) +
labs(title = "GDP by World Bank Region") +
xlab("Year") +
ylab("GDP ($trillions)") +
theme_minimal(base_size = 13)
GDP_area +
geom_area(aes(x = year, y = GDP, fill = region)) +
scale_fill_brewer(palette = "Set2")
