Nationa Assignement 2nd attempt

Download Libraries

library(tidyverse)

── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
✔ dplyr     1.1.4     ✔ readr     2.1.5
✔ forcats   1.0.0     ✔ stringr   1.5.1
✔ ggplot2   3.5.1     ✔ tibble    3.2.1
✔ lubridate 1.9.3     ✔ tidyr     1.3.1
✔ purrr     1.0.2     
── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
✖ dplyr::filter() masks stats::filter()
✖ dplyr::lag()    masks stats::lag()
ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors

library(dplyr)
library(ggplot2)
library(RColorBrewer)
library(readr)

Download Dataset

getwd()

[1] "C:/Users/cbash/OneDrive/Desktop/DATA 110"

setwd("C:/Users/cbash/OneDrive/desktop/data 110")
Nations <- read_csv("nations.csv")

Rows: 5275 Columns: 10
── Column specification ────────────────────────────────────────────────────────
Delimiter: ","
chr (5): iso2c, iso3c, country, region, income
dbl (5): year, gdp_percap, population, birth_rate, neonat_mortal_rate

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.

##Create a new variable

nations <- Nations %>%
  mutate(gdp_trillion = gdp_percap * population / 10^12)
head(nations)

# A tibble: 6 × 11
  iso2c iso3c country  year gdp_percap population birth_rate neonat_mortal_rate
  <chr> <chr> <chr>   <dbl>      <dbl>      <dbl>      <dbl>              <dbl>
1 AD    AND   Andorra  1996         NA      64291       10.9                2.8
2 AD    AND   Andorra  1994         NA      62707       10.9                3.2
3 AD    AND   Andorra  2003         NA      74783       10.3                2  
4 AD    AND   Andorra  1990         NA      54511       11.9                4.3
5 AD    AND   Andorra  2009         NA      85474        9.9                1.7
6 AD    AND   Andorra  2011         NA      82326       NA                  1.6
# ℹ 3 more variables: region <chr>, income <chr>, gdp_trillion <dbl>

##Filter the data for the four desired countries

Most_populated_countries <- c("United States", "China", "India", "Indonesia")  
filtered_data <- nations %>%
  filter(country %in% Most_populated_countries)
head(Most_populated_countries)

[1] "United States" "China"         "India"         "Indonesia"    

Create a dot line plot - Chart #1

ggplot(filtered_data, aes(x=year, y=gdp_trillion, color = country)) +
  geom_point()+
  geom_line()+
  scale_color_brewer(palette = "Set1") +
  labs(title = "GDP Over the Most Popluated Countries",
       X = "Year",
       Y = "GDP ($trillion)",
       Color = "Country")+
    theme_minimal()

Group by region and year, then summarize the GDP

summarise_data <- nations %>%
  group_by(region, year) %>%
  summarise(GDP = sum(gdp_trillion,na.rm = TRUE))

`summarise()` has grouped output by 'region'. You can override using the
`.groups` argument.

head(summarise_data)

# A tibble: 6 × 3
# Groups:   region [1]
  region               year   GDP
  <chr>               <dbl> <dbl>
1 East Asia & Pacific  1990  5.52
2 East Asia & Pacific  1991  6.03
3 East Asia & Pacific  1992  6.50
4 East Asia & Pacific  1993  7.04
5 East Asia & Pacific  1994  7.64
6 East Asia & Pacific  1995  8.29

Create Chart #2

ggplot(summarise_data, aes(x= year, y = GDP, fill = region))+
  geom_area(color= "white", size = 0.2) +
  scale_fill_brewer(palette = "Set2") +
  labs(title = "Total GDP by Region Over Time",
       x = "Year",
       Y = "Total GDP (Trillions)",
       fill = "Region") +
  theme_minimal()

Warning: Using `size` aesthetic for lines was deprecated in ggplot2 3.4.0.
ℹ Please use `linewidth` instead.