Nations Assignment

Loading the 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   3.4.4     ✔ 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(htmltools)
library(dplyr)
library(plotly)


Attaching package: 'plotly'

The following object is masked from 'package:ggplot2':

    last_plot

The following object is masked from 'package:stats':

    filter

The following object is masked from 'package:graphics':

    layout

library(ggfortify)
library(RColorBrewer)

Setting the Pathway

setwd("/Users/Mathew/Downloads/Data Sets - 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.

Presenting GDP of each country

nat_mutate <- mutate(nations, gdp_trillion = (gdp_percap*population)/(10^12))

Selecting 4 Nations

gdp4 <- filter(nat_mutate, country %in% c("United States", "China", "Japan", "Germany"))

gdp4

# A tibble: 100 × 11
   iso2c iso3c country  year gdp_percap population birth_rate neonat_mortal_rate
   <chr> <chr> <chr>   <dbl>      <dbl>      <dbl>      <dbl>              <dbl>
 1 CN    CHN   China    1992      1260. 1164970000       18.3               29.4
 2 CN    CHN   China    2005      5053. 1303720000       12.4               14  
 3 CN    CHN   China    2000      2915. 1262645000       14.0               21.2
 4 CN    CHN   China    1991      1091. 1150780000       19.7               29.7
 5 CN    CHN   China    2013     12219. 1357380000       12.1                6.3
 6 CN    CHN   China    1999      2650. 1252735000       14.6               22.2
 7 CN    CHN   China    2014     13255. 1364270000       12.4                5.9
 8 CN    CHN   China    2003      3934. 1288400000       12.4               17.1
 9 CN    CHN   China    2004      4423. 1296075000       12.3               15.5
10 CN    CHN   China    1993      1453. 1178440000       18.1               28.8
# ℹ 90 more rows
# ℹ 3 more variables: region <chr>, income <chr>, gdp_trillion <dbl>

Creating the Visualizations

ggplot(gdp4, aes(x=year, y=gdp_trillion, color=country)) +
  geom_line()+
  geom_point()+
  scale_color_brewer(palette="Set1")+
  labs(x="Year", y="GDP ($ trillion)", title = "China's Rise in Economy", color ="")

Summarizing GDP

gdp_reg<-nat_mutate|>
  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.

gdp_reg

# A tibble: 175 × 3
# Groups:   region [7]
   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
 7 East Asia & Pacific  1996  8.96
 8 East Asia & Pacific  1997  9.55
 9 East Asia & Pacific  1998  9.60
10 East Asia & Pacific  1999 10.1 
# ℹ 165 more rows

Creating another Visualization

options(scipen = 999)
ggplot(gdp_reg, aes(x=year, y=GDP, group=region, fill=region)) +
  geom_area(color="white")+
  scale_fill_brewer(palette="Set2")+
  labs(x="Year", y="GDP ($ trillion)", title = "GDP by World Bank Region")+
  theme_minimal()