Nations’GDP

#install.packages("treemap")
#install.packages("RColorBrewer")
library(treemap)
library(tidyverse)

## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.2 ──
## ✔ ggplot2 3.3.6     ✔ purrr   0.3.4
## ✔ tibble  3.1.7     ✔ dplyr   1.0.9
## ✔ tidyr   1.2.0     ✔ stringr 1.4.0
## ✔ readr   2.1.2     ✔ forcats 0.5.1
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()

library(RColorBrewer)
library(ggplot2)

Read the data

setwd("C:/Data 110.MC") 
nations <- read_csv("nations.hw6.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.

head(nations)

## # A tibble: 6 × 10
##   iso2c iso3c country  year gdp_percap population birth_…¹ neona…² region income
##   <chr> <chr> <chr>   <dbl>      <dbl>      <dbl>    <dbl>   <dbl> <chr>  <chr> 
## 1 AD    AND   Andorra  1996         NA      64291     10.9     2.8 Europ… High …
## 2 AD    AND   Andorra  1994         NA      62707     10.9     3.2 Europ… High …
## 3 AD    AND   Andorra  2003         NA      74783     10.3     2   Europ… High …
## 4 AD    AND   Andorra  1990         NA      54511     11.9     4.3 Europ… High …
## 5 AD    AND   Andorra  2009         NA      85474      9.9     1.7 Europ… High …
## 6 AD    AND   Andorra  2011         NA      82326     NA       1.6 Europ… High …
## # … with abbreviated variable names ¹​birth_rate, ²​neonat_mortal_rate

s1 <- nations %>%   
  filter(!is.na(gdp_percap))  # remove na's 

s2 <-s1 %>% mutate(GDPc=((gdp_percap*population)/1e+12)) # calculate GDP per population
head (s2)

## # A tibble: 6 × 11
##   iso2c iso3c country   year gdp_p…¹ popul…² birth…³ neona…⁴ region income  GDPc
##   <chr> <chr> <chr>    <dbl>   <dbl>   <dbl>   <dbl>   <dbl> <chr>  <chr>  <dbl>
## 1 AE    ARE   United …  1991  73037. 1913190    24.6     7.9 Middl… High … 0.140
## 2 AE    ARE   United …  1993  71960. 2127863    22.4     7.3 Middl… High … 0.153
## 3 AE    ARE   United …  2001  83534. 3217865    15.8     5.5 Middl… High … 0.269
## 4 AE    ARE   United …  1992  73154. 2019014    23.5     7.6 Middl… High … 0.148
## 5 AE    ARE   United …  1994  74684. 2238281    21.3     6.9 Middl… High … 0.167
## 6 AE    ARE   United …  2007  75427. 6010100    12.8     4.7 Middl… High … 0.453
## # … with abbreviated variable names ¹​gdp_percap, ²​population, ³​birth_rate,
## #   ⁴​neonat_mortal_rate

s3 <- s2 %>%
filter(country == "Israel" | country == "Egypt, Arab Rep." | country =="Turkey" | country == "Germany") # selected 4 countries

ggplot(s3, aes(x = year, y = GDPc )) +
  labs(title = "GDP by four countries",
  caption = "Source: International GDP data") +
  xlab("Country") +
  ylab ("Calculated GDP ratio") +
  theme_minimal(base_size = 12)

p1 <- ggplot(s3, aes(x = year, y = GDPc, color=country )) +
  labs(title = "GDP by four countries",
  caption = "Source: International GDP data") +
  xlab("Country") +
  ylab ("Calculated GDP ratio") +
  theme_minimal(base_size = 12)
  p1 + geom_point()+
       geom_line()

p2<- p1+ scale_colour_brewer(palette = "Set1") 

s4 <-nations %>%               # by statement
  group_by(region, year)

s4 <- s4 %>%
  summarise(GDPc = sum(gdp_percap, na.rm = TRUE)) # remove NA

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

options(scipen = 999)

A1 <- ggplot(s4, aes(x = year, y = GDPc, fill=region )) +
  labs(title = "GDP by region",
  caption = "Source: International GDP data") +
  xlab("Country") +
  ylab (" Total GDP") +
  theme_minimal(base_size = 12)
  A1 + geom_area ()

  A2<- A1+ scale_fill_brewer(palette = "Set2") 

Note:From 1990 to 2015 the most significant GDP growth occurred in East Asia & Pacific. In contrast, the lowest change in GDP occurred Sub-Saharan Africa, and the USA is in the middle range of regional GDP growth.