Homework 7 Nations Charts

Loading Library

library(tidyverse)

## -- Attaching packages --------------------------------------- tidyverse 1.3.1 --

## v ggplot2 3.3.5     v purrr   0.3.4
## v tibble  3.1.5     v dplyr   1.0.7
## v tidyr   1.1.4     v stringr 1.4.0
## v readr   2.0.2     v forcats 0.5.1

## -- Conflicts ------------------------------------------ tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag()    masks stats::lag()

library(dplyr)
library(ggplot2)
library(scales)

## 
## Attaching package: 'scales'

## The following object is masked from 'package:purrr':
## 
##     discard

## The following object is masked from 'package:readr':
## 
##     col_factor

Data Preparation

library(readr)
setwd("C:/Users/Jerem/Downloads")
#rerading dataset into spotify
nations <- read_csv("~/Montgomery College/Fall 2021/DATA 110/Datasets/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.

#view(nations)

Data Preparation Summary

nations %>% head() %>% knitr::kable()

iso2c	iso3c	country	year	gdp_percap	population	birth_rate	neonat_mortal_rate	region	income
AD	AND	Andorra	1996	NA	64291	10.9	2.8	Europe & Central Asia	High income
AD	AND	Andorra	1994	NA	62707	10.9	3.2	Europe & Central Asia	High income
AD	AND	Andorra	2003	NA	74783	10.3	2.0	Europe & Central Asia	High income
AD	AND	Andorra	1990	NA	54511	11.9	4.3	Europe & Central Asia	High income
AD	AND	Andorra	2009	NA	85474	9.9	1.7	Europe & Central Asia	High income
AD	AND	Andorra	2011	NA	82326	NA	1.6	Europe & Central Asia	High income

Mutating Variable

nations1 <- mutate(nations, GDP = gdp_percap*population/10**12)

Chart One

nations2 <- filter(nations1, country == "Brazil" | country == "Japan" | country == "France" | country == "United States")

ggplot(nations2, aes(x = year, y = GDP, color = country)) +
  geom_point() +
  geom_line() +
  ggtitle("National Economic Performance") +
  labs(x = "Years",
       y = "GDP ($Trillions)") +
  scale_color_brewer(palette = "Set1")

Grouping and Summarize Variables

nations3 <- nations1 %>%
  group_by(region, year) %>%
  summarise(GDP = sum(GDP, na.rm = TRUE))

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

Chart Two

ggplot(nations3, aes(x = year, y = GDP)) +
  geom_area(color = "white", aes(fill = region)) +
  ggtitle("GDP by Region") +
  labs(x = "Years",
       y = "GDP ($ Trillions)") +
  scale_color_brewer(palette = "Set2")