nealhoage wk 7

getwd()

## [1] "/Users/h0age/Documents/data110/Week 7"

setwd("/Users/h0age/Documents/data110/Week 7")
library(tidyverse)

## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.0 ──

## ✓ ggplot2 3.3.3     ✓ purrr   0.3.4
## ✓ tibble  3.1.0     ✓ dplyr   1.0.4
## ✓ tidyr   1.1.2     ✓ stringr 1.4.0
## ✓ readr   1.4.0     ✓ forcats 0.5.1

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

library(dbplyr)

## 
## Attaching package: 'dbplyr'

## The following objects are masked from 'package:dplyr':
## 
##     ident, sql

library(RColorBrewer)
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()
## )

look at structure of data

colnames(nations)

##  [1] "iso2c"              "iso3c"              "country"           
##  [4] "year"               "gdp_percap"         "population"        
##  [7] "birth_rate"         "neonat_mortal_rate" "region"            
## [10] "income"

Make a new variable GDP for each country in trillions of dollars, by multiplying gdp_percap by population and dividing by a trillion.

natl_gdp <- nations %>% ## new data frame natl_gdp using nations data
   mutate(GDP = gdp_percap * population / 1000000000000) ## create new GDP column from percap gdp and population
natl_gdp

## # A tibble: 5,275 x 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
##  7 AD    AND   Andorra  2004         NA      78337       10.9                2  
##  8 AD    AND   Andorra  2010         NA      84419        9.8                1.7
##  9 AD    AND   Andorra  2001         NA      67770       11.8                2.1
## 10 AD    AND   Andorra  2002         NA      71046       11.2                2.1
## # … with 5,265 more rows, and 3 more variables: region <chr>, income <chr>,
## #   GDP <dbl>

new object china_rise - filter out China Gernmany Japan US

china_rise <- natl_gdp %>% ## new object
  filter(country == "China" | country == "Germany" | country == "Japan" | country == "United States")

plot 1

plot1 <- china_rise %>% ## new object into 
  ggplot(aes(year, GDP, color = country)) + 
  geom_point() + ## denotes point graph
  geom_line() + ## adds line connecting dots
  ylab("GDP $ Trillions") + ## edit y axis label

  scale_colour_brewer(palette = "Set1") + ## sets color pallet
  ggtitle("China's Rise to Become the World's Largest Economy") ## sets title

plot1

new object by_region displaying data by region

by_region <- natl_gdp %>% ## new object grouping by region
  group_by(region, year) %>% ## grouping by region
  summarise(GDP = sum(GDP, na.rm = TRUE)) ##%>% ## remove NA data from GDP

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

plot 2 (b)

plot2b <- by_region %>% ## using by_
  ggplot(aes(x = year, y = GDP, fill = region)) + ## parameters of the chart
  geom_area(color = "white") + ## area plot
  ## scale_fill_brewer(palette = "Set2") + ## set color pallet
  theme_dark()
  ##scale_fill_discrete(name = "Region") + ## labeling for legend 

plot2b