Week7

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

## 
## Attaching package: 'dplyr'

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

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

## 
## Attaching package: 'plotly'
setwd("C:/Users/munis/Documents/Comm in Data Science/Datasets")
nations <- read_csv('nations.csv')

## Parsed with 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()
## )

## Parsed with column specification:
## cols(
##   state = col_character(),
##   murder = col_double(),
##   forcible_rape = col_double(),
##   robbery = col_double(),
##   aggravated_assault = col_double(),
##   burglary = col_double(),
##   larceny_theft = col_double(),
##   motor_vehicle_theft = col_double(),
##   population = col_double()
## )
head(nations)

## # A tibble: 6 x 10
##   iso2c iso3c country  year gdp_percap population birth_rate
##   <chr> <chr> <chr>   <dbl>      <dbl>      <dbl>      <dbl>
## 1 AD    AND   Andorra  1996         NA      64291       10.9
## 2 AD    AND   Andorra  1994         NA      62707       10.9
## 3 AD    AND   Andorra  2003         NA      74783       10.3
## 4 AD    AND   Andorra  1990         NA      54511       11.9
## 5 AD    AND   Andorra  2009         NA      85474        9.9
## 6 AD    AND   Andorra  2011         NA      82326       NA  
## # ... with 3 more variables: neonat_mortal_rate <dbl>, region <chr>,
## #   income <chr>

#nations <- nations %>%
#  filter( id== "China" | id == "Germany" | id == "Japan" | id == "United States")

nations2 <- nations %>%
  mutate(GDP = (gdp_percap * population)/1000000000000) %>%
  filter(country == "China" | country == "Germany" | country == "Japan" | country == "United States")
head(nations2)

## # A tibble: 6 x 11
##   iso2c iso3c country  year gdp_percap population birth_rate
##   <chr> <chr> <chr>   <dbl>      <dbl>      <dbl>      <dbl>
## 1 CN    CHN   China    1992      1260. 1164970000       18.3
## 2 CN    CHN   China    2005      5053. 1303720000       12.4
## 3 CN    CHN   China    2000      2915. 1262645000       14.0
## 4 CN    CHN   China    1991      1091. 1150780000       19.7
## 5 CN    CHN   China    2013     12219. 1357380000       12.1
## 6 CN    CHN   China    1999      2650. 1252735000       14.6
## # ... with 4 more variables: neonat_mortal_rate <dbl>, region <chr>,
## #   income <chr>, GDP <dbl>

p1 <- ggplot(nations2, aes(year, GDP, color=country)) +
  xlab("year") + 
  ylab("GDP ($trillion)") +
  scale_color_brewer(palette = "Set1")
p1 + 
  geom_line() +
  geom_point()

p2 <- nations %>%
  group_by(region, year) %>%
  summarise(sum = sum(gdp_percap, na.rm = TRUE)) 
p2

## # A tibble: 175 x 3
## # Groups:   region [7]
##    region               year     sum
##    <chr>               <dbl>   <dbl>
##  1 East Asia & Pacific  1990 213116.
##  2 East Asia & Pacific  1991 234287.
##  3 East Asia & Pacific  1992 246209.
##  4 East Asia & Pacific  1993 257732.
##  5 East Asia & Pacific  1994 272159.
##  6 East Asia & Pacific  1995 286105.
##  7 East Asia & Pacific  1996 296956.
##  8 East Asia & Pacific  1997 304359.
##  9 East Asia & Pacific  1998 298089.
## 10 East Asia & Pacific  1999 307967.
## # ... with 165 more rows

plot2 <- ggplot(p2, aes(x = year, y = sum, fill=region)) +
    scale_fill_brewer(palette = "Set2") +
  xlab("year") + 
  ylab("GDP ($trillion)") 
plot2 + 
  geom_area(color = "white")