Week 9 Class Work

# highcharter in R

# highcharter is an R package used to create interactive charts. 

# install.packages(c("highcharter", "RColorBrewer", "dplyr"))

library(highcharter) # for interactive charts

Registered S3 method overwritten by 'quantmod':
  method            from
  as.zoo.data.frame zoo 

library(RColorBrewer) # for color palettes
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(tidyverse)

── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
✔ forcats   1.0.1     ✔ readr     2.2.0
✔ ggplot2   4.0.3     ✔ stringr   1.6.0
✔ lubridate 1.9.5     ✔ tibble    3.3.1
✔ purrr     1.2.2     ✔ tidyr     1.3.2
── 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

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.

nations <- read_csv("nations.csv") |>
  mutate(gdp_tn = gdp_percap*population/10^12)

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.

Make a version of the “China’s rise” chart from unit 3 assignment

# prepare data
big4 <- nations |>
  filter(iso3c %in% c("CHN","DEU", "JPN", "USA")) |>
  arrange(year)

# basic symbol-and-line chart, default settings
highchart() |>
  hc_add_series(data = big4,
                type = "line", 
                hcaes(x = year,
                      y = gdp_tn, 
                      group = country))

# Use a ColorBrewer palette
# define color palette
cols <- brewer.pal(4, "Set1")

highchart() |>
  hc_add_series(data = big4,
                type = "line", hcaes(x = year,
                                     y = gdp_tn, 
                                     group = country)) |>
  hc_colors(cols)

# label axis 
highchart() |>
  hc_add_series(data = big4,
                type = "line",
                hcaes(x = year,
                      y = gdp_tn, 
                      group = country)) |>
  hc_colors(cols) |>
  hc_xAxis(title = list(text="Year")) |>
  hc_yAxis(title = list(text="GDP ($ trillion)"))

# change legend position

highchart() |>
  hc_add_series(data = big4,
                type = "line",
                hcaes(x = year,
                      y = gdp_tn, 
                      group = country)) |>
  hc_colors(cols) |>
  hc_xAxis(title = list(text="Year")) |>
  hc_yAxis(title = list(text="GDP ($ trillion)")) |>
  hc_plotOptions(series = list(marker = list(symbol = "circle"))) |>
  hc_legend(align = "right", 
            verticalAlign = "top")

# customize the tooltips

big4_chart <- highchart() |>
  hc_add_series(data = big4,
                type = "line",
                hcaes(x = year,
                      y = gdp_tn, 
                      group = country)) |>
  hc_colors(cols) |>
  hc_xAxis(title = list(text="Year")) |>
  hc_yAxis(title = list(text="GDP ($ trillion)")) |>
  hc_plotOptions(series = list(marker = list(symbol = "circle"))) |>
  hc_legend(align = "right", 
            verticalAlign = "top") |>
  hc_tooltip(shared = TRUE,
             borderColor = "black",
             pointFormat = "{point.country}: {point.gdp_tn:.2f}")
big4_chart

# prepare data

regions <- nations |>
  group_by(year,region) |>
  summarize(gdp_tn = sum(gdp_tn, na.rm = TRUE)) |>
  arrange(year,region)

`summarise()` has regrouped the output.
ℹ Summaries were computed grouped by year and region.
ℹ Output is grouped by year.
ℹ Use `summarise(.groups = "drop_last")` to silence this message.
ℹ Use `summarise(.by = c(year, region))` for per-operation grouping
  (`?dplyr::dplyr_by`) instead.

# basic area chart, default options
highchart () |>
  hc_add_series(data = regions,
                type = "area",
                hcaes(x = year,
                      y = gdp_tn, 
                      group = region))

# they're overlapping each other, lets fix

# set color palette
cols <- brewer.pal(7, "Set2")

# stacked area chart
highchart () |>
  hc_add_series(data = regions,
                type = "area",
                hcaes(x = year,
                      y = gdp_tn, 
                      group = region)) |>
  hc_colors(cols) |> 
  hc_chart(style = list(fontFamily = "Georgia",
                        fontWeight = "bold")) |>
  hc_plotOptions(series = list(stacking = "normal",
                               marker = list(enabled = FALSE,
                                             states = list(hover = list(enabled = FALSE))),
                               lineWidth = 0.5,
                               lineColor = "white")) |>
  hc_xAxis(title = list(text="Year")) |>
  hc_yAxis(title = list(text="GDP ($ trillion)")) |>
  hc_legend(align = "right", verticalAlign = "top",
            layout = "vertical") 

# Food Stamps Data - Combine Two Types

food_stamps<- read_csv("food_stamps.csv")

Rows: 47 Columns: 3
── Column specification ────────────────────────────────────────────────────────
Delimiter: ","
dbl (3): year, participants, costs

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.

cols <- c("dodgerblue","orange")  # set the color palette to dodger blue and orange

highchart() |>
  hc_yAxis_multiples(
    list(title = list(text = "Participants (millions)")),
    list(title = list(text = "Costs ($ billions)"),
         opposite = TRUE)
  ) |>
  hc_add_series(data = food_stamps$participants,
                name = "Participants (millions)",
                type = "column",
                yAxis = 0) |>
  hc_add_series(data = food_stamps$costs,
                name = "Costs ($ billions)",
                type = "line",
                yAxis = 1) |>
  hc_xAxis(categories = food_stamps$year,
           tickInterval = 5) |>
  hc_colors(cols) |>
  hc_chart(style = list(fontFamily = "AvantGarde",
                        fontWeight = "bold"))

Week 9 Class Work Submission

# For both charts, you will first need to create a new variable in the data, usingmutate from dplyr, giving the GDP of each country in trillions of dollars, by multiplying gdp_percap by population and dividing by a trillion. 


nations <- read_csv("nations.csv") |>
  mutate(gdp_tn = gdp_percap*population/10^12)

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.

regions <- nations |>
  group_by(year,region) |>
  summarize(gdp_tn = sum(gdp_tn, na.rm = TRUE)) |>
  arrange(year,region)

`summarise()` has regrouped the output.
ℹ Summaries were computed grouped by year and region.
ℹ Output is grouped by year.
ℹ Use `summarise(.groups = "drop_last")` to silence this message.
ℹ Use `summarise(.by = c(year, region))` for per-operation grouping
  (`?dplyr::dplyr_by`) instead.

# Draw both charts with ggplot2.

p1 <- big4 %>%
  ggplot(aes(year, gdp_tn, color = country)) +
  geom_point() +
  geom_line() +
  labs(
    x = "Year",
    y = "GDP ($ trillion)",
    color = "Country",
    title = "China's Rise to Become the Largest Economy"
  ) +
  theme(legend.text = element_text(size = 7)) +
  scale_color_brewer(palette = "Set1")



p1

# 2nd chart 

# For the second chart, using dplyr you will need to group_by region and  year, and then summarize on your mutated value for gdpusing (done earlier)


p2 <- ggplot(regions, aes( x = year, y = gdp_tn, fill = region)) +
  geom_area(color = "white", linewidth = 0.5 ) +
  scale_fill_brewer(palette = "Set2") +
  labs(
    x = "Year",
    y = "GDP ($ trillion)"
  ) +
  theme(legend.position = "right", legend.direction = "vertical")

p2