Introduction to Highcharts in R

Highcharts is a JavaScript charting library that creates interactive visualizations. The highcharter package integrates this functionality into R, allowing us to produce dynamic plots easily.

Note: To experience the interactive features, such as the range selector, knit this document to HTML. Static formats like PDF or Word will only show static images.

Scatterplot

First we will create a simple scatterplot using the penguins dataset from the palmerpenguins package. Notice how easy it is to create an interactive scatterplot with highcharter. The hchart() function is used to create the chart, and hcaes() is used to specify the aesthetics (x and y axes, and grouping variable).

data(penguins, package = "palmerpenguins") 

hchart(
  penguins,
  "scatter",
  hcaes(x = flipper_length_mm, y = bill_length_mm, group = species)
)
hchart(
  penguins,
  "scatter",
  hcaes(x = flipper_length_mm, y = bill_length_mm, group = species)
) %>% hc_add_theme(hc_theme_smpl())
hchart(
  penguins,
  "scatter",
  hcaes(x = flipper_length_mm, y = bill_length_mm, group = species)
) %>% hc_add_theme(hc_theme_tufte())
hchart(
  penguins,
  "scatter",
  hcaes(x = flipper_length_mm, y = bill_length_mm, group = species)
) %>% hc_add_theme(hc_theme_538())

Multiple Line Chart

data(economics_long, package = "ggplot2")

economics_long2 <- dplyr::filter(economics_long, variable %in% c("pop", "uempmed", "unemploy"))

hchart(economics_long2, "line", 
       hcaes(x = date, y = value01, group = variable))

Example: Median Duration of Unemployment Over Time

We’ll use the economics dataset from ggplot2, which contains monthly U.S. economic indicators from July 1967 to 2015.

This line chart visualizes the median duration of unemployment (uempmed) in weeks, also with a range selector.

data(economics)

hchart(economics, "line", hcaes(x = date, y = uempmed)) %>%
  hc_title(text = "Median Duration of Unemployment Over Time") %>%
  hc_xAxis(type = "datetime", title = list(text = "Date")) %>%
  hc_yAxis(title = list(text = "Median Duration (weeks)")) %>%
  hc_rangeSelector(
    enabled = TRUE,
    buttons = list(
      list(type = "year", count = 1, text = "1y"),
      list(type = "year", count = 5, text = "5y"),
      list(type = "year", count = 10, text = "10y"),
      list(type = "all", text = "All")
    ),
    inputEnabled = TRUE
  ) %>% hc_add_theme(hc_theme_538())

Forecasts

#summary(AirPassengers)

airforecast <- forecast(auto.arima(AirPassengers), h = 24, level = 95)
my_chart <- hchart(airforecast)

# The first series is the historical data
my_chart$x$hc_opts$series[[1]]$name <- "Historical"

# The second series is the forecast data
my_chart$x$hc_opts$series[[2]]$name <- "Forecast"

# 3. Display the chart with the new labels
my_chart

Example: Life Expectancy Over Time by Country

Let’s try an interactive multiple line chart of life expectancy over time for selected countries.

library(gapminder)

# Select countries for the chart
countries <- c("United States", "China", "Japan", "Germany", "India")

# Filter the gapminder dataset for selected countries
gapminder_filtered <- gapminder %>% filter(country %in% countries)

# Create the interactive line chart
hchart(gapminder_filtered, "line", hcaes(x = year, y = lifeExp, group = country)) %>%
  hc_title(text = "Life Expectancy Over Time by Country") %>%
  hc_xAxis(title = list(text = "Year")) %>%
  hc_yAxis(title = list(text = "Life Expectancy (years)")) %>%
  hc_plotOptions(line = list(
    lineWidth = 1,              # Default thin lines
    marker = list(enabled = FALSE),  # No markers for cleaner look
    states = list(
      hover = list(
        enabled = TRUE,
        lineWidthPlus = 3      # Thicken line on hover
      ),
      inactive = list(
        opacity = 0.1          # Fade other lines
      )
    )
  )) %>%
  hc_tooltip(pointFormat = "{series.name}: {point.y} years")  # Custom tooltip

Simple Bar Chart

x <- c(rnorm(10000), rnorm(1000, 4, 0.5))

hchart(x, name = "data", color = "steelblue") %>%
  hc_title(text = "Histogram of Random Data") %>%
  hc_xAxis(title = list(text = "Value")) %>%
  hc_yAxis(title = list(text = "Frequency")) %>%
  hc_plotOptions(column = list(
    pointPadding = 0.2,
    borderWidth = 0
  )) %>%
  hc_tooltip(pointFormat = "Value: {point.x}<br>Frequency: {point.y}")

Bar Chart: Average Savings Rate by Decade

This bar chart displays the average personal savings rate by decade, with the savings rate shown to one decimal place in the tooltip.

First, we prepare the data by calculating the average savings rate for each decade.

We divide a given year by 10, round it down, then multiply back by 10 to group by the start of the decade in order to calculate the average personal savings rate (psavert).

data(economics)

economics_decade <- economics %>%
  mutate(decade = floor(year(date) / 10) * 10) %>%
  group_by(decade) %>%
  summarize(avg_psavert = mean(psavert, na.rm = TRUE))

Then, we create the bar chart with a formatted tooltip.

hchart(economics_decade, "column", hcaes(x = decade, y = avg_psavert)) %>%
  hc_title(text = "Average Personal Savings Rate by Decade") %>%
  hc_xAxis(title = list(text = "Decade")) %>%
  hc_yAxis(title = list(text = "Average Savings Rate (%)")) %>%
  hc_tooltip(pointFormat = "Decade: {point.x}<br>Avg Savings Rate: {point.y:.1f}%")

Stock Chart

x <- getSymbols("GOOG", auto.assign = FALSE)

highchart(type = "stock") |> 
  hc_add_series(x)

Pie Chart: Distribution of Unemployment Duration Categories

This pie chart shows the distribution of median unemployment duration categories over the entire period from 1967 to 2015. Each slice represents the proportion of months where the median unemployment duration fell into a specific range.

First, we categorize the median unemployment duration (uempmed) into bins and count the number of months in each category.

# Prepare data for pie chart

economics
## # A tibble: 574 × 6
##    date         pce    pop psavert uempmed unemploy
##    <date>     <dbl>  <dbl>   <dbl>   <dbl>    <dbl>
##  1 1967-07-01  507. 198712    12.6     4.5     2944
##  2 1967-08-01  510. 198911    12.6     4.7     2945
##  3 1967-09-01  516. 199113    11.9     4.6     2958
##  4 1967-10-01  512. 199311    12.9     4.9     3143
##  5 1967-11-01  517. 199498    12.8     4.7     3066
##  6 1967-12-01  525. 199657    11.8     4.8     3018
##  7 1968-01-01  531. 199808    11.7     5.1     2878
##  8 1968-02-01  534. 199920    12.3     4.5     3001
##  9 1968-03-01  544. 200056    11.7     4.1     2877
## 10 1968-04-01  544  200208    12.3     4.6     2709
## # ℹ 564 more rows
economics_pie <- economics %>%
  mutate(duration_cat = cut(uempmed,
                            breaks = c(0, 5, 10, 15, 20, Inf),
                            labels = c("<5 weeks", "5-10 weeks", "10-15 weeks", "15-20 weeks", "20+ weeks"),
                            right = FALSE)) %>%
  count(duration_cat)

Then, we create the interactive pie chart.

# Create the pie chart
hchart(economics_pie, "pie", hcaes(name = duration_cat, y = n)) %>%
  hc_title(text = "Distribution of Median Unemployment Duration Categories") %>%
  hc_subtitle(text = "Based on monthly data from 1967 to 2015") %>%
  hc_plotOptions(pie = list(
    allowPointSelect = TRUE,
    cursor = "pointer",
    dataLabels = list(enabled = TRUE, format = "{point.percentage:.1f}%")
  )) %>%
  hc_tooltip(pointFormat = "{point.name}: {point.y} months ({point.percentage:.1f}%)")

Heatmap

dfdiam <- diamonds |> 
  group_by(cut, clarity) |>
  summarize(price = median(price))

hchart(dfdiam, "heatmap", hcaes(x = cut, y = clarity, value = price), name = "Median Price")