Matt Parker recently showed us how to create multi-tab reports with R and jQuery UI. His example was absurdly easy to reproduce; it was a great blog post.

I have been teaching myself Shiny in fits and starts, and I decided to attempt to reproduce Matt’s jQuery UI example in Shiny. You can play with the app on shinyapps.io, and the complete project is up on Github. The rest of this post walks through how I built the Shiny app.

It’s a demo

The result demonstrates a few Shiny and ggplot2 techniques that will be useful in other projects, including:

• Creating tabbed reports in Shiny, with different interactive controls or widgets associated with each tab;
• Combining different ggplot2 scale changes in a single legend;
• Sorting a data frame so that categorical labels in a legend are ordered to match the position of numerical data on a plot;
• Borrowing from Matt’s work,
  • Summarizing and plotting data using dplyr and ggplot2;
  • Limiting display of categories in a graph legend to the top n (selectable by the user), with remaining values listed as “other;”
  • Coloring only the top n categories on a graph, and making all other categories gray;
  • Changing line weight for the top n categories on a graph, and making;

Obtaining the data

As with Matt’s original report, the data can be downloaded from the CDC WONDER database by selecting “Data Request” under “current cases.”

To get the same data that I’ve used, group results by “state” and by “year,” check “incidence rate per 100,000” and, near the bottom, “export results.” Uncheck “show totals,” then submit the request. This will download a .txt tab-delimited data file, which in this app I read in using read_tsv() from the readr package.

Looking at Matt’s example, his “top 5” states look suspiciously like the most populous states. He’s used total count of cases, which will be biased toward more populous states and doesn’t tell us anything interesting. When examining occurrences—whether disease, crime or defects—we have to look at the rates rather than total counts; we can only make meaningful comparisons and make useful decisions from an examination of the rates.

Setup

As always, we need to load our libraries into R. For this example, I use readr, dplyr, ggplot2 and RColorBrewer.

The UI

The app generates three graphs: a national total, that calculates national rates from the state values; a combined state graph that highlights the top states, where the user chooses ; and a graph that displays individual state data, where the user can select the state to view. Each goes on its own tab.

ui.R contains the code to create a tabset panel with three tab panels.

tabsetPanel(
  tabPanel("National", fluidRow(plotOutput("nationPlot"))),
  tabPanel("By State",
           fluidRow(plotOutput("statePlot"),
                    wellPanel(
                      sliderInput(inputId = "nlabels",
                                  label = "Top n States:",
                                  min = 1,
                                  max = 10,
                                  value = 6,
                                  step = 1)
                    )
           )
  ),
  tabPanel("State Lookup",
           fluidRow(plotOutput("iStatePlot"),
                    wellPanel(
                      htmlOutput("selectState"))
           )
  )
)

Each panel contains a fluidRow element to ensure consistent alignment of graphs across tabs, and on tabs where I want both a graph and controls, fluidRow() is used to add the controls below the graph. The controls are placed inside a wellPanel() so that they are visually distinct from the graph.

Because I wanted to populate a selection menu (selectInput()) from the data frame, I created the selection menu in server.R and then displayed it in the third tab panel set using the htmlOutput() function.

The graphs

The first two graphs are very similar to Matt’s example. For the national rates, the only change is the use of rates rather than counts.

df_tb <- read_tsv("../data/OTIS 2013 TB Data.txt", n_max = 1069, col_types = "-ciiii?di")

df_tb %>%
  group_by(Year) %>%
  summarise(n_cases = sum(Count), pop = sum(Population), us_rate = (n_cases / pop * 100000)) %>%
  ggplot(aes(x = Year, y = us_rate)) +
  geom_line() +
  labs(x = "Year Reported",
       y = "TB Cases per 100,000 residents",
       title = "Reported Active Tuberculosis Cases in the U.S.") +
  theme_minimal()

The main trick, here, is the use of dplyr to summarize the data across states. Since we can’t just sum or average rates to get the combined rate, we have to sum all of the state counts and populations for each year, and add another column for the calculated national rate.

To create a graph that highlights the top states, we generate a data frame with one variable, State, that contains the top states. This is, again, almost a direct copy of Matt’s code with changes to make the graph interactive within Shiny. This code goes inside of the shinyServer() block so that it will update when the user selects a different value for . Instead of hard-coding , there’s a Shiny input slider named nlabels. With a list of the top states ordered by rate of TB cases, df_tb is updated with a new field containing the top state names and “Other” for all other states.

top_states <- df_tb %>%
      filter(Year == 2013) %>%
      arrange(desc(Rate)) %>%
      slice(1:input$nlabels) %>%
      select(State)

df_tb$top_state <- factor(df_tb$State, levels = c(top_states$State, "Other"))
df_tb$top_state[is.na(df_tb$top_state)] <- "Other"

The plot is generated from the newly-organized data frame. Where Matt’s example has separate legends for line weight (size) and color, I’ve had ggplot2 combine these into a single legend by passing the same value to the “guide =” argument in the scale_XXX_manual() calls. The colors and line sizes also have to be updated dynamically for the selected .

    df_tb %>%
      ggplot() +
      labs(x = "Year reported",
           y = "TB Cases per 100,000 residents",
           title = "Reported Active Tuberculosis Cases in the U.S.") +
      theme_minimal() +
      geom_line(aes(x = Year, y = Rate, group = State, colour = top_state, size = top_state)) +
      scale_colour_manual(values = c(brewer.pal(n = input$nlabels, "Paired"), "grey"), guide = guide_legend(title = "State")) +
      scale_size_manual(values = c(rep(1,input$nlabels), 0.5), guide = guide_legend(title = "State"))
  })

})

The last graph is nearly a copy of the national totals graph, except that it is filtered for the state selected in the drop-down menu control. The menu is as selectInput() control.

renderUI({
    selectInput(inputId = "state", label = "Which state?", choices = unique(df_tb$State), selected = "Alabama", multiple = FALSE)
  })

With a state selected, the data is filtered by the selected state and TB rates are plotted.

df_tb %>%
  filter(State == input$state) %>%
  ggplot() +
  labs(x = "Year reported",
       y = "TB Cases per 100,000 residents",
       title = "Reported Active Tuberculosis Cases in the U.S.") +
  theme_minimal() +
  geom_line(aes(x = Year, y = Rate))

Wrap up

I want to thank Matt Parker for his original example. It was well-written, clear and easy to reproduce.

“The emphasis in ggplot2 is reducing the amount of thinking time by making it easier to go from the plot in your brain to the plot on the page.” (Wickham, 2012)

“Base graphics are good for drawing pictures; ggplot2 graphics are good for understanding the data.” (Wickham, 2012)

I’m not ggplot2’s creator, Hadley Wickham, but I do find myself in discussions trying to explain how to build graphs in ggplot2. It’s a very elegant system, but also very different from other graphing systems. Once you understand the organizing philosophy, ggplot2 becomes very easy to work with.

The grammar of ggplot2 graphics

There is a basic grammar to all graphics production. In R‘s base graphics or in Excel, you feed ranges of data to a plot as x and y elements, then manipulate colors, scale dimensions and other parts of the graph as graphical elements or options.

ggplot2’s grammar makes a clear distinction between your data and what gets displayed on the screen or page. You feed ggplot2 your data, then apply a series of mappings and transformations to create a visual representation of that data. Even with base graphics or Excel we never really plot the data itself, we only create a representation; ggplot2 makes this distinction explicit. In addition, ggplot2’s structure makes it very easy to tweak a graph to look the way you want by adding mappings.

A ggplot2 graph is built up from a few basic elements:

1.	Data		The raw data that you want to plot
2.	Geometries	geom_	The geometric shapes that will represent the data.
3.	Aethetics	aes()	Aesthetics of the geometric and statistical objects, such as color, size, shape and position.
4.	Scales	scale_	Maps between the data and the aesthetic dimensions, such as data range to plot width or factor values to colors

Putting it together, the code to build a ggplot2 graph looks something like:

data
+ geometry to represent the data,
+ aesthetic mappings of data to plot coordinates like position, color and size
+ scaling of ranges of the data to ranges of the aesthetics

A real example shows off how this all fits together.

library(ggplot2)
# Create some data for our example
some.data <- data.frame(timer = 1:12, 
                        countdown = 12:1, 
                        category = factor(letters[1:3]))
# Generate the plot
some.plot <- ggplot(data = some.data, aes(x = timer, y = countdown)) +
  geom_point(aes(colour = category)) +
  scale_x_continuous(limits = c(0, 15)) +
  scale_colour_brewer(palette = "Dark2") +
  coord_fixed(ratio=1)
# Display the plot
some.plot

Here you can see that the data is passed to ggplot(), aesthetic mappings between the data and the plot coordinates, a geometry to represent the data and a couple of scales to map between the data range and the plot ranges.

More advanced parts of the ggplot2 grammar

The above will get you a basic graph, but ggplot2 includes a few more parts of the grammar that you’ll want to be aware of as you try to visualize more complex data:

5.	Statistical transformations	stat_	Statistical summaries of the data that can be plotted, such as quantiles, fitted curves (loess, linear models, etc.), sums and so o.
6.	Coordinate systems	coord_	The transformation used for mapping data coordinates into the plane of the data rectangle.
7.	Facets	facet_	The arrangement of the data into a grid of plots (also known as latticing, trellising or creating small multiples).
8.	Visual Themes	theme	The overall visual defaults of a plot: background, grids, axe, default typeface, sizes, colors, etc.

Hadley Wickham describes various pieces of this grammar in recorded presentations on Vimeo and YouTube and the online documentation to ggplot2. The most complete explanation is in his book ggplot2: Elegant Graphics for Data Analysis (Use R!) (Wickham, 2009).

References

Wickham, Hadley. ggplot2: Elegant Graphics for Data Analysis. Dordrecht, Heibelberg, London, New York: Springer, 2009. Print.
Wickham, Hadley. A Backstage Tour of ggplot2 with Hadley Wickham. 2012. Video. YouTube. Web. 21 Mar 2014. . Contributed by REvolutionAnalytics.