---
#############################################################
#                                                           #
# In RStudio click on "Run Document" to run this tutorial   #
#                                                           #
#############################################################
title: "Visualizing Amounts"
author: "Luke Tierney"
output: learnr::tutorial
runtime: shiny_prerendered
---

```{r setup, include = FALSE}
library(learnr)
library(tidyverse)
knitr::opts_chunk$set(echo = FALSE, comment = "", warning = FALSE)
<<load-packages>>
<<prepare-data>>
```

```{r stop_when_browser_closes, context = "server"}
# stop the app when the browser is closed (or, unfortunately, refreshed)
session$onSessionEnded(stopApp)
```

## Average Life Expectancy by Continent
These exercises will use `gapminder` data:
```{r load-packages, echo = TRUE, eval = FALSE}
library(ggplot2)
library(dplyr)
library(gapminder)
```

In particular, you will look at average life expectancy values for the
continents in the each of the years covered by the data set:

```{r prepare-data, echo = TRUE, eval = FALSE}
avgLE <- group_by(gapminder, continent, year) %>%
    summarize(avgLifeExp = mean(lifeExp)) %>%
    ungroup()
```

## Some Dot Plots

Start by creating a dot plot for the average life expectancy values
for the different continents in 2007. Show the continent values in
increasing order.

```{r avgLE-2007, exercise = TRUE}


```
```{r avgLE-2007-solution}
filter(avgLE, year == 2007) %>%
    mutate(continent = reorder(continent, avgLifeExp)) %>%
    ggplot(aes(x = avgLifeExp, y = continent)) +
    geom_point()
```

Next, show the values for both 1952 and 2007, using color to
identify the years. Increasing the points size will make the colors
easier to see.

```{r avgLE-1952-2007, exercise = TRUE}



```
```{r avgLE-1952-2007-solution}
filter(avgLE, year == 2007 | year == 1952) %>%
    mutate(continent = reorder(continent, avgLifeExp),
           year = factor(year)) %>%
    ggplot(aes(x = avgLifeExp, y = continent, color = year)) +
    geom_point(size = 3)
```

A _dumbbell_ chart can emphasize the sizes of the changes from 1952 to
2007. Modify your chart to show a dumbbell chart.

```{r aveLE-db, exercise = TRUE}



```
```{r aveLE-db-solution}
filter(avgLE, year == 2007 | year == 1952) %>%
    mutate(continent = reorder(continent, avgLifeExp),
           year = factor(year)) %>%
    ggplot(aes(x = avgLifeExp, y = continent, color = year)) +
    geom_line(aes(group = continent), size = 2, color = "black") +
    geom_point(aes(color = year), size = 4)
```


## Some Bar Charts

Now create a bar chart for the average life expectancy values
for the different continents in 2007. Again show the continent values in
increasing order.

```{r avgLE-bar, exercise = TRUE}


```
```{r avgLE-bar-solution}
filter(avgLE, year == 2007) %>%
    mutate(continent = reorder(continent, avgLifeExp)) %>%
    ggplot(aes(x = avgLifeExp, y = continent)) +
    geom_col()
```

Use a side-by-side bar chart to show the life expectancy values for
1952 and 2007.

```{r avgLE-dodge, exercise = TRUE}


```
```{r avgLE-dodge-solution}
filter(avgLE, year == 2007 | year == 1952) %>%
    mutate(continent = reorder(continent, avgLifeExp),
           year = factor(year)) %>%
    ggplot(aes(x = avgLifeExp, y = continent, fill = year)) +
    geom_col(position = "dodge")
```

Another option for showing the two years is is to use faceting on
year.

```{r avgLE-bar-facet, exercise = TRUE}



```
```{r avgLE-bar-facet-solution}
filter(avgLE, year == 2007 | year == 1952) %>%
    mutate(continent = reorder(continent, avgLifeExp),
           year = factor(year)) %>%
    ggplot(aes(x = avgLifeExp, y = continent)) +
    geom_col() +
    facet_wrap(~ year, ncol = 1)
```

## Exercises

### Exercise 1

A plot similar to this was featured in a CNN news story several years ago:

```{r, echo = FALSE}
library(ggplot2)
levs <- c("Democrats", "Repubicans", "Independents")
d <- data.frame(party = factor(levs, levs),
                pct = c(62, 54, 54))

ggplot(d, aes(x = party, y = pct - 50)) +
    geom_col(width = 0.5) +
    scale_y_continuous(labels = seq(50, 64, by = 2),
                       breaks = seq(0, 14, by = 2),
                       expand = expansion(c(0, 0.18))) +
    labs(x = "Political Party",
         y = NULL,
         title = "Percent Who Agreed With Court") +
    theme(text = element_text(size = 20, face = "bold"),
          panel.grid.minor.x = element_blank(),
          panel.grid.major.x = element_blank(),
          panel.grid.minor.y = element_blank(),
          panel.grid.major.y = element_line(color = "black"),
          panel.background = element_rect(fill = "grey", color = NA),
          plot.background=element_rect(fill = "white", color = "black",
                                       size = 2),
          plot.margin=margin(20, 20, 20, 20)) +
    coord_fixed(0.1)
```

```{r court-question, echo = FALSE}
question(
    "Which of the following is approximately correct:",
    answer("About the same number of democrats as republicans agreed with the court."),
    answer("About 15% more democrats than republicans agreed with the court.",
          correct = TRUE),
    answer("About tree times as many democrats than republicans agreed with the court."),
    answer("About two times as many democrats than republicans agreed with the court."),
    random_answer_order = TRUE,
    allow_retry = TRUE
)
```


### Exercise 2

Consider the stacked bar chart produced by the following code:

```{r four-cyl-exercise, exercise = TRUE}
library(tidyverse)
mpg2 <- mutate(mpg,
               class = fct_rev(fct_infreq(class)),
               cyl = factor(cyl))
p <- ggplot(mpg2, aes(y = class, fill = cyl)) +
    geom_bar()
```

```{r four-cyl-question, echo = FALSE}
question(
    "Which of these modifications makes it easiest to compare the count of 4-cylinder models within the different classes?",
    answer("`p %+% mutate(mpg2, cyl = factor(cyl, c(4, 5, 6, 8)))`"),
    answer("`p %+% mutate(mpg2, cyl = factor(cyl, c(5, 6, 4, 8)))`"),
    answer("`p %+% mutate(mpg2, cyl = factor(cyl, c(4, 6, 8, 5)))`"),
    answer("`p %+% mutate(mpg2, cyl = factor(cyl, c(8, 6, 5, 4)))`",
           correct = TRUE),
    random_answer_order = TRUE,
    allow_retry = TRUE
)
```


### Exercise 3

The bar chart produced by the following code has `x` axis labels
that could be improved:

```{r not-better-x-exercise, exercise = TRUE}
library(gapminder)
library(dplyr)
library(ggplot2)
library(scales)
p <- filter(gapminder, year == 2007) %>%
    group_by(continent) %>%
    summarize(avgGdpPercap = mean(gdpPercap)) %>%
    ggplot(aes(x = avgGdpPercap, y = continent)) +
    geom_col() +
    labs(x = "Average GDP Per Capita", y = NULL) +
    theme_minimal() + theme(text = element_text(size = 16))
```

There are a number of different options.

```{r, not-better-x-question, echo = FALSE}
question(
    "Which of the following does **not** provide improved `x` axis labels?",
    answer("`p + scale_x_continuous(labels = label_comma())`"),
    answer("`p + scale_x_continuous(labels = label_dollar())`"),
    answer("`p + scale_x_continuous(labels = unit_format(scale = 1/1000, unit = \"K\", prefix = \"$\"))`"),
    answer("`p + scale_x_continuous(labels = c(\"$10,000\", \"$20,000\", \"$30,000\"))`", correct = TRUE),
    random_answer_order = TRUE,
    allow_retry = TRUE
)
```

### Exercise 4

A stacked bar chart is appropriate if the combined bar heights of
the stacked bars have a reasonable interpretation. Consider the
following two plots:


```{r, fig.height = 4, fig.width = 8}
library(gapminder)
library(dplyr)
library(ggplot2)
library(patchwork)
p1 <- filter(gapminder, year >= 2000) %>%
    group_by(continent, year) %>%
    summarize(avgLifeExp = mean(lifeExp), .groups = "drop") %>%
    ggplot(aes(x = avgLifeExp, y = continent, fill = factor(year))) +
    geom_col() +
    theme_minimal() +
    theme(text = element_text(size = 12)) +
    scale_x_continuous(expand = expansion(mult = c(0, .1))) +
    labs(x = "Average Life Expectancy",
         y = NULL,
         fill = "Year",
         title = "Average Life Expectancy\nby Continent for Two Years",
         tag = "P1:")
p2 <- count(mpg, class, cyl) %>%
    ggplot(aes(x = n, y = class, fill = factor(cyl))) +
    geom_col() +
    theme_minimal() +
    theme(text = element_text(size = 12)) +
    scale_x_continuous(expand = expansion(mult = c(0, .1))) +
    labs(x = "Number of Models",
         y = NULL,
         fill = "Cylinders",
         title = "Number of Car Models\nby Class and Cylinder Count",
         tag = "P2:")
p1 + p2
```

```{r stacked-bar-question, echo = FALSE}
question(
    "Which of the following statements is true:",
    answer("P1 is an appropriate use of a stacked bar chart but P2 is not."),
    answer("P2 is an appropriate use of a stacked bar chart but P1 is not.",
           correct = TRUE),
    answer("Neither P1 nor P2 is an appropriate use of a stacked bar chart."),
    answer("Both P1 and P2 are appropriate uses of a stacked bar chart."),
    random_answer_order = TRUE,
    allow_retry = TRUE
)
```