vector-maps/vector-maps-solution.Rmd at main · MACS40700/vector-maps · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
---
title: "Practice drawing vector maps"
output: html_document
---

```{r packages}
library(tidyverse)
library(sf)
library(colorspace) # for better color palettes
library(here) # for specifying directory location

theme_set(theme_minimal()) # could choose something better for maps
```

## Import information on median household income in 2020 for Cook County, IL at the tract-level using the ACS

```{r}
cook_county_path <- here("data", "cook-county-inc.geojson")
cook_inc <- st_read(dsn = cook_county_path)
cook_inc
```

## Draw a choropleth using the median household income data

- Use a continuous color gradient to identify each tract's median household income

```{r}
# use fill channel
ggplot(data = cook_inc) +
  geom_sf(mapping = aes(fill = estimate)) +
  scale_fill_continuous_sequential(palette = "viridis", rev = FALSE)

# use fill and color channels - what is the difference?
ggplot(data = cook_inc) +
  geom_sf(mapping = aes(fill = estimate, color = estimate)) +
  scale_fill_continuous_sequential(palette = "viridis", rev = FALSE, aesthetics = c("fill", "color"))
```

```{r}
# fully labeled
ggplot(data = cook_inc) +
  geom_sf(mapping = aes(fill = estimate, color = estimate)) +
  scale_fill_continuous_sequential(
    palette = "viridis",
    rev = FALSE,
    aesthetics = c("fill", "color"),
    labels = scales::label_dollar(),
    name = NULL
  ) +
  labs(
    title = "Median household income in 2020",
    subtitle = "Cook County, by census tract"
  ) +
  ggthemes::theme_map()
```

## Draw the same choropleth for Cook County, but convert median household income into a discrete variable with 6 levels

- Using `cut_interval()`

```{r}
cook_inc %>%
  mutate(inc_cut = cut_interval(estimate, n = 6)) %>%
  ggplot() +
  geom_sf(mapping = aes(fill = inc_cut, color = inc_cut)) +
  scale_fill_discrete_sequential(palette = "viridis", rev = FALSE, aesthetics = c("fill", "color"))
```

- Using `cut_number()`

```{r}
cook_inc %>%
  mutate(inc_cut = cut_number(estimate, n = 6)) %>%
  ggplot() +
  geom_sf(mapping = aes(fill = inc_cut, color = inc_cut)) +
  scale_fill_discrete_sequential(palette = "viridis", rev = FALSE, aesthetics = c("fill", "color"))
```

- Using `binned_scale()`

```{r}
# default breaks
ggplot(data = cook_inc) +
  geom_sf(mapping = aes(fill = estimate, color = estimate)) +
  scale_fill_binned_sequential(
    palette = "viridis",
    rev = FALSE,
    aesthetics = c("fill", "color"),
    labels = scales::label_dollar()
  )

# quartiles
ggplot(data = cook_inc) +
  geom_sf(mapping = aes(fill = estimate, color = estimate)) +
  scale_fill_binned_sequential(
    palette = "viridis",
    rev = FALSE,
    aesthetics = c("fill", "color"),
    n.breaks = 4, nice.breaks = FALSE,
    labels = scales::label_dollar()
  )
```

## Draw a choropleth of median household income for each US county

- Adjust to use Albers equal-area projection

```{r}
usa_inc <- st_read(dsn = here("data", "usa-inc.geojson"))
usa_inc
```

```{r}
ggplot(data = usa_inc) +
  geom_sf(mapping = aes(fill = estimate, color = estimate)) +
  scale_fill_continuous_sequential(
    palette = "viridis",
    rev = FALSE,
    aesthetics = c("fill", "color"),
    labels = scales::label_dollar()
  ) +
  coord_sf(crs = 2163)
```

## Session Info

```{r}
sessioninfo::session_info()
```