Created
February 26, 2020 19:22
-
-
Save ryanbthomas/9e6c6d8cf88f70de9227c4f4922fdc6c to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
--- | |
title: "R Notebook" | |
output: html_notebook | |
--- | |
```{r} | |
# setup | |
library(readr) | |
library(dplyr) | |
library(forcats) | |
library(ggplot2) | |
library(tibble) | |
``` | |
```{r} | |
#load data | |
url <- "https://gist.githubusercontent.com/dgkeyes/a9b47cfa9a7bd8313e5603d18cf3d444/raw/3de0e4074db23636ebd420af78e90c4009aa10c7/oregon-economic-mobility-data.csv" | |
raw_data <- read_csv(url, col_names = c("name", "upward_mobile"), skip = 1) | |
``` | |
```{r} | |
# clean data | |
extract_percentage <- function(x) { | |
sans_percent <- substr(x, 1, nchar(x) - 1) | |
as.numeric(sans_percent) | |
} | |
clean_data <- mutate(raw_data, upward_mobile = extract_percentage(upward_mobile)) | |
state_mean <- mean(clean_data$upward_mobile) | |
county_data <- clean_data %>% | |
mutate(highlow = if_else(upward_mobile > state_mean, "High", "Low"), | |
simple_name = stringr::str_extract(string = name, | |
pattern = "^[A-Za-z ]+(?= County, OR)")) | |
state_data <- tibble(name = "Oregon Average", | |
upward_mobile = state_mean, | |
highlow = "", | |
simple_name = "Oregon Average") | |
plot_data <- bind_rows(county_data, state_data) %>% | |
arrange(upward_mobile) %>% | |
mutate(simple_name = forcats::fct_inorder(simple_name), | |
highlow = forcats::fct_inorder(highlow)) | |
``` | |
```{r, fig.height=10, fig.width=5} | |
# plot | |
vert_axis <- 7 | |
use_palette <- c("#f5a52f", "#5c5c5c","#2f50f5") | |
ggplot(plot_data, aes(x = upward_mobile, y = simple_name)) + | |
geom_segment(aes(x = vert_axis, xend = upward_mobile, yend = simple_name, color = highlow), size = 1.5) + | |
geom_point(aes(color = highlow), size = 4) + | |
geom_text(aes(x = upward_mobile + 0.8, y = simple_name, label = scales::percent(upward_mobile/100))) + | |
scale_color_manual(values = use_palette) + | |
scale_x_continuous(limits = c(vert_axis, 16), expand = expand_scale()) + | |
labs(title = "Upward Mobility") + | |
theme_classic() + | |
theme(legend.position = "none", | |
axis.title.x = element_blank(), | |
axis.title.y = element_blank(), | |
plot.background = element_rect(fill = "#fffff0"), | |
panel.background = element_rect(fill = "#fffff0"), | |
axis.text.x = element_blank(), | |
axis.line.x = element_blank(), | |
axis.line.y = element_blank(), | |
axis.ticks = element_blank(), | |
title = element_text(size = 20) ) | |
``` | |
Thanks... I actually noted that in your gist. Going to remember that one for the future.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
FYI,
reader::parse_number()
is a standard drop in for yourextract_percentage()