MiniProject1

# Initial packages required (we'll be adding more)
library(tidyverse)
library(mdsr)     # package associated with our MDSR book
library(maps)
library(viridis)
library(leaflet)

library(htmltools)
library(glue)

Import dataset

driving <- read_csv("~/SDS264_F24/Licensed_Driver_Dashboard_Data.csv")

Warning: One or more parsing issues, call `problems()` on your data frame for details,
e.g.:
  dat <- vroom(...)
  problems(dat)

Rows: 66006 Columns: 6
── Column specification ────────────────────────────────────────────────────────
Delimiter: ","
chr (3): Sex, Cohort, State
dbl (2): Year, Drivers
lgl (1): Unnamed Column

ℹ Use `spec()` to retrieve the full column specification for this data.
ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

driving <- driving |> 
  filter(Year == 2019) |>
  mutate(State = str_to_lower(State))
  
female_totals <- driving |> 
  filter(Sex == "Female") |> 
  group_by(State) |> 
  summarise(female_total = sum(Drivers))
  

drivingTotals <- driving |> 
  group_by(State) |> 
  summarise(total = sum(Drivers)) |> 
  mutate(total_rounded = total/1000) |> 
  full_join(female_totals) |> 
  mutate(pct_female = trunc((female_total / total)*10^4)/10^4) |> 
  mutate(majority_female = ifelse(pct_female >= 0.50, "Majority Female", "Majority Male"))

Joining with `by = join_by(State)`

Map 1

us_states <- map_data("state")

drivingTotals |>
  right_join(us_states, by = c("State" = "region")) |>
  rename(region = State) |>
  ggplot(mapping = aes(x = long, y = lat,
                          group = group)) + 
  geom_polygon(aes(fill = total_rounded), color = "black") +
  theme_void() +
  scale_fill_viridis() +
  labs(
    fill = "Total Drivers (Thousands)",
    title = "Distribution of Total Drivers in the United States",
    caption = "https://catalog.data.gov/dataset/licensed-drivers-by-state-gender-and-age-group"
  )

This map shows us how many total drivers are in each state. We can see that states with higher populations and larger urban areas (California, Texas, Florida) have more licensed drivers.

Interactive Map 1

library(sf) 

Linking to GEOS 3.13.0, GDAL 3.10.1, PROJ 9.5.1; sf_use_s2() is TRUE

states <- read_sf("https://rstudio.github.io/leaflet/json/us-states.geojson")

states <- states |> 
  mutate(name = str_to_lower(name))

totalInteractiveMap <- states |>
  left_join(drivingTotals, by = c("name" = "State")) |> 
  mutate(labels = str_c(name, ": ", total_rounded, " drivers, in thousands"))

bins <- c(100, 500, 1000, 2000, 4000, 7000, 10000, 20000, Inf)
pal <- colorBin("YlOrRd", domain = totalInteractiveMap$total_rounded, bins = bins)

labels <- lapply(totalInteractiveMap$labels, HTML)

leaflet(totalInteractiveMap) %>%
  setView(-96, 37.8, 4) %>%
  addTiles() %>%
  addPolygons(
    fillColor = ~pal(total_rounded),
    weight = 2,
    opacity = 1,
    color = "white",
    dashArray = "3",
    fillOpacity = 0.7,
    highlightOptions = highlightOptions(
      weight = 2,
      color = "#666",
      dashArray = "",
      fillOpacity = 0.7,
      bringToFront = TRUE),
    label = labels,
    labelOptions = labelOptions(
      style = list("font-weight" = "normal", padding = "3px 8px"),
      textsize = "15px",
      direction = "auto")) %>%
  addLegend(pal = pal, values = ~total_rounded, opacity = 0.7, title = NULL,
    position = "bottomright")

Map 2

drivingTotals |>
  right_join(us_states, by = c("State" = "region")) |>
  rename(region = State) |>
  ggplot(mapping = aes(x = long, y = lat,
                          group = group)) + 
  geom_polygon(aes(fill = majority_female), color = "black") +
  theme_void() +
  scale_fill_manual(values = c("purple", "green")) +
  labs(
    fill = "Driver Distribution",
    title = "Distribution of Male and Female Drivers in the United States",
    caption = "https://catalog.data.gov/dataset/licensed-drivers-by-state-gender-and-age-group"
  )

This is a coded map showing the distribution of male and female drivers for all contiguous states in the US. The variable displayed is categorical, with the 2 categories being “Majority Female” and “Majority Male”. Based on this graph, we can see that most states have a majority female population of drivers. The south west, pacific northwest, and Midwest regions are almost all majority male drivers, and almost every other state is a majority female.

totalInteractiveMap <- states |>
  left_join(drivingTotals, by = c("name" = "State")) |> 
  mutate(labels2 = str_c(name, ": ", (pct_female*100), "% of driver population is female"))

factpal <- colorFactor(c("purple", "green"),
                       levels(totalInteractiveMap$majority_female))

labels2 <- lapply(totalInteractiveMap$labels2, HTML)

leaflet(totalInteractiveMap) %>%
  setView(-96, 37.8, 4) %>%
  addTiles() %>%
  addPolygons(
    fillColor = ~factpal(totalInteractiveMap$majority_female),
    weight = 2,
    opacity = 1,
    color = "white",
    dashArray = "3",
    fillOpacity = 0.7,
    highlightOptions = highlightOptions(
      weight = 2,
      color = "#666",
      dashArray = "",
      fillOpacity = 0.7,
      bringToFront = TRUE),
    label = labels2,
    labelOptions = labelOptions(
      style = list("font-weight" = "normal", padding = "3px 8px"),
      textsize = "15px",
      direction = "auto")) %>%
  addLegend(pal = factpal, values = ~majority_female, opacity = 0.7, title = NULL,
    position = "bottomright")

Warning in sf::st_is_longlat(x): bounding box has potentially an invalid value
range for longlat data