library(readr)
raw <- read_csv("data/alt_fuel_stations (Sep 25 2024)_joined.csv")

library(tidyverse)
dataset <- raw %>%
  select(
    `Station Name`, 
    `City`, 
    `EV Level2 EVSE Num`, 
    `EV DC Fast Count`, 
    `Latitude`, 
    `Longitude`, 
    `EV Connector Types`, 
    `EV Workplace Charging`, 
    `UR20`
  )

has_null_ur20 <- dataset %>%
  summarise(any_null = any(is.na(UR20)))

dataset <- dataset %>%
  filter(!is.na(UR20)) %>% 
  mutate(UR20 = recode(UR20, "R" = "Rural", "U" = "Urban"))

library(ggplot2)
library(scales)
ggplot(dataset, aes(y = factor(UR20))) + 
  geom_bar(aes(x = after_stat(count))) +
  geom_text(stat = 'count', aes(label = comma(after_stat(count))),  # Use comma for thousands separators
            position = position_stack(vjust = 0.5), 
            color = "white") +  # Set label color to white
  labs(title = "Urban-Rural Station Histogram",
       x = "Classification",
       y = "Count") +
  theme_minimal()

ggplot(dataset, aes(y = factor(UR20))) + 
  geom_bar(aes(x = after_stat(count))) +
  geom_text(stat = 'count', aes(label = comma(after_stat(count))),  # Use comma for thousands separators
            position = position_stack(vjust = 0.5), 
            color = "white") +  # Set label color to white
  labs(title = "Urban-Rural Charger Histogram",
       x = "Classification",
       y = "Count") +
  theme_minimal()