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

problems(raw) %>% 
  print(n=Inf)

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`
  )

problems(dataset) %>% 
  print(n=Inf)

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")) %>%
  mutate('Total Chargers' = rowSums(select(., `EV Level2 EVSE Num`, `EV DC Fast Count`), na.rm = TRUE))

filtered_df <- dataset %>%
  filter(!is.na(`EV Level2 EVSE Num`) & !is.na(`EV DC Fast Count`))

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()



charger_by_UR20_summary <- dataset %>%
  group_by(UR20) %>%
  summarise(`Total Chargers` = sum(`Total Chargers`))

ggplot(charger_by_UR20_summary, aes(x = UR20, y = `Total Chargers`)) +
  geom_bar(stat = "identity", fill = "skyblue", color = "black") +
  geom_text(aes(label = comma(`Total Chargers`)), 
            vjust = -0.5, size = 5) +  # Label position
  labs(title = "Total Chargers by UR20",
       x = "UR20",
       y = "Total Chargers") +
  theme_minimal()