# Install and load the tidyverse packages if not already installed
if (!requireNamespace("tidyverse", quietly = TRUE)) {
  install.packages("tidyverse")
}
library(tidyverse)

# Read the raw data from the CSV file
raw_data <- read_csv("measuring_distress.csv")

# Rename columns and make them tidy
cleaned_data <- raw_data %>%
  rename(
    Geography = "2022 Per Capita Money Income (ACS 5-year PCMI)",
    Unemployment = "24 Month Unemployment",
    Unemployment_Threshold_Calculation = "Threshold Calculation",
    BEA_PCPI = "BEA PCPI",
    BEA_PCPI_Threshold_Calculation = "Threshold Calculation.1",
    ACS_PCMI = "ACS 5-Year PCMI",
    ACS_PCMI_Threshold_Calculation = "Threshold Calculation.2"
  ) %>%
  mutate(across(everything(), as.character)) %>%  # Convert all columns to character
  mutate(
    Unemployment = as.numeric(Unemployment),
    Unemployment_Threshold_Calculation = as.numeric(Unemployment_Threshold_Calculation),
    BEA_PCPI = as.numeric(gsub("\\$", "", BEA_PCPI)),
    BEA_PCPI_Threshold_Calculation = as.numeric(gsub("\\$", "", BEA_PCPI_Threshold_Calculation)),
    ACS_PCMI = as.numeric(gsub("\\$", "", ACS_PCMI)),
    ACS_PCMI_Threshold_Calculation = as.numeric(gsub("\\$", "", ACS_PCMI_Threshold_Calculation))
  )  # Convert numeric columns to numeric format

# Export the cleaned dataset to a new CSV file
write_csv(cleaned_data, "cleaned_measuring_distress.csv")