Add FFS data?

[philiporlando]

I was working on a separate project that relied on the FFS data. It might be interesting to include this data source within this project and compare it against the managed care provider data.

library(dplyr)
library(fs)
library(glue)
library(httr2)
library(readr)
library(stringr)


# Helper function to derive the current month's file name from the response url
get_file_name_from_url <- function(url) {
  file_name <- url |>
    fs::path_file() |>
    stringr::str_remove("\\?.*$")
}

# Main function to download the latest FFS file and return it as a dataframe
get_latest_ffs_data <- function() {
  
  # This url will automatically navigate to the latest file version (e.g. medi_cal_ffs_provider_listing_9_25_24.csv)
  url <- "https://data.chhs.ca.gov/dataset/profile-of-enrolled-medi-cal-fee-for-service-ffs-providers/resource/d652b210-ec3d-4a92-b7e0-e55c3dcbc7dc/download"
  response <- httr2::request(url) |>
    httr2::req_perform()
  
  # Guard clause to handle invalid HTTP status codes
  status_code <- httr2::resp_status(response)
  if (status_code != 200L) {
    stop(glue::glue("Invalid HTTP status code {status_code} returned when querying {url}"))
  }
  
  # Guard clause to handle invalid content type (if the URL returns anything besides a text file)
  content_type <- httr2::resp_header(response, "Content-Type")
  if (stringr::str_detect(content_type, "text/csv", negate = TRUE)) {
    stop(glue::glue("Invalid content type {content_type} returned when querying {url}"))
  }
  
  # Extract the monthly file name from the URL
  file_name <- get_file_name_from_url(response$url)
  file_path <- fs::path(tempdir(), file_name)
  
  # Save the response body to a local temp file
  writeBin(response$body, file_path)
  
  # Read in the csv contents as a dataframe
  df <- readr::read_csv(file_path) |> 
    janitor::clean_names() |> 
    # Include the basename of the source file as a new column
    dplyr::mutate(
      source_file = {{ file_name }}
    )
  
  return(df)
}

df <- get_latest_ffs_data()