In andangshide/farsfunctions: Analyse the accident data in different states

library(farsfunctions) library(dplyr) library(maps)

Introduction

This is a package to deal with the data from US National Highway Traffic Safety Administration's Fatality Analysis Reporting System, it can analyse the accident datas from different states in different years.

Functions

make_filename

this function makes the year you want the standard file name for covenience after

make_filename <- function(year) {
  year <- as.integer(year)
  sprintf("accident_%d.csv.bz2", year)}
filename<-make_filename(2014)
print(filename)

fars_read

this function continues the make_filename funtion to read the data according to the years and make it data frame.(use the make_filename funciton first.)

fars_read <- function(filename) {
  if(!file.exists(filename))
    stop("file '", filename, "' does not exist")
  data <- suppressMessages({
    readr::read_csv(filename, progress = FALSE)
  })
  dplyr::tbl_df(data)
}
filepath <- system.file("extdata", filename, package = "farsfunctions")
accident_2014 <- fars_read(filepath)
print(head(accident_2014))

fars_read_years

this function will arrange the data by months and years

fars_read_years <- function(years) {
        lapply(years, function(year) {
                file <- make_filename(year)
                tryCatch({
                        dat <- fars_read(system.file("extdata", file, package = "farsfunctions"))
                        dplyr::mutate(dat, year = year) %>% 
                                dplyr::select(MONTH, year)
                        }, error = function(e) {
                        warning("invalid year: ", year)
                        return(NULL)
    })
  })
}
accidents <- fars_read_years(2014)
print(accidents)

fars_summarize_years

this function will summarize the total accidents by months and show the spread sheet.

fars_summarize_years <- function(years) {
  dat_list <- fars_read_years(years)
  dplyr::bind_rows(dat_list) %>%
    dplyr::group_by(year, MONTH) %>%
    dplyr::summarize(n = n()) %>%
    tidyr::spread(year, n)
}
library(dplyr)
summary <- fars_summarize_years(2013:2015)
print(summary)

fars_map_state

this funtion will show the number of the accident in the year on the map of states

fars_map_state <- function(state.num, year) {
  filename <- make_filename(year)
  data <- fars_read(system.file("extdata", file, package = "farsfunctions"))
  state.num <- as.integer(state.num)

  if(!(state.num %in% unique(data$STATE)))
    stop("invalid STATE number: ", state.num)
  data.sub <- dplyr::filter(data, STATE == state.num)
  if(nrow(data.sub) == 0L) {
    message("no accidents to plot")
    return(invisible(NULL))
  }
  is.na(data.sub$LONGITUD) <- data.sub$LONGITUD > 900
  is.na(data.sub$LATITUDE) <- data.sub$LATITUDE > 90
  with(data.sub, {
    maps::map("state", ylim = range(LATITUDE, na.rm = TRUE),
              xlim = range(LONGITUD, na.rm = TRUE))
    graphics::points(LONGITUD, LATITUDE, pch = 46)
  })
}