In cogitoergoread/fars: Helper package to process data from accidents for a US states by year

The package supports summary and plot functions for the data of US accidents.

Data: US Accidents

The package operates on the data from the US National Highway Traffic Safety Administration's Fatality Analysis Reporting System, which is a nationwide census providing the American public yearly data regarding fatal injuries suffered in motor vehicle traffic crashes.

Package content

The following functions are for loading a specific year's data from the compressed data file:

• fars_read(filename) to read data from a file
• make_filename(year) to create a specific filename for the year datafile
• fars_read_years(years) to read data forone or more years

There are two important entry points for displaying the statistical data:

• fars_summarize_years(years) produces a table for the monthly number of accidents by years
• fars_map_state(state.num, year) plots a map of the US state for a given year

Important to note, the datafiles should be at the working directory!

Create a filename with make_filename()

It is important to properly follow the naming convention of the datafiles. The function returns the name of the datafile calculated from the year parameter.

Usage:

make_filename(2014)
[1] "accident_2014.csv.bz2"

The result of this function is used by fars_read_years() and fars_map_state.

Read one years data with fars_read()

The function tries to read the compressed CSV fájl. If no files can be read an error is thrown.

The function has no path parametres, so the datafiles should be at the workig directory.

The function returs a data frame, containing the accidents data from the required year.

Usage:

accdf<-fars_read(filename="accident_2014.csv.bz2")
str(accdf)
Classes ‘tbl_df’, ‘tbl’ and 'data.frame':   30056 obs. of  50 variables:
 $ STATE     : int  1 1 1 1 1 1 1 1 1 1 ...
 $ ST_CASE   : int  10001 10002 10003 10004 10005 10006 10007 10008 10009 10010 ...
 $ VE_TOTAL  : int  1 1 2 3 1 1 3 2 3 2 ...
...

The result of this function is used by fars_read_years() and fars_map_state.

Read one or more years data with fars_read_years()

The function reads the data from the specified years, then keeps the year and month infromation. The function is a vectorized wrapper for make_filename() and fars_read().

The result of the function is a data frame with two columns for the month and year of a sample.

Usage:

accdm<-fars_read_years(years=c(2014,2015))
str(accdm)
List of 2
 $ :Classes ‘tbl_df’, ‘tbl’ and 'data.frame':   30056 obs. of  2 variables:
  ..$ MONTH: int [1:30056] 1 1 1 1 1 1 1 1 1 1 ...
  ..$ year : num [1:30056] 2014 2014 2014 2014 2014 ...
 $ :Classes ‘tbl_df’, ‘tbl’ and 'data.frame':   32166 obs. of  2 variables:
  ..$ MONTH: int [1:32166] 1 1 1 1 1 1 1 1 1 1 ...
  ..$ year : num [1:32166] 2015 2015 2015 2015 2015 ...

The result of the functin is used by fars_summarize_years()

Display monthly data with fars_summarize_years()

The function aggregates the monthly number of accidents by year.

Summarises the data supplied by fars_read_years().

The result is a data frame with 12 rows for each month. The columns contains the number of accidents by year.

Usage:

accsumm<-fars_summarize_years(years=c(2014,2015))
accsumm
# A tibble: 12 x 3
   MONTH `2014` `2015`
 * <int>  <int>  <int>
 1     1   2168   2368
 2     2   1893   1968
 3     3   2245   2385
 4     4   2308   2430
 5     5   2596   2847
 6     6   2583   2765
 7     7   2696   2998
 8     8   2800   3016
 9     9   2618   2865
10    10   2831   3019
11    11   2714   2724
12    12   2604   2781

Plot a map with fars_map_state()

The function plots the locations of the accidents in a US state to a map.

It is based on the data read by fars_read() for a filename supplied by make_filename() .

Usage:

fars_map_state(state.num=1,year=2015)

cogitoergoread/fars documentation built on Jan. 25, 2020, 1:12 p.m.