sortinghat-test.R

# run unique baby names from the babynames package through the sorting hat
# used in http://blog.sellorm.com/2017/12/21/command-line-utilities-in-r-pt-4/
# to check the distribution of results

# house lookup ------------------------------------------------------------
houses <- c("0" = "Hufflepuff",
            "1" = "Gryffindor",
            "2" = "Ravenclaw",
            "3" = "Slytherin",
            "4" = "Hufflepuff",
            "5" = "Gryffindor",
            "6" = "Ravenclaw",
            "7" = "Slytherin",
            "8" = "Hufflepuff",
            "9" = "Gryffindor",
            "a" = "Ravenclaw",
            "b" = "Slytherin",
            "c" = "Hufflepuff",
            "d" = "Gryffindor",
            "e" = "Ravenclaw",
            "f" = "Slytherin"
)


# get unique names --------------------------------------------------------
student_names <- unique(babynames::babynames$name)


# Get house name ----------------------------------------------------------
get_house <- function(student_name){
  name_hash <- digest::sha1(tolower(student_name))
  house_index <- substr(name_hash, 1, 1)
  house <- houses[house_index]
  return(house)
}


# main --------------------------------------------------------------------
house_results <- lapply(student_names, get_house)
housedf <- data.frame(cbind(house_results), stringsAsFactors = TRUE)
dplyr::count(housedf, unlist(housedf$house_results))

My results look like this...

# A tibble: 4 x 2
  `unlist(housedf$house_results)`     n
                            <chr> <int>
1                      Gryffindor 23783
2                      Hufflepuff 23587
3                       Ravenclaw 23913
4                       Slytherin 23742

Thank you very much for the informative survey of the command line arugment paser packages!

re: this code, I think convert hex to decimal and take mod might be less tedious.

# run unique baby names from the babynames package through the sorting hat
# used in http://blog.sellorm.com/2017/12/21/command-line-utilities-in-r-pt-4/
# to check the distribution of results

# house lookup ------------------------------------------------------------
houses <- c("Hufflepuff", "Gryffindor", "Ravenclaw", "Slytherin")


# get unique names --------------------------------------------------------
student_names <- unique(babynames::babynames$name)


# Get house name ----------------------------------------------------------
get_house <- function(student_name){
  name_hash <- digest::sha1(tolower(student_name))
  house_index <- strtoi(substr(name_hash, 1, 1), base = 16) %% 4 + 1
  house <- houses[house_index]
  return(house)
}


# main --------------------------------------------------------------------
house_results <- lapply(student_names, get_house)
housedf <- data.frame(cbind(house_results), stringsAsFactors = TRUE)
dplyr::count(housedf, unlist(housedf$house_results))
#> # A tibble: 4 x 2
#>   `unlist(housedf$house_results)`     n
#>   <chr>                           <int>
#> 1 Gryffindor                      23783
#> 2 Hufflepuff                      23587
#> 3 Ravenclaw                       23913
#> 4 Slytherin                       23742

Created on 2018-04-15 by the reprex package (v0.2.0).