guess_fish_weight.R

guess_weight = function(posts){

  # reading in the guesses
  guesses = readLines(posts)

  # Match the guesses in kilograms and store result in vector
  kgmatch = regmatches(guesses,regexpr('[1-9]+\\.?[0-9]* *(k|K) *(g|G)(s|S)?',guesses))

  # Changing to numeric and storing in a vector
  kgnumerics = as.numeric(regmatches(kgmatch,regexpr('[1-9]+\\.?[0-9]*',kgmatch)))

  # Match the guesses in pounds and store result in vector
  lbmatch = regmatches(guesses,regexpr('[1-9]+\\.?[0-9]* *(l|L) *(b|B)(s|S)?',guesses))

  # Changing to numeric and storing in a vector
  lbnumerics = as.numeric(regmatches(lbmatch,regexpr('[1-9]+\\.?[0-9]*',lbmatch)))

  # Converting lbs to kgs
  lbnumericsK = lbnumerics*0.453592

  # Combining both measures
  totalGuesses = append(kgnumerics,lbnumericsK) 

  # calculating the mean of the guesses
  myGuess = mean(totalGuesses)

  # summary statistics
  print(summary(totalGuesses))

  # histogram of guesses
  hist(totalGuesses)

  # vector of cleaned guesses
  invisible(totalGuesses)

}