A quick and dirty implementation of the cohort model of word recognition (devised by Marslen-Wilson, I believe?)

cohortModel.py

def cohortModel(word, EnglishWords):
    soFar = ''                                 # when we start, we haven't heard anything yet, so we'll represent that as an empty string
    candidates = set(EnglishWords)             # before we've heard anything, all the words we know are possible
    for letter in word:                        # then start listening to the word letter by letter
        soFar += letter                        # add the newly heard letter to the portion of the word heard so far
        for word in set(candidates):           # now look through the candidate words
            if not word.startswith(soFar):     # if the word seen so far is NOT consistent with a word we know
                candidates.remove(word)        # remove the word from the candidates
        print("These are the possible words when we've heard {} so far:\n{}".format(str(soFar),str(candidates)))
    return candidates

# run the model on a tiny fragment of English

EnglishWords = set(['cathedral', 'cat','dog','catheter'])
word = 'cathedral'

print("After hearing everything, the only possible word(s) are {}".format(cohortModel(word, EnglishWords)))