This is realated to a discussion that me and my girlfriend were having about the Infinite monkey theorem. Needless to say it devolved into us wondering what the average word length of all of shakespeare is. Text file is from Project Gutenberg and can be found on their website.

shakespeare.py

def main():

    words = {
        # word: [
        #     length,
        #     count
        # ]
    }

    with open('t8.shakespeare.txt', 'r', encoding='utf-8') as file:
        comment = False

        for line in file:
            if '>>' in line:
                comment = False
                continue

            if '<<' in line or comment is True:
                comment = True
                continue

            for word in line.split():
                # add word to dictionary
                if word in words.keys():
                    words[word][1] = words[word][1] + 1
                else:
                    words[word] = [len(word), 1]

    printStats(words)


def printStats(dict):
    print("Stats:")

    totalChars = 0
    for word in dict:
        totalChars += dict[word][0]*dict[word][1]
    totalWords = 0
    for word in dict:
        totalWords += dict[word][1]
    avgWordLen = totalChars / totalWords
    print("Avg word length:", round(avgWordLen, 4))

    sort = sorted(dict, key=lambda w: dict[w][1], reverse=True)
    iteration = 10
    i = 0
    print("Top", iteration, "occured words in Shakespeare's writing...")
    for word in sort:
        if i > iteration:
            break
        print("|_", word)
        print("| |_ Length:", dict[word][0])
        print("| |_ Occurence:", dict[word][1])
        i += 1


if __name__ == '__main__':
    main()