# Design Example
# Text Analysis Module


def read_words(filename):
    """Given a filename, return a dictionary mapping each word in
    filename to its frequency in the file"""
    wordfile = open(filename)
    worddata = wordfile.read()
    word_list = worddata.split()
    wordfile.close()
    wordcounts_dict = {}
    for word in word_list:
        # See the lecture slides for more on setdefault
        count = wordcounts_dict.setdefault(word, 0)
        wordcounts_dict[word] = count + 1
    return wordcounts_dict


def word_count(wordcounts_dict, word):
    """Given a dictionary mapping word to counts, return the count of
    the given word in the dictionary. """
    # Could also do: return wordcounts_dict.get(word, 0)
    if word in wordcounts_dict:
        return wordcounts_dict[word]
    else:
        return 0


def topk(wordcounts_dict, k=10):
    """Given a dictionary mapping word to counts, return a list of
    (count, word) tuples of the top k most frequent words in the dictionary,
    sorted from most to least frequent. If less then k unique words in
    wordcounts_dict, return all words.
    If more than one word has a certain count, the ordering between
    them is unspecified.  Returns at most k words.  If the k+1th word has
    the same count as the kth word, pick which one to return arbitrarily."""
    # Could also do sorting as we have done before using itemgetter
    # and multiple sorts. Here we use a list comprehension to create
    # a list of (count, word) tuples.
    counts_with_words = [(c, w) for (w, c) in wordcounts_dict.items()]
    counts_with_words.sort(reverse=True)
    return counts_with_words[0:k]


def total_words(wordcounts_dict):
    """Given a dictionary mapping word to counts, return the total
    number of words used to create the dictionary"""
    return sum(wordcounts_dict.values())