Calculate number of words in sentences using map/reduce and sorting dictionary by value in descending order

count_words.py

'''Calculating number of words and number of times they occurred in sentences

Example of how to use map, reduce, and sorting dictionary by value

Available functions:
- count_words: counts how many times each word occurred in the sentence
- combine_counts: combines two dictionaries. In other word sums up number of
                    times word occurred in each sentence
'''

from functools import reduce


def count_words(sentence):
    '''Counts number of words in sentence
    
    Args:
        sentence: target sentence to be processed

    Returns:
        Dictionary of words and number of times it occurred in sentence
    '''

    normalized_doc = ''.join(c.lower()
                                  if c.isalpha()
                                  else ' ' for c in sentence)
    frequencies = {}
    for word in normalized_doc.split():
        frequencies[word] = frequencies.get(word, 0) + 1
    return frequencies


def combine_counts(d1, d2):
    '''Combines two dictionaries in one.

    Each processed sentence data stored in dictionary.
    This function combines two dictionaries with correct
    number of words occurred.
    
    Args:
        d1: first dictionary
        d2: second dictionary

    Result:
        Combined dictionary that contains sum of words
        and number of times they occurred
    '''

    d = d1.copy()
    for word, count in d2.items():
        d[word] = d.get(word, 0) + count
    return d


# Words from Python manifesto example
manifesto = [
    "Beautiful is better than ugly.",
    "Explicit is better than implicit.",
    "Simple is better than complex.",
    "Complex is better than complicated.",
    "Flat is better than nested.",
    "Sparse is better than dense.",
    "Readability counts.",
    "Special cases aren't special enough to break the rules.",
    "Although practicality beats purity.",
    "Errors should never pass silently.",
    "Unless explicitly silenced.",
    "In the face of ambiguity, refuse the temptation to guess.",
    "There should be one-- and preferably only one --obvious way to do it.",
    "Although that way may not be obvious at first unless you're Dutch.",
    "Now is better than never.",
    "Although never is often better than *right* now.",
    "If the implementation is hard to explain, it's a bad idea.",
    "If the implementation is easy to explain, it may be a good idea.",
    "Namespaces are one honking great idea -- let's do more of those!"
]

def main():
    '''Main entries of the module'''

    # get list of dictionaries for each sentence
    words = map(count_words, manifesto)
    # get total number of words and number of times they occurred
    total_counts = reduce(combine_counts, words)
    # print result
    for w, c in sorted(total_counts.items(), key=lambda x: x[1], reverse=True):
        #print('{0:15}{1}'.format(w, c))     # Python less than 3.6
        print(f'{w:15}{c}')


if __name__ == '__main__':
    main()