def count_beans(beans):
    '''Return a dictionary mapping colors to the number of beans
    of that color.'''
    color_counts = {}
    for color in beans:
        color_counts[color] = color_counts.get(color, 0) + 1         
    return color_counts


def most_common_bean(beans):
    '''Return a 2-tuple of the color and count of the most common bean.
    Assume no ties.'''
    sorted_colors = sorted(beans, key=beans.get) # sort keys by value
    most_common_color = sorted_colors[-1] # get most common color
    largest_count = beans[most_common_color]
    return (most_common_color, largest_count)


def most_common_bean_v2(beans):
    '''Return a 2-tuple of the color and count of the most common bean.
    Assume no ties.'''
    largest_count = max(beans.values())
    for color in beans:
        if beans[color] == largest_count:
            return (color, largest_count)


def most_common_beans(beans):
    '''Return a list of 2-tuple of the color and count of the most common beans.'''
    result_list = []
    largest_count = max(beans.values())
    for color in beans:
        if beans[color] == largest_count:
            result_list.append((color, largest_count))
    return result_list


############## Project Gutenberg examples #############


import re

def count_words(filename):
    '''Return a dictionary of words to the number of times that word appears
    in filename.'''
    word_counts = {}
    file = open(filename, errors='ignore')
    for line in file: # loop over the lines of the file
        words = re.findall('[a-zA-Z]+', line) # grab all the words from the line
        for word in words:
            # tally each word
            word = word.lower() # ignore capitals
            word_counts[word] = word_counts.get(word, 0) + 1
    file.close()
    return word_counts


def top_words(filename):
    '''Return the ten most frequently used words in filename
    as (word, count) tuples.'''
    word_map = count_words(filename)
    sorted_keys = sorted(word_map, key=word_map.get)
    first_ten = sorted_keys[:20] # the ten most frequently occurring words
    top_list = []
    for word in first_ten:
        top_list.append((word, word_map[word]))
    return top_list


def unique_words(filename, all_filenames):
    '''Returns a set of words that appear in filename but NOT in
    any of all_filenames.'''
    unique_words = set(count_words(filename))
    for other_filename in all_filenames:
        if other_filename != filename:
            other_words = set(count_words(other_filename))
            unique_words -= other_words
    return unique_words