wordcount.py

import sys

# +++your code here+++
# Define print_words(filename) and print_top(filename) functions.
# You could write a helper utility function that reads a file
# and builds and returns a word/count dict for it.
# Then print_words() and print_top() can just call the utility function.

###

def open_file_dict(filename):

    word_count = {}
    f = open(filename, 'r')

    for line in f:
        words = line.split()
        for to_lower in words:
            lower_words = to_lower.lower()
            #print lower_words

            if not lower_words in word_count: # if not exist yet lower_words in word_count
                word_count[lower_words] = 1   # put it in the dictionary
            else: # if it is already exist
                word_count[lower_words] = word_count[lower_words] + 1 #increment it by how many there is by 1
    return word_count


def print_words(filename):


    word_count = open_file_dict(filename)

    words = sorted(word_count.keys())

    for word in words:
        print word, word_count[word]


def get_count(word_count_tuple):
  """Returns the count from a dict word/count tuple  -- used for custom sort."""
  return word_count_tuple[1]



def print_top(filename):

    word_count = word_count_dict(filename)

    items = sorted(word_count.items(), key=get_count, reverse=True)

  # Print the first 20
    for item in items[:20]:
        print item[0], item[1]



# This basic command line argument parsing code is provided and
# calls the print_words() and print_top() functions which you must define.
def main():
  if len(sys.argv) != 3:
    print 'usage: ./wordcount.py {--count | --topcount} file'
    sys.exit(1)

  option = sys.argv[1]
  filename = sys.argv[2]
  if option == '--count':
    print_words(filename)
  elif option == '--topcount':
    print_top(filename)
  else:
    print 'unknown option: ' + option
    sys.exit(1)

if __name__ == '__main__':
  main()