paradigms9

import sys
import operator
import re

def count_combos(input_string):
  freq = {}
  words = input_string.split()
  if len(words) == 1:
    return freq
  for idx, word in enumerate(words):
    if idx+1 < len(words):
      word_pair = (word, words[idx+1])
      if word_pair in freq:
        freq[word_pair] += 1
      else:
        freq[word_pair] = 1
  return freq

def main():
  story_path = sys.argv[1]
  skip_path = sys.argv[2]

  with open(story_path, 'r') as content:
    story_content = content.read().lower()

  with open(skip_path, 'r') as content:
    skip_words = content.read().lower().split(',')

  story_content = re.sub('[\n\t.?,;:\'\"]', ' ', story_content)
  story_list = story_content.split(' ')
  story_list = list(filter(None, story_list))
  story_list = list(filter(lambda x: x not in skip_words, story_list))

  freq_dict = count_combos(" ".join(story_list))
  freq_dict = sorted(freq_dict.items(), key=operator.itemgetter(1))
  top_5 = freq_dict[len(freq_dict)-5:len(freq_dict)]

  print(f"Story file name: {story_path}")
  print(f"Skip words file name: {skip_path}")
  print(f"Skip words: {skip_words}")
  print(f"The five most frequently occuring word pairs are:")
  for pair in top_5[::-1]:
    print(f"('{pair[0][0]} {pair[0][1]}', {pair[1]})")

if __name__ == "__main__":
  main()