MPQALexicon.py

def load():
  filename = "subjclueslen1-HLTEMNLP05.tff"
  f = open(filename)
  lines = f.readlines()
  f.close()
  words = []
  labels = []
  for line in lines:
    fields = line.split(" ")
    fields = [field for field in fields if "=" in field] #ugh, two lines have a random extra char in them
    d = dict([field.rstrip().split("=") for field in fields])
    (word, label, pos) = d["word1"], d["priorpolarity"], d["pos1"]
    if pos == "adj":
      if label == "positive":
        words.append(word)
        labels.append("pos")
      elif label == "negative":
        words.append(word)
        labels.append("neg")
  return (words, labels)