precompute_probs.py 文件源码

def main():
  parser = argparse.ArgumentParser()
  parser.add_argument('tags', nargs='+')
  parser.add_argument('--dest-tag', default='stacked', 
      help='Tag for generated pdict (default: "stacked")')
  parser.add_argument('--fold', default='test')
  args = parser.parse_args()

  metavec = load_metavectors(args.fold)

  #clf = train.load_model()
  clf = joblib.load('model.pkl')

  with time_me('Vectorized fold {}'.format(args.fold)):
    # TODO: this fn is not a thing?
    X, y = train.vectorize_fold(args.fold, args.tags, metavec)

  if hasattr(clf, 'predict_proba'):
    probs = clf.predict_proba(X)
    # returns an array of shape (n, 2), where each len-2 subarray
    # has the probability of the negative and positive classes. which is silly.
    probs = probs[:,1]
  else:
    scores = clf.decision_function(X)
    probs = expit(scores)

  pdict = pdictify(probs, metavec)
  common.save_pdict_for_tag(args.dest_tag, pdict, args.fold)