classifier_hyperopt_tuning.py 文件源码

def cv_score(classifier, dataset, metric=accuracy_score, n_folds=10):
  """
  Calculate K-fold cross validation score.
  """  
  true_labels = []
  predicted_labels = []
  for train_idx, test_idx in StratifiedKFold(list(dataset.get_labels()), n_folds=n_folds):
    # clear the classifier (call `clear` RPC).
    classifier.clear()

    # split the dataset to train/test dataset.
    (train_ds, test_ds) = (dataset[train_idx], dataset[test_idx])

    # train the classifier using train dataset.
    for (idx, label) in classifier.train(train_ds):
      pass

    # test the classifier using test dataset.
    for (idx, label, result) in classifier.classify(test_ds):     
      # labels are already desc sorted by score values, so you can get a label
      # name with the hightest prediction score by:
      pred_label = result[0][0]

      # store the result.
      true_labels.append(label)
      predicted_labels.append(pred_label)

  # return cross-validation score
  return metric(true_labels, predicted_labels)