Failed to train the comments-content model with train_many_models

[kun-ninja]

Hi, I am new to the machine learning area, and try to train the model based on https://github.com/dragnet-org/dragnet#training-content-extraction-models, but it failed with the error ValueError: setting an array element with a sequence.
I just use the dragnet data , and my code is simply as follows:

features = ['kohlschuetter', 'weninger', 'readability']
to_extract = ['content', 'comments']

extract_all_gold_standard_data(
    data_dir=rootdir,
    nprocesses=20
)
model = ExtraTreesClassifier()
base_extractor = Extractor(
    features=features,
    to_extract=to_extract,
    model=model
)
param_grid={'n_estimators': [10, 20, 50, 75]}
extractor = train_many_models(base_extractor, param_grid, rootdir, train_out_dir, verbose=1)

The details error message is:

train.py
WARNING:root:extraction failed: too few blocks (1)
/Users/XXXXXX/dev/venv3/lib/python3.6/site-packages/sklearn/model_selection/_search.py:643: DeprecationWarning: "fit_params" as a constructor argument was deprecated in version 0.19 and will be removed in version 0.21. Pass fit parameters to the "fit" method instead.
  '"fit" method instead.', DeprecationWarning)
Fitting 5 folds for each of 4 candidates, totalling 20 fits
[Parallel(n_jobs=1)]: Using backend SequentialBackend with 1 concurrent workers.
Traceback (most recent call last):
  File "/Users/XXXXXX/dev/src/train.py", line 31, in <module>
    extractor = train_many_models(base_extractor, param_grid, rootdir, train_out_dir, verbose=1)
  File "/Users/XXXXXX/dev/venv3/lib/python3.6/site-packages/dragnet/model_training.py", line 190, in train_many_models
    gscv = gscv.fit(train_features, train_labels)
  File "/Users/XXXXXX/dev/venv3/lib/python3.6/site-packages/sklearn/model_selection/_search.py", line 722, in fit
    self._run_search(evaluate_candidates)
  File "/Users/XXXXXX/dev/venv3/lib/python3.6/site-packages/sklearn/model_selection/_search.py", line 1191, in _run_search
    evaluate_candidates(ParameterGrid(self.param_grid))
  File "/Users/XXXXXX/dev/venv3/lib/python3.6/site-packages/sklearn/model_selection/_search.py", line 711, in evaluate_candidates
    cv.split(X, y, groups)))
  File "/Users/XXXXXX/dev/venv3/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py", line 917, in __call__
    if self.dispatch_one_batch(iterator):
  File "/Users/XXXXXX/dev/venv3/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py", line 759, in dispatch_one_batch
    self._dispatch(tasks)
  File "/Users/XXXXXX/dev/venv3/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py", line 716, in _dispatch
    job = self._backend.apply_async(batch, callback=cb)
  File "/Users/XXXXXX/dev/venv3/lib/python3.6/site-packages/sklearn/externals/joblib/_parallel_backends.py", line 182, in apply_async
    result = ImmediateResult(func)
  File "/Users/XXXXXX/dev/venv3/lib/python3.6/site-packages/sklearn/externals/joblib/_parallel_backends.py", line 549, in __init__
    self.results = batch()
  File "/Users/XXXXXX/dev/venv3/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py", line 225, in __call__
    for func, args, kwargs in self.items]
  File "/Users/XXXXXX/dev/venv3/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py", line 225, in <listcomp>
    for func, args, kwargs in self.items]
  File "/Users/XXXXXX/dev/venv3/lib/python3.6/site-packages/sklearn/model_selection/_validation.py", line 528, in _fit_and_score
    estimator.fit(X_train, y_train, **fit_params)
  File "/Users/XXXXXX/dev/venv3/lib/python3.6/site-packages/sklearn/ensemble/forest.py", line 253, in fit
    sample_weight = check_array(sample_weight, ensure_2d=False)
  File "/Users/XXXXXX/dev/venv3/lib/python3.6/site-packages/sklearn/utils/validation.py", line 527, in check_array
    array = np.asarray(array, dtype=dtype, order=order)
  File "/Users/XXXXXX/dev/venv3/lib/python3.6/site-packages/numpy/core/numeric.py", line 538, in asarray
    return array(a, dtype, copy=False, order=order)
ValueError: setting an array element with a sequence.

However, if I change
to_extract = ['content', 'comments'] to to_extract = ['content'], it succeeded.

Could I have your guidance on the failure? Thanks.