Error running tutorial example

I'm trying to run the sample code provided here:
And I'm getting this error:
Welcome to auto_ml! We're about to go through and make sense of your data using machine learning, and give you a production-ready pipeline to get predictions with.

If you have any issues, or new feature ideas, let us know at http://auto.ml
Now using the model training_params that you passed in:
{}
After overwriting our defaults with your values, here are the final params that will be used to initialize the model:
{'presort': False, 'learning_rate': 0.1, 'warm_start': True}
Running basic data cleaning
Fitting DataFrameVectorizer
Now using the model training_params that you passed in:
{}
After overwriting our defaults with your values, here are the final params that will be used to initialize the model:
{'presort': False, 'learning_rate': 0.1, 'warm_start': True}

********************************************************************************************
About to fit the pipeline for the model GradientBoostingRegressor to predict MEDV
Started at:
2018-01-04 14:22:46
[1] random_holdout_set_from_training_data's score is: -8.721
---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
<ipython-input-45-2b110959d739> in <module>()
     11 ml_predictor = Predictor(type_of_estimator='regressor', column_descriptions=column_descriptions)
     12 
---> 13 ml_predictor.train(df_train)
     14 
     15 ml_predictor.score(df_test, df_test.MEDV)

C:\ProgramData\Anaconda3\lib\site-packages\auto_ml\predictor.py in train(***failed resolving arguments***)
    632 
    633         # This is our main logic for how we train the final model
--> 634         self.trained_final_model = self.train_ml_estimator(self.model_names, self._scorer, X_df, y)
    635 
    636         if self.ensemble_config is not None and len(self.ensemble_config) > 0:

C:\ProgramData\Anaconda3\lib\site-packages\auto_ml\predictor.py in train_ml_estimator(self, estimator_names, scoring, X_df, y, feature_learning, prediction_interval)
   1212         # Use Case 1: Super straightforward: just train a single, non-optimized model
   1213         elif (feature_learning == True and self.optimize_feature_learning != True) or (len(estimator_names) == 1 and self.optimize_final_model != True):
-> 1214             trained_final_model = self.fit_single_pipeline(X_df, y, estimator_names[0], feature_learning=feature_learning, prediction_interval=False)
   1215 
   1216         # Use Case 2: Compare a bunch of models, but don't optimize any of them

C:\ProgramData\Anaconda3\lib\site-packages\auto_ml\predictor.py in fit_single_pipeline(self, X_df, y, model_name, feature_learning, prediction_interval)
    837             print(start_time)
    838 
--> 839         ppl.fit(X_df, y)
    840 
    841         if self.verbose:

C:\ProgramData\Anaconda3\lib\site-packages\auto_ml\utils_model_training.py in fit(self, X, y)
    266 
    267                     self.model.set_params(n_estimators=num_iter, warm_start=warm_start)
--> 268                     self.model.fit(X_fit, y)
    269 
    270                     if self.training_prediction_intervals == True:

C:\ProgramData\Anaconda3\lib\site-packages\sklearn\ensemble\gradient_boosting.py in fit(self, X, y, sample_weight, monitor)
   1005                                     self.estimators_.shape[0]))
   1006             begin_at_stage = self.estimators_.shape[0]
-> 1007             y_pred = self._decision_function(X)
   1008             self._resize_state()
   1009 

C:\ProgramData\Anaconda3\lib\site-packages\sklearn\ensemble\gradient_boosting.py in _decision_function(self, X)
   1123         # not doing input validation.
   1124         score = self._init_decision_function(X)
-> 1125         predict_stages(self.estimators_, X, self.learning_rate, score)
   1126         return score
   1127 

TypeError: Argument 'X' has incorrect type (expected numpy.ndarray, got csr_matrix)
sklearn version: 0.18
After upgrade sklearn to 0.19 it worked, but this should be a requirement for pip install. Right?
ClimbsRocks / auto_ml

Error running tutorial example #369
