Merge pull request #595 from automl/development

Prepare release of Auto-sklearn 0.4.2

Author: mfeurer

autosklearn/__version__.py

@@ -1,4 +1,4 @@
 """Version information."""
 
 # The following line *must* be the last in the module, exactly as formatted:
-__version__ = "0.4.1"
+__version__ = "0.4.2"

autosklearn/automl.py

@@ -66,6 +66,7 @@ def __init__(self,
                  initial_configurations_via_metalearning=25,
                  ensemble_size=1,
                  ensemble_nbest=1,
+                 ensemble_memory_limit=1000,
                  seed=1,
                  ml_memory_limit=3072,
                  metadata_directory=None,
@@ -94,6 +95,7 @@ def __init__(self,
             initial_configurations_via_metalearning
         self._ensemble_size = ensemble_size
         self._ensemble_nbest = ensemble_nbest
+        self._ensemble_memory_limit = ensemble_memory_limit
         self._seed = seed
         self._ml_memory_limit = ml_memory_limit
         self._data_memory_limit = None
@@ -635,18 +637,22 @@ def _get_ensemble_process(self, time_left_for_ensembles,
         else:
             self._ensemble_size = ensemble_size
 
-        return EnsembleBuilder(backend=self._backend,
-                               dataset_name=dataset_name,
-                               task_type=task,
-                               metric=metric,
-                               limit=time_left_for_ensembles,
-                               ensemble_size=ensemble_size,
-                               ensemble_nbest=ensemble_nbest,
-                               seed=self._seed,
-                               shared_mode=self._shared_mode,
-                               precision=precision,
-                               max_iterations=max_iterations,
-                               read_at_most=np.inf)
+        return EnsembleBuilder(
+            backend=self._backend,
+            dataset_name=dataset_name,
+            task_type=task,
+            metric=metric,
+            limit=time_left_for_ensembles,
+            ensemble_size=ensemble_size,
+            ensemble_nbest=ensemble_nbest,
+            seed=self._seed,
+            shared_mode=self._shared_mode,
+            precision=precision,
+            max_iterations=max_iterations,
+            read_at_most=np.inf,
+            memory_limit=self._ensemble_memory_limit,
+            random_state=self._seed,
+        )
 
     def _load_models(self):
         if self._shared_mode:

autosklearn/data/xy_data_manager.py

@@ -2,7 +2,6 @@
 
 import numpy as np
 from scipy import sparse
-import six
 
 from autosklearn.constants import *
 from autosklearn.data.abstract_data_manager import AbstractDataManager
@@ -13,7 +12,7 @@ class XYDataManager(AbstractDataManager):
     def __init__(self, X, y, X_test, y_test, task, feat_type, dataset_name):
         super(XYDataManager, self).__init__(dataset_name)
 
-        if isinstance(task, six.string_types):
+        if isinstance(task, str):
             task = STRING_TO_TASK_TYPES[task]
 
         self.info['task'] = task