FIx unit test

Author: franchuterivera

autoPyTorch/api/base_task.py

@@ -749,14 +749,14 @@ def _search(
                 running the top performing pipelines on max_budget.
                 min_budget states the minimum resource allocation a pipeline should have
                 so that we can compare and quickly discard bad performing models.
-                For example, if the budget_type is epochs, and min_epochs=5, then we will
+                For example, if the budget_type is epochs, and min_budget=5, then we will
                 run every pipeline to a minimum of 5 epochs before performance comparison.
             max_budget (int):
                 Auto-PyTorch uses `Hyperband <https://arxiv.org/abs/1603.06560>_` to
                 trade-off resources between running many pipelines at min_budget and
                 running the top performing pipelines on max_budget.
                 max_budget states the maximum resource allocation a pipeline is going to
-                be ran. For example, if the budget_type is epochs, and max_epochs=50,
+                be ran. For example, if the budget_type is epochs, and max_budget=50,
                 then the pipeline training will be terminated after 50 epochs.
             total_walltime_limit (int), (default=100): Time limit
                 in seconds for the search of appropriate models.

autoPyTorch/api/tabular_classification.py

@@ -159,14 +159,14 @@ def search(
                 running the top performing pipelines on max_budget.
                 min_budget states the minimum resource allocation a pipeline should have
                 so that we can compare and quickly discard bad performing models.
-                For example, if the budget_type is epochs, and min_epochs=5, then we will
+                For example, if the budget_type is epochs, and min_budget=5, then we will
                 run every pipeline to a minimum of 5 epochs before performance comparison.
             max_budget (int):
                 Auto-PyTorch uses `Hyperband <https://arxiv.org/abs/1603.06560>_` to
                 trade-off resources between running many pipelines at min_budget and
                 running the top performing pipelines on max_budget.
                 max_budget states the maximum resource allocation a pipeline is going to
-                be ran. For example, if the budget_type is epochs, and max_epochs=50,
+                be ran. For example, if the budget_type is epochs, and max_budget=50,
                 then the pipeline training will be terminated after 50 epochs.
             total_walltime_limit (int), (default=100): Time limit
                 in seconds for the search of appropriate models.

autoPyTorch/api/tabular_regression.py

@@ -151,14 +151,14 @@ def search(
                 running the top performing pipelines on max_budget.
                 min_budget states the minimum resource allocation a pipeline should have
                 so that we can compare and quickly discard bad performing models.
-                For example, if the budget_type is epochs, and min_epochs=5, then we will
+                For example, if the budget_type is epochs, and min_budget=5, then we will
                 run every pipeline to a minimum of 5 epochs before performance comparison.
             max_budget (int):
                 Auto-PyTorch uses `Hyperband <https://arxiv.org/abs/1603.06560>_` to
                 trade-off resources between running many pipelines at min_budget and
                 running the top performing pipelines on max_budget.
                 max_budget states the maximum resource allocation a pipeline is going to
-                be ran. For example, if the budget_type is epochs, and max_epochs=50,
+                be ran. For example, if the budget_type is epochs, and max_budget=50,
                 then the pipeline training will be terminated after 50 epochs.
             total_walltime_limit (int), (default=100): Time limit
                 in seconds for the search of appropriate models.

autoPyTorch/optimizer/smbo.py

@@ -178,14 +178,14 @@ def __init__(self,
                 running the top performing pipelines on max_budget.
                 min_budget states the minimum resource allocation a pipeline should have
                 so that we can compare and quickly discard bad performing models.
-                For example, if the budget_type is epochs, and min_epochs=5, then we will
+                For example, if the budget_type is epochs, and min_budget=5, then we will
                 run every pipeline to a minimum of 5 epochs before performance comparison.
             max_budget (int):
                 Auto-PyTorch uses `Hyperband <https://arxiv.org/abs/1603.06560>_` to
                 trade-off resources between running many pipelines at min_budget and
                 running the top performing pipelines on max_budget.
                 max_budget states the maximum resource allocation a pipeline is going to
-                be ran. For example, if the budget_type is epochs, and max_epochs=50,
+                be ran. For example, if the budget_type is epochs, and max_budget=50,
                 then the pipeline training will be terminated after 50 epochs.
         """
         super(AutoMLSMBO, self).__init__()

test/test_api/test_base_api.py

@@ -97,7 +97,6 @@ def test_set_pipeline_config():
     estimator = BaseTask()
     pipeline_options = {"device": "cuda",
                         "budget_type": "epochs",
-                        "min_epochs": 10,
                         "epochs": 51,
                         "runtime": 360}
     estimator.set_pipeline_config(**pipeline_options)

test/test_evaluation/test_train_evaluator.py

@@ -87,6 +87,7 @@ def tearDown(self):
 
     @unittest.mock.patch('autoPyTorch.pipeline.tabular_classification.TabularClassificationPipeline')
     def test_holdout(self, pipeline_mock):
+        pipeline_mock.fit_dictionary = {'budget_type': 'epochs', 'epochs': 50}
         # Binary iris, contains 69 train samples, 31 test samples
         D = get_binary_classification_datamanager()
         pipeline_mock.predict_proba.side_effect = \
@@ -99,7 +100,8 @@ def test_holdout(self, pipeline_mock):
         backend_api.load_datamanager = lambda: D
         queue_ = multiprocessing.Queue()
 
-        evaluator = TrainEvaluator(backend_api, queue_, configuration=configuration, metric=accuracy, budget=0)
+        evaluator = TrainEvaluator(backend_api, queue_, configuration=configuration, metric=accuracy, budget=0,
+                                   pipeline_config={'budget_type': 'epochs', 'epochs': 50})
         evaluator.file_output = unittest.mock.Mock(spec=evaluator.file_output)
         evaluator.file_output.return_value = (None, {})
 
@@ -137,7 +139,8 @@ def test_cv(self, pipeline_mock):
         backend_api.load_datamanager = lambda: D
         queue_ = multiprocessing.Queue()
 
-        evaluator = TrainEvaluator(backend_api, queue_, configuration=configuration, metric=accuracy, budget=0)
+        evaluator = TrainEvaluator(backend_api, queue_, configuration=configuration, metric=accuracy, budget=0,
+                                   pipeline_config={'budget_type': 'epochs', 'epochs': 50})
         evaluator.file_output = unittest.mock.Mock(spec=evaluator.file_output)
         evaluator.file_output.return_value = (None, {})
 
@@ -241,7 +244,8 @@ def test_predict_proba_binary_classification(self, mock):
         configuration = unittest.mock.Mock(spec=Configuration)
         queue_ = multiprocessing.Queue()
 
-        evaluator = TrainEvaluator(self.backend_mock, queue_, configuration=configuration, metric=accuracy, budget=0)
+        evaluator = TrainEvaluator(self.backend_mock, queue_, configuration=configuration, metric=accuracy, budget=0,
+                                   pipeline_config={'budget_type': 'epochs', 'epochs': 50})
 
         evaluator.fit_predict_and_loss()
         Y_optimization_pred = self.backend_mock.save_numrun_to_dir.call_args_list[0][1][