[MAINT] Drop 3.6 python support (#258)

* Drop 3.6 python

* torch tensor fix

* Increase samples

* fix flake

Author: franchuterivera

.github/workflows/pytest.yml

@@ -8,7 +8,7 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: [3.6, 3.7, 3.8]
+        python-version: [3.7, 3.8]
         include:
           - python-version: 3.8
             code-cov: true
@@ -52,4 +52,4 @@ jobs:
       uses: codecov/codecov-action@v1
       with:
         fail_ci_if_error: true
-        verbose: true
+        verbose: true

autoPyTorch/pipeline/components/preprocessing/image_preprocessing/normalise/ImageNormalizer.py

@@ -2,7 +2,7 @@
 
 import numpy as np
 
-import torch.tensor
+import torch
 
 from autoPyTorch.pipeline.components.preprocessing.image_preprocessing.normalise.base_normalizer import BaseNormalizer
 
@@ -30,16 +30,16 @@ def fit(self, X: Dict[str, Any], y: Optional[Any] = None) -> "ImageNormalizer":
         self.std = X['dataset_properties']['std']
         return self
 
-    def __call__(self, X: Union[np.ndarray, torch.tensor]) -> Union[np.ndarray, torch.tensor]:
+    def __call__(self, X: Union[np.ndarray, torch.Tensor]) -> Union[np.ndarray, torch.Tensor]:
         """
         Makes the autoPyTorchPreprocessingComponent Callable. Calling the component
         calls the transform function of the underlying early_preprocessor and
         returns the transformed array.
         Args:
-            X (Union[np.ndarray, torch.tensor]): input data tensor
+            X (Union[np.ndarray, torch.Tensor]): input data tensor
 
         Returns:
-            Union[np.ndarray, torch.tensor]: Transformed data tensor
+            Union[np.ndarray, torch.Tensor]: Transformed data tensor
         """
         X = (X - self.mean) / self.std
         return X

autoPyTorch/pipeline/components/preprocessing/image_preprocessing/normalise/NoNormalizer.py

@@ -2,7 +2,7 @@
 
 import numpy as np
 
-import torch.tensor
+import torch
 
 from autoPyTorch.pipeline.components.preprocessing.image_preprocessing.normalise.base_normalizer import (
     BaseNormalizer
@@ -34,16 +34,16 @@ def transform(self, X: Dict[str, Any]) -> Dict[str, Any]:
         X.update({'normalise': self})
         return X
 
-    def __call__(self, X: Union[np.ndarray, torch.tensor]) -> Union[np.ndarray, torch.tensor]:
+    def __call__(self, X: Union[np.ndarray, torch.Tensor]) -> Union[np.ndarray, torch.Tensor]:
         """
         Makes the autoPyTorchPreprocessingComponent Callable. Calling the component
         calls the transform function of the underlying early_preprocessor and
         returns the transformed array.
         Args:
-            X (Union[np.ndarray, torch.tensor]): input data tensor
+            X (Union[np.ndarray, torch.Tensor]): input data tensor
 
         Returns:
-            Union[np.ndarray, torch.tensor]: Transformed data tensor
+            Union[np.ndarray, torch.Tensor]: Transformed data tensor
         """
         return X
 

setup.py

@@ -1,4 +1,10 @@
 import setuptools
+import sys
+if sys.version_info < (3, 7):
+    raise ValueError(
+        'Unsupported Python version %d.%d.%d found. Auto-PyTorch requires Python '
+        '3.7 or higher.' % (sys.version_info.major, sys.version_info.minor, sys.version_info.micro)
+    )
 
 with open("README.md", "r") as f:
     long_description = f.read()
@@ -27,10 +33,12 @@
         "Topic :: Utilities",
         "Topic :: Scientific/Engineering",
         "Topic :: Scientific/Engineering :: Artificial Intelligence",
-        "Programming Language :: Python :: 3",
+        'Programming Language :: Python :: 3.7',
+        'Programming Language :: Python :: 3.8',
+        'Programming Language :: Python :: 3.9',
         "License :: OSI Approved :: BSD License",
     ],
-    python_requires='>=3',
+    python_requires='>=3.7',
     platforms=['Linux'],
     install_requires=requirements,
     include_package_data=True,

test/conftest.py

@@ -26,7 +26,7 @@
 from autoPyTorch.utils.pipeline import get_dataset_requirements
 
 
-N_SAMPLES = 200
+N_SAMPLES = 300
 
 
 @pytest.fixture(scope="session")
@@ -222,7 +222,7 @@ def get_tabular_data(task):
         validator = TabularInputValidator(is_classification=True).fit(X.copy(), y.copy())
 
     elif task == "regression_numerical_only":
-        X, y = make_regression(n_samples=N_SAMPLES,
+        X, y = make_regression(n_samples=3 * N_SAMPLES,
                                n_features=4,
                                n_informative=3,
                                n_targets=1,

test/test_api/test_api.py

@@ -2,7 +2,6 @@
 import os
 import pathlib
 import pickle
-import sys
 import unittest
 from test.test_api.utils import dummy_do_dummy_prediction, dummy_eval_function, dummy_traditional_classification
 
@@ -63,17 +62,11 @@ def test_tabular_classification(openml_id, resampling_strategy, backend, resampl
     X_train, X_test, y_train, y_test = sklearn.model_selection.train_test_split(
         X, y, random_state=42)
 
-    include = None
-    # for python less than 3.7, learned entity embedding
-    # is not able to be stored on disk (only on CI)
-    if sys.version_info < (3, 7):
-        include = {'network_embedding': ['NoEmbedding']}
     # Search for a good configuration
     estimator = TabularClassificationTask(
         backend=backend,
         resampling_strategy=resampling_strategy,
         resampling_strategy_args=resampling_strategy_args,
-        include_components=include,
         seed=42,
     )
 
@@ -210,18 +203,14 @@ def test_tabular_classification(openml_id, resampling_strategy, backend, resampl
     assert 'train_loss' in incumbent_results
 
     # Check that we can pickle
-    # Test pickle
-    # This can happen on python greater than 3.6
-    # as older python do not control the state of the logger
-    if sys.version_info >= (3, 7):
-        dump_file = os.path.join(estimator._backend.temporary_directory, 'dump.pkl')
+    dump_file = os.path.join(estimator._backend.temporary_directory, 'dump.pkl')
 
-        with open(dump_file, 'wb') as f:
-            pickle.dump(estimator, f)
+    with open(dump_file, 'wb') as f:
+        pickle.dump(estimator, f)
 
-        with open(dump_file, 'rb') as f:
-            restored_estimator = pickle.load(f)
-        restored_estimator.predict(X_test)
+    with open(dump_file, 'rb') as f:
+        restored_estimator = pickle.load(f)
+    restored_estimator.predict(X_test)
 
     # Test refit on dummy data
     estimator.refit(dataset=backend.load_datamanager())
@@ -264,17 +253,11 @@ def test_tabular_regression(openml_name, resampling_strategy, backend, resamplin
     X_train, X_test, y_train, y_test = sklearn.model_selection.train_test_split(
         X, y, random_state=1)
 
-    include = None
-    # for python less than 3.7, learned entity embedding
-    # is not able to be stored on disk (only on CI)
-    if sys.version_info < (3, 7):
-        include = {'network_embedding': ['NoEmbedding']}
     # Search for a good configuration
     estimator = TabularRegressionTask(
         backend=backend,
         resampling_strategy=resampling_strategy,
         resampling_strategy_args=resampling_strategy_args,
-        include_components=include,
         seed=42,
     )
 
@@ -403,30 +386,26 @@ def test_tabular_regression(openml_name, resampling_strategy, backend, resamplin
     assert 'train_loss' in incumbent_results, estimator.run_history.data
 
     # Check that we can pickle
-    # Test pickle
-    # This can happen on python greater than 3.6
-    # as older python do not control the state of the logger
-    if sys.version_info >= (3, 7):
-        dump_file = os.path.join(estimator._backend.temporary_directory, 'dump.pkl')
+    dump_file = os.path.join(estimator._backend.temporary_directory, 'dump.pkl')
 
-        with open(dump_file, 'wb') as f:
-            pickle.dump(estimator, f)
+    with open(dump_file, 'wb') as f:
+        pickle.dump(estimator, f)
 
-        with open(dump_file, 'rb') as f:
-            restored_estimator = pickle.load(f)
-        restored_estimator.predict(X_test)
+    with open(dump_file, 'rb') as f:
+        restored_estimator = pickle.load(f)
+    restored_estimator.predict(X_test)
 
-        # Test refit on dummy data
-        estimator.refit(dataset=backend.load_datamanager())
+    # Test refit on dummy data
+    estimator.refit(dataset=backend.load_datamanager())
 
-        # Make sure that a configuration space is stored in the estimator
-        assert isinstance(estimator.get_search_space(), CS.ConfigurationSpace)
+    # Make sure that a configuration space is stored in the estimator
+    assert isinstance(estimator.get_search_space(), CS.ConfigurationSpace)
 
-        representation = estimator.show_models()
-        assert isinstance(representation, str)
-        assert 'Weight' in representation
-        assert 'Preprocessing' in representation
-        assert 'Estimator' in representation
+    representation = estimator.show_models()
+    assert isinstance(representation, str)
+    assert 'Weight' in representation
+    assert 'Preprocessing' in representation
+    assert 'Estimator' in representation
 
 
 @pytest.mark.parametrize('openml_id', (
@@ -536,16 +515,10 @@ def test_portfolio_selection(openml_id, backend, n_samples):
     X_train, X_test, y_train, y_test = sklearn.model_selection.train_test_split(
         X, y, random_state=1)
 
-    include = None
-    # for python less than 3.7, learned entity embedding
-    # is not able to be stored on disk (only on CI)
-    if sys.version_info < (3, 7):
-        include = {'network_embedding': ['NoEmbedding']}
     # Search for a good configuration
     estimator = TabularClassificationTask(
         backend=backend,
         resampling_strategy=HoldoutValTypes.holdout_validation,
-        include_components=include
     )
 
     with unittest.mock.patch.object(estimator, '_do_dummy_prediction', new=dummy_do_dummy_prediction):
@@ -584,16 +557,9 @@ def test_portfolio_selection_failure(openml_id, backend, n_samples):
     X_train, X_test, y_train, y_test = sklearn.model_selection.train_test_split(
         X, y, random_state=1)
 
-    include = None
-    # for python less than 3.7, learned entity embedding
-    # is not able to be stored on disk (only on CI)
-    if sys.version_info < (3, 7):
-        include = {'network_embedding': ['NoEmbedding']}
-        # Search for a good configuration
     estimator = TabularClassificationTask(
         backend=backend,
         resampling_strategy=HoldoutValTypes.holdout_validation,
-        include_components=include
     )
     with pytest.raises(FileNotFoundError, match=r"The path: .+? provided for 'portfolio_selection' "
                                                 r"for the file containing the portfolio configurations "

test/test_ensemble/test_ensemble.py

@@ -690,8 +690,6 @@ def test_ensemble_builder_process_realrun(dask_client, ensemble_backend):
 
 @flaky(max_runs=3)
 @unittest.mock.patch('autoPyTorch.ensemble.ensemble_builder.EnsembleBuilder.fit_ensemble')
-@pytest.mark.skipif(sys.version_info >= (3, 7),
-                    reason="Causes out-of-memory Errors in CI")
 def test_ensemble_builder_nbest_remembered(fit_ensemble, ensemble_backend, dask_client):
     """
     Makes sure ensemble builder returns the size of the ensemble that pynisher allowed

test/test_evaluation/test_evaluation.py

@@ -356,7 +356,6 @@ def test_exception_in_target_function(self, eval_holdout_mock):
         self.assertIn('traceback', info[1].additional_info)
         self.assertNotIn('exitcode', info[1].additional_info)
 
-    @unittest.skipIf(sys.version_info < (3, 7), reason="requires python3.7 or higher")
     def test_silent_exception_in_target_function(self):
         config = unittest.mock.Mock(spec=int)
         config.config_id = 198

test/test_pipeline/components/setup/test_setup_traditional_models.py

@@ -126,12 +126,11 @@ def test_model_fit_predict_score(traditional_learner, fit_dictionary_tabular):
                         fit_dictionary_tabular['y_train'][fit_dictionary_tabular['val_indices']])
     assert np.allclose(score, model.fit_output['val_score'], atol=1e-6)
 
-    if sys.version_info >= (3, 7):
-        dump_file = os.path.join(fit_dictionary_tabular['backend'].temporary_directory, 'dump.pkl')
+    dump_file = os.path.join(fit_dictionary_tabular['backend'].temporary_directory, 'dump.pkl')
 
-        with open(dump_file, 'wb') as f:
-            pickle.dump(model, f)
+    with open(dump_file, 'wb') as f:
+        pickle.dump(model, f)
 
-        with open(dump_file, 'rb') as f:
-            restored_estimator = pickle.load(f)
-        restored_estimator.predict(fit_dictionary_tabular['X_train'])
+    with open(dump_file, 'rb') as f:
+        restored_estimator = pickle.load(f)
+    restored_estimator.predict(fit_dictionary_tabular['X_train'])