STYLE: Trim trailing whitespaces with pre-commit (#715)

.github/workflows/linting_and_hello_world.yml

@@ -21,7 +21,7 @@ jobs:
  pip install flake8
  python -m flake8
  shell: bash
- if: always() 
+ if: always()
 
  # This script also does "conda init" for all shells. For bash, this modifies .bashrc.
  # However, the default "bash" in a github workflow does not execute bashrc. Hence, all

.pre-commit-config.yaml

@@ -2,28 +2,29 @@
 # See https://pre-commit.com/hooks.html for more hooks
 # See https://github.com/pre-commit/pre-commit-hooks/blob/master/.pre-commit-config.yaml for an example with more hooks
 
-exclude: '^excluded_files_regex$'
 repos:
-- repo: https://github.com/pre-commit/pre-commit-hooks
- rev: v4.0.1
- hooks:
- - id: trailing-whitespace
- - id: end-of-file-fixer
- - id: check-yaml
- - id: check-added-large-files
- - id: check-ast
- - id: check-merge-conflict
- - id: debug-statements
- - id: mixed-line-ending
- args: [--fix=lf]
+- repo: https://github.com/pre-commit/pre-commit-hooks
+ rev: v4.0.1
+ hooks:
+ - id: trailing-whitespace
+ - id: end-of-file-fixer
+ - id: check-yaml
+ - id: check-added-large-files
+ - id: check-ast
+ - id: check-merge-conflict
+ - id: debug-statements
+ - id: mixed-line-ending
+ args:
+ - --fix=lf
 
-- repo: https://github.com/PyCQA/flake8
- rev: 3.9.2
- hooks:
- - id: flake8
- additional_dependencies: [flake8-typing-imports==1.7.0]
+- repo: https://github.com/PyCQA/flake8
+ rev: 3.9.2
+ hooks:
+ - id: flake8
+ additional_dependencies:
+ - flake8-typing-imports==1.7.0
 
--  repo: https://github.com/pre-commit/mirrors-autopep8
-  rev: v1.5.7
-  hooks:
-  - id: autopep8
+- repo: https://github.com/pre-commit/mirrors-autopep8
+ rev: v1.5.7
+ hooks:
+ - id: autopep8

.vscode/settings.json

@@ -4,5 +4,6 @@
  "Tests"
  ],
  "python.testing.unittestEnabled": false,
- "python.testing.pytestEnabled": true
-}
+ "python.testing.pytestEnabled": true,
+ "files.trimTrailingWhitespace": true
+}

InnerEye/ML/SSL/utils.py

@@ -39,7 +39,7 @@ def create_ssl_encoder(encoder_name: str, use_7x7_first_conv_in_resnet: bool = T
  """
  Creates SSL encoder.
  :param encoder_name: available choices: resnet18, resnet50, resnet101 and densenet121.
- :param use_7x7_first_conv_in_resnet: If True, use a 7x7 kernel (default) in the first layer of resnet. 
+ :param use_7x7_first_conv_in_resnet: If True, use a 7x7 kernel (default) in the first layer of resnet.
  If False, replace first layer by a 3x3 kernel. This is required for small CIFAR 32x32 images to not shrink them.
  """
  from pl_bolts.models.self_supervised.resnets import resnet18, resnet50, resnet101

InnerEye/ML/configs/classification/DummyClassification.py

@@ -12,7 +12,7 @@
 
 
 class DummyClassification(ScalarModelBase):
- "A config file for dummy image classification model for debugging purposes" 
+ "A config file for dummy image classification model for debugging purposes"
 
  def __init__(self) -> None:
  num_epochs = 4

InnerEye/ML/configs/other/HelloContainer.py

@@ -39,7 +39,7 @@ def __init__(self, raw_data: List[List[float]]) -> None:
  must be numeric data which can be converted into a tensor. See the static method
  from_path_and_indexes for an example call.
  """
- super().__init__() 
+ super().__init__()
  self.data = torch.tensor(raw_data, dtype=torch.float)
 
  def __len__(self) -> int:
@@ -253,9 +253,9 @@ def create_model(self) -> LightningModule:
  return HelloRegression()
 
  # This method must be overridden by any subclass of LightningContainer. It returns a data module, which
- # in turn contains 3 data loaders for training, validation, and test set. 
- # 
- # If the container is used for cross validation then this method must handle the cross validation splits. 
+ # in turn contains 3 data loaders for training, validation, and test set.
+ #
+ # If the container is used for cross validation then this method must handle the cross validation splits.
  # Because this deals with data loaders, not loaded data, we cannot check automatically that cross validation is
  # handled correctly within the LightningContainer base class, i.e. if you forget to do the cross validation split
  # in your subclass nothing will fail, but each child run will be identical since they will each be given the full

InnerEye/ML/configs/segmentation/HelloWorld.py

@@ -28,7 +28,7 @@ class HelloWorld(SegmentationModelBase):
 
  * This model can be trained from the commandline: python InnerEye/runner.py --model=HelloWorld
 
- * If you want to test that your AzureML workspace is working, please follow the instructions in 
+ * If you want to test that your AzureML workspace is working, please follow the instructions in
  <repo_root>/docs/hello_world_model.md.
 
  In this example, the model is trained on 2 input image channels channel1 and channel2, and

InnerEye/ML/dataset/scalar_dataset.py

@@ -498,7 +498,7 @@ def _load_single_data_source(_rows: pd.DataFrame,
  is_classification_dataset=self.is_classification_dataset,
  num_classes=self.num_classes,
  sequence_position_numeric=_sequence_position_numeric
- ) 
+ )
  if len(self.expected_channels) > 0:
  missing_channels = self.expected_channels - set(rows[self.channel_column])
  if len(missing_channels) > 0:

InnerEye/ML/lightning_container.py

@@ -295,7 +295,7 @@ def get_cross_validation_hyperdrive_config(self, run_config: ScriptRunConfig) ->
  """
  Returns a configuration for AzureML Hyperdrive that varies the cross validation split index.
  Because this adds a val/Loss metric it is important that when subclassing LightningContainer
- your implementeation of LightningModule logs val/Loss. There is an example of this in 
+ your implementation of LightningModule logs val/Loss. There is an example of this in
  HelloRegression's validation_step method.
  :param run_config: The AzureML run configuration object that training for an individual model.
  :return: A hyperdrive configuration object.

SECURITY.md

@@ -14,7 +14,7 @@ Instead, please report them to the Microsoft Security Response Center (MSRC) at
 
 If you prefer to submit without logging in, send email to [[email protected]](mailto:[email protected]). If possible, encrypt your message with our PGP key; please download it from the [Microsoft Security Response Center PGP Key page](https://www.microsoft.com/en-us/msrc/pgp-key-msrc).
 
-You should receive a response within 24 hours. If for some reason you do not, please follow up via email to ensure we received your original message. Additional information can be found at [microsoft.com/msrc](https://www.microsoft.com/msrc). 
+You should receive a response within 24 hours. If for some reason you do not, please follow up via email to ensure we received your original message. Additional information can be found at [microsoft.com/msrc](https://www.microsoft.com/msrc).
 
 Please include the requested information listed below (as much as you can provide) to help us better understand the nature and scope of the possible issue:
 

Tests/ML/models/test_parallel.py

@@ -19,7 +19,7 @@
 
 class SimpleModel(BaseSegmentationModel):
  """
- A simple neural network model to test model parallelisation functions. 
+ A simple neural network model to test model parallelisation functions.
  """
 
  def __init__(self, input_channels: Any, channels: Any, n_classes: int, kernel_size: int):

Tests/ML/models/test_scalar_model.py

@@ -105,10 +105,10 @@ def test_train_classification_model(class_name: str, test_output_dirs: OutputFol
  f"{LoggingColumns.OptimalThreshold.value}," \
  f"{LoggingColumns.SubjectCount.value},{LoggingColumns.Epoch.value}," \
  f"{LoggingColumns.CrossValidationSplitIndex.value}\n" + \
- """0.6866141557693481,0.6866141557693481,0.5,0.0001,1.0,1.0,0.5,0.0,0.0,0.529514,2.0,0,-1 
- 0.6864652633666992,0.6864652633666992,0.5,9.999712322065557e-05,1.0,1.0,0.5,0.0,0.0,0.529475,2.0,1,-1 
- 0.6863163113594055,0.6863162517547607,0.5,9.999306876841536e-05,1.0,1.0,0.5,0.0,0.0,0.529437,2.0,2,-1 
- 0.6861673593521118,0.6861673593521118,0.5,9.998613801725043e-05,1.0,1.0,0.5,0.0,0.0,0.529399,2.0,3,-1 
+ """0.6866141557693481,0.6866141557693481,0.5,0.0001,1.0,1.0,0.5,0.0,0.0,0.529514,2.0,0,-1
+ 0.6864652633666992,0.6864652633666992,0.5,9.999712322065557e-05,1.0,1.0,0.5,0.0,0.0,0.529475,2.0,1,-1
+ 0.6863163113594055,0.6863162517547607,0.5,9.999306876841536e-05,1.0,1.0,0.5,0.0,0.0,0.529437,2.0,2,-1
+ 0.6861673593521118,0.6861673593521118,0.5,9.998613801725043e-05,1.0,1.0,0.5,0.0,0.0,0.529399,2.0,3,-1
  """
  check_log_file(epoch_metrics_path, expected_epoch_metrics, ignore_columns=[])
  # Check metrics.csv: This contains the per-subject per-epoch model outputs

Tests/ML/reports/test_segmentation_report.py

@@ -59,8 +59,8 @@ def _test_generate_segmentation_report_with_partial_ground_truth(
  partial_metrics.to_csv(partial_metrics_file, index=False, float_format="%.3f", na_rep="")
  result_html = generate_segmentation_notebook(result_notebook=result_file, test_metrics=partial_metrics_file)
  result_html_text = result_html.read_text(encoding='utf-8')
- # Look for this row in the HTML Dice table: 
- # <td>brainstem</td>\n <td>0.82600</td>\n <td>0.8570</td>\n <td>0.87600</td>\n <td>17.0</td>\n 
+ # Look for this row in the HTML Dice table:
+ # <td>brainstem</td>\n <td>0.82600</td>\n <td>0.8570</td>\n <td>0.87600</td>\n <td>17.0</td>\n
  # It shows that for the brainstem label there are only 17, not 20, patients with that label,
  # because we removed the brainstem label for patients 14, 15, and 19.
 

Tests/ML/test_data/Val_outliers.txt

@@ -3,7 +3,7 @@
 === METRIC: Dice ===
 
  count mean min max
-Patient Structure seriesId institutionId 
+Patient Structure seriesId institutionId
 341 rectum d41cb61517793f87f97d5d6c0cee9f91df94169c29701c10190723ff8ede419a 641eda02-90c3-45ed-b8b1-2651b6a5da6c 1.0 1.1 1.1 1.1
 366 rectum f040ac05a1eeee9a064662adda21f703d7ba969b7dfc2787248b2c596ccf59a7 641eda02-90c3-45ed-b8b1-2651b6a5da6c 1.0 0.9 0.9 0.9
 411 rectum 6fa04f324339c532a7c06877d1129bfacd7504d9c0bf6277a393915e73e41d66 5a6ba8fe-65bc-43ec-b1fc-682c8c37e40c 1.0 0.9 0.9 0.9

Tests/ML/test_data/Val_outliers_pruned.txt

@@ -3,7 +3,7 @@
 === METRIC: Dice ===
 
  count mean min max
-Patient Structure 
+Patient Structure
 341 rectum 1.0 1.1 1.1 1.1
 366 rectum 1.0 0.9 0.9 0.9
 411 rectum 1.0 0.9 0.9 0.9

Tests/ML/test_lightning_containers.py

@@ -308,7 +308,7 @@ def test_get_hyperdrive_config(number_of_cross_validation_splits: int,
  with pytest.raises(NotImplementedError) as not_implemented_error:
  container.get_hyperdrive_config(run_config=run_config)
  assert 'Parameter search is not implemented' in str(not_implemented_error.value)
- # The error should be thrown by 
+ # The error should be thrown by
  # InnerEye.ML.lightning_container.LightningContainer.get_parameter_search_hyperdrive_config
  # since number_of_cross_validation_splits == 0 implies a parameter search hyperdrive config and
  # not a cross validation one.

Tests/SSL/test_ssl_containers.py

@@ -287,7 +287,7 @@ def test_simclr_lr_scheduler() -> None:
 
 @pytest.mark.gpu
 def test_simclr_training_recovery(test_output_dirs: OutputFolderForTests) -> None:
- """ This test checks if a SSLContainer correctly resumes training. 
+ """ This test checks if a SSLContainer correctly resumes training.
  First we run SSL using a Trainer for 20 epochs.
  Second, we run a new SSL job for 15 epochs.
  Third we resume the job and run it for 5 more epochs.
@@ -332,7 +332,7 @@ def run_simclr_dummy_container(test_output_dirs: OutputFolderForTests,
 
  small_encoder = torch.nn.Sequential(torch.nn.Flatten(), torch.nn.Linear(3, 2))
  with mock.patch("InnerEye.ML.SSL.encoders.create_ssl_encoder", return_value=small_encoder):
- with mock.patch("InnerEye.ML.SSL.encoders.get_encoder_output_dim", return_value=2): 
+ with mock.patch("InnerEye.ML.SSL.encoders.get_encoder_output_dim", return_value=2):
  # Normal run
  normal_lrs, normal_loss, _ = run_simclr_dummy_container(test_output_dirs, 20, last_checkpoint=None)
 

docs/WSL.md

@@ -48,8 +48,8 @@ winget install Microsoft.WindowsTerminal
 Remember to restart your machine if you were doing a fresh installation of WSL 2 before trying further steps.
 
 Since it is possible to choose the version of WSL that a particular distribution is running, once you have WSL2
-installed, ensure that your distribution is running on top of WSL2 by executing 
-`wsl --list --verbose` 
+installed, ensure that your distribution is running on top of WSL2 by executing
+`wsl --list --verbose`
 If all is good, the output should look like this:
 
 ```