📝 Fix whitespace errors on :return statements

InnerEye/Azure/azure_runner.py

@@ -107,7 +107,7 @@ def create_dataset_configs(azure_config: AzureConfig,
     :param all_dataset_mountpoints: When using the datasets in AzureML, these are the per-dataset mount points.
     :param all_local_datasets: The paths for all local versions of the datasets.
     :return: A list of DatasetConfig objects, in the same order as datasets were provided in all_azure_dataset_ids,
-    omitting datasets with an empty name.
+        omitting datasets with an empty name.
     """
     datasets: List[DatasetConfig] = []
     num_local = len(all_local_datasets)

InnerEye/Azure/run_pytest.py

@@ -23,7 +23,7 @@ def run_pytest(pytest_mark: str, outputs_folder: Path) -> Tuple[bool, Path]:
     :param pytest_mark: The PyTest mark to use for filtering out the tests to run.
     :param outputs_folder: The folder into which the test result XML file should be written.
     :return: True if PyTest found tests to execute and completed successfully, False otherwise.
-    Also returns the path to the generated PyTest results file.
+        Also returns the path to the generated PyTest results file.
     """
     from _pytest.main import ExitCode
     _outputs_file = outputs_folder / PYTEST_RESULTS_FILE

InnerEye/Azure/secrets_handling.py

@@ -107,7 +107,7 @@ def read_all_settings(project_settings_file: Optional[Path] = None,
     :param project_settings_file: The first YAML settings file to read.
     :param project_root: The folder that can contain a 'InnerEyePrivateSettings.yml' file.
     :return: A dictionary mapping from string to variable value. The dictionary key is the union of variable names
-    found in the two settings files.
+        found in the two settings files.
     """
     private_settings_file = None
     if project_root and project_root.is_dir():
@@ -126,7 +126,7 @@ def read_settings_and_merge(project_settings_file: Optional[Path] = None,
     :param project_settings_file: The first YAML settings file to read.
     :param private_settings_file: The second YAML settings file to read. Settings in this file has higher priority.
     :return: A dictionary mapping from string to variable value. The dictionary key is the union of variable names
-    found in the two settings files.
+        found in the two settings files.
     """
     result = dict()
     if project_settings_file:

InnerEye/Common/Statistics/mann_whitney_test.py

@@ -187,7 +187,7 @@ def roc_value(lst1: List[float], lst2: List[float]) -> float:
     :param lst1: a list of numbers
     :param lst2: another list of numbers
     :return: the proportion of pairs (x, y), where x is from lst1 and y is from lst2, for which
-    x < y, with x == y counting as half an instance.
+        x < y, with x == y counting as half an instance.
     """
     if len(lst1) == 0 or len(lst2) == 0:
         return 0.5
@@ -273,7 +273,7 @@ def compare_scores_across_institutions(metrics_file: str, splits_to_use: str = "
     :param splits_to_use: a comma-separated list of split names
     :param mode_to_use: test, validation etc
     :return: a list of comparison lines between pairs of splits. If splits_to_use is non empty,
-    only pairs involving at least one split from that set are compared.
+        only pairs involving at least one split from that set are compared.
     """
     valid_splits = set(splits_to_use.split(",")) if splits_to_use else None
     metrics = pd.read_csv(metrics_file)
@@ -330,7 +330,7 @@ def get_arguments(arglist: List[str] = None) -> Tuple[Optional[argparse.Namespac
         The value of the "-a" switch is one or more split names; pairs of splits not including these
         will not be compared.
     :return: parsed arguments and identifier for pattern (1, 2, 3 as above), or None, None if none of the
-    patterns are followed
+        patterns are followed
     """
     # Use argparse because we want to have mandatory non-switch arguments, which GenericConfig doesn't support.
     parser = argparse.ArgumentParser("Run Mann-Whitney tests")

InnerEye/Common/Statistics/report_structure_extremes.py

@@ -175,7 +175,7 @@ def extent_list(presence: np.array, max_value: int) -> Tuple[List[int], List[str
     :param presence: a 1-D array of distinct integers in increasing order.
     :param max_value: any integer, not necessarily related to presence
     :return: two tuples: (1) a list of the minimum and maximum values of presence, and max_value;
-    (2) a list of strings, each denoting a missing range of values within "presence".
+        (2) a list of strings, each denoting a missing range of values within "presence".
     """
     if len(presence) == 0:
         return [-1, -1, max_value], []

InnerEye/Common/Statistics/wilcoxon_signed_rank_test.py

@@ -136,7 +136,7 @@ def difference_counts(values1: List[float], values2: List[float]) -> Tuple[int,
     :param values1: list of values
     :param values2: list of values, same length as values1
     :return: number of pairs in which first value is greater than second, and number of pairs
-    in which second is greater than first
+        in which second is greater than first
     """
     n1 = 0
     n2 = 0

InnerEye/Common/spawn_subprocess.py

@@ -20,7 +20,7 @@ def spawn_and_monitor_subprocess(process: str,
     :param env: The environment variables that the new process will run with. If not provided, copy the
         environment from the current process.
     :return: Return code after the process has finished, and the list of lines that were written to stdout by the
-    subprocess.
+        subprocess.
     """
     if env is None:
         env = dict(os.environ.items())

InnerEye/ML/SSL/lightning_containers/ssl_container.py

@@ -204,9 +204,9 @@ def _create_ssl_data_modules(self, is_ssl_encoder_module: bool) -> InnerEyeVisio
 
         :param is_ssl_encoder_module: whether to return the data module for SSL training or for linear head. If true,
         :return transforms with two views per sample (batch like (img_v1, img_v2, label)). If False, return only one
-        view per sample but also return the index of the sample in the dataset (to make sure we don't use twice the same
-        batch in one training epoch (batch like (index, img_v1, label), as classifier dataloader expected to be shorter
-        than SSL training, hence CombinedDataloader might loop over data several times per epoch).
+            view per sample but also return the index of the sample in the dataset (to make sure we don't use twice the same
+            batch in one training epoch (batch like (index, img_v1, label), as classifier dataloader expected to be shorter
+            than SSL training, hence CombinedDataloader might loop over data several times per epoch).
         """
         datamodule_args = self.datamodule_args[SSLDataModuleType.ENCODER] if is_ssl_encoder_module else \
             self.datamodule_args[SSLDataModuleType.LINEAR_HEAD]

InnerEye/ML/baselines_util.py

@@ -116,8 +116,8 @@ def download_and_compare_scores(outputs_folder: Path, azure_config: AzureConfig,
     :param model_dataset_df: dataframe containing contents of dataset.csv for the current model
     :param model_metrics_df: dataframe containing contents of metrics.csv for the current model
     :return: a dataframe for all the data (current model and all baselines); whether any comparisons were
-    done, i.e. whether a valid baseline was found; and the text lines to be written to the Wilcoxon results
-    file.
+        done, i.e. whether a valid baseline was found; and the text lines to be written to the Wilcoxon results
+        file.
     """
     comparison_baselines = get_comparison_baselines(outputs_folder, azure_config, comparison_blob_storage_paths)
     result = perform_score_comparisons(model_dataset_df, model_metrics_df, comparison_baselines)
@@ -261,7 +261,7 @@ def compare_folder_contents(expected_folder: Path,
     :param csv_relative_tolerance: When comparing CSV files, use this as the maximum allowed relative discrepancy.
         If 0.0, do not allow any discrepancy.
     :return: A list of human readable error messages, with message and file path. If no errors are found, the list is
-    empty.
+        empty.
     """
     messages = []
     if run and is_offline_run_context(run):

InnerEye/ML/configs/other/HelloContainer.py

@@ -61,12 +61,12 @@ def from_path_and_indexes(
         :param start_index: The first row to read.
         :param end_index: The last row to read (exclusive)
         :return: A new instance based on the root folder and the start and end indexes.
-        '''
-        raw_data = np.loadtxt(root_folder / "hellocontainer.csv", delimiter=",")[start_index:end_index]
-        return HelloDataset(raw_data)
-
-
-class HelloDataModule(LightningDataModule):
+            '''
+            raw_data = np.loadtxt(root_folder / "hellocontainer.csv", delimiter=",")[start_index:end_index]
+            return HelloDataset(raw_data)
+    
+    
+    class HelloDataModule(LightningDataModule):
     """
     A data module that gives the training, validation and test data for a simple 1-dim regression task.
     If not using cross validation a basic 50% / 20% / 30% split between train, validation, and test data

InnerEye/ML/dataset/scalar_dataset.py

@@ -746,7 +746,7 @@ def load_item(self, item: ScalarDataSource) -> ScalarItem:
 
         :param item: The item to load.
         :return: A ClassificationItem instances with the loaded images, and the labels and non-image features copied
-        from the argument.
+            from the argument.
         """
         sample = item.load_images(
             root_path=self.args.local_dataset,

InnerEye/ML/dataset/scalar_sample.py

@@ -135,7 +135,7 @@ def load_images(self,
         :param image_size: If given, all loaded images will be reshaped to the size given here, prior to the
             center crop.
         :return: An instance of ClassificationItem, with the same label and numerical_non_image_features fields,
-        and all images loaded.
+            and all images loaded.
         """
         full_channel_files = self.get_all_image_filepaths(root_path=root_path,
                                                           file_mapping=file_mapping)
@@ -160,7 +160,7 @@ def is_valid(self) -> bool:
         be not None, and none of the non imaging features may be NaN or infinity.
 
         :return: True if channel files is a list with not-None entries, and all non imaging features are finite
-        floating point numbers.
+            floating point numbers.
         """
         return self.files_valid() and super().is_valid()
 

InnerEye/ML/deep_learning_config.py

@@ -855,10 +855,10 @@ def load_checkpoint_and_modify(self, path_to_checkpoint: Path) -> Dict[str, Any]
 
         :param path_to_checkpoint: Path to the checkpoint file.
         :return: Dictionary with model and optimizer state dicts. The dict should have at least the following keys:
-        1. Key ModelAndInfo.MODEL_STATE_DICT_KEY and value set to the model state dict.
-        2. Key ModelAndInfo.EPOCH_KEY and value set to the checkpoint epoch.
-        Other (optional) entries corresponding to keys ModelAndInfo.OPTIMIZER_STATE_DICT_KEY and
-        ModelAndInfo.MEAN_TEACHER_STATE_DICT_KEY are also supported.
+            1. Key ModelAndInfo.MODEL_STATE_DICT_KEY and value set to the model state dict.
+            2. Key ModelAndInfo.EPOCH_KEY and value set to the checkpoint epoch.
+            Other (optional) entries corresponding to keys ModelAndInfo.OPTIMIZER_STATE_DICT_KEY and
+            ModelAndInfo.MEAN_TEACHER_STATE_DICT_KEY are also supported.
         """
         return load_checkpoint(path_to_checkpoint=path_to_checkpoint, use_gpu=self.use_gpu)
 

InnerEye/ML/metrics.py

@@ -227,7 +227,7 @@ def compute_dice_across_patches(segmentation: torch.Tensor,
     :param allow_multiple_classes_for_each_pixel: If set to False, ground-truth tensor has
         to contain only one foreground label for each pixel.
     :return A torch tensor of size (Patches, Classes) with the Dice scores. Dice scores are computed for
-    all classes including the background class at index 0.
+        all classes including the background class at index 0.
     """
     check_size_matches(segmentation, ground_truth, 4, 5, [0, -3, -2, -1],
                        arg1_name="segmentation", arg2_name="ground_truth")

InnerEye/ML/model_config_base.py

@@ -119,7 +119,7 @@ def create_data_loaders(self) -> Dict[ModelExecutionMode, Any]:
         """
         Creates the torch DataLoaders that supply the training and the validation set during training only.
         :return: A dictionary, with keys ModelExecutionMode.TRAIN and ModelExecutionMode.VAL, and their respective
-        data loaders.
+            data loaders.
         """
         logging.info("Starting to read and parse the datasets.")
         if self._datasets_for_training is None:
@@ -185,7 +185,7 @@ def get_cross_validation_dataset_splits(self, dataset_split: DatasetSplits) -> D
 
         :param dataset_split: The full dataset, split into training, validation and test section.
         :return: The dataset split with training and validation sections shuffled according to the current
-        cross validation index.
+            cross validation index.
         """
         splits = dataset_split.get_k_fold_cross_validation_splits(self.number_of_cross_validation_splits)
         return splits[self.cross_validation_split_index]

InnerEye/ML/model_training.py

@@ -212,8 +212,8 @@ def model_train(checkpoint_path: Optional[Path],
     :param container: A container object that holds the training data in PyTorch Lightning format
         and the model to train.
     :return: A tuple of [Trainer, StoringLogger]. Trainer is the Lightning Trainer object that was used for fitting
-    the model. The StoringLogger object is returned when training an InnerEye built-in model, this is None when
-    fitting other models.
+        the model. The StoringLogger object is returned when training an InnerEye built-in model, this is None when
+        fitting other models.
     """
     lightning_model = container.model
 

InnerEye/ML/pipelines/ensemble.py

@@ -56,7 +56,7 @@ def aggregate_results(results: Iterable[InferencePipeline.Result],
 
         :param aggregation_type: aggregation function to use to combine the results.
         :return: InferenceResult: contains a Segmentation for each of the classes and their posterior
-        probabilities.
+            probabilities.
         """
         if aggregation_type != EnsembleAggregationType.Average:
             raise NotImplementedError(f"Ensembling is not implemented for aggregation type: {aggregation_type}")
@@ -86,7 +86,7 @@ def predict_whole_image(self, image_channels: np.ndarray,
         :param mask: A binary image used to ignore results outside it in format: Z x Y x X.
         :param patient_id: The identifier of the patient this image belongs to.
         :return InferenceResult: that contains Segmentation for each of the classes and their posterior
-        probabilities.
+            probabilities.
         """
         logging.info(f"Ensembling inference pipelines ({self._get_pipeline_ids()}) "
                      f"predictions for patient: {patient_id}, "

InnerEye/ML/plotting.py

@@ -70,7 +70,7 @@ def plot_val_dice_per_epoch(metrics: Dict[str, Any]) -> int:
 
     :param metrics:
     :return: The number of series that were plotted in the graph. Can return 0 if the metrics dictionary
-    does not contain any validation Dice score.
+        does not contain any validation Dice score.
     """
     plt.clf()
     series_count = 0

InnerEye/ML/reports/classification_report.py

@@ -219,8 +219,8 @@ def plot_scores_and_summary(all_labels_and_model_outputs: Sequence[LabelsAndPred
 
     :param ax: Axes object onto which to plot (default: use current axes).
     :return: A tuple of `(line_handles, summary_handle)` to use in setting a legend for the plot: `line_handles` is a
-    list corresponding to the curves for each `LabelsAndPredictions`, and `summary_handle` references the median line
-    and shaded CI area.
+        list corresponding to the curves for each `LabelsAndPredictions`, and `summary_handle` references the median line
+        and shaded CI area.
     """
     if ax is None:
         ax = plt.gca()

InnerEye/ML/run_ml.py

@@ -530,7 +530,7 @@ def register_model(self,
         :param checkpoint_paths: Checkpoint paths to register.
         :param model_proc: whether it's a single or ensemble model.
         :returns Tuple element 1: AML model object, or None if no model could be registered.
-        Tuple element 2: The result of running the model_deployment_hook, or None if no hook was supplied.
+            Tuple element 2: The result of running the model_deployment_hook, or None if no hook was supplied.
         """
         if self.is_offline_run:
             raise ValueError("Cannot register models when InnerEye is running outside of AzureML.")
@@ -731,7 +731,7 @@ def are_sibling_runs_finished(self) -> bool:
         or cancelled.
 
         :return: True if all sibling runs of the current run have finished (they either completed successfully,
-        or failed). False if any of them is still pending (running or queued).
+            or failed). False if any of them is still pending (running or queued).
         """
         if (not self.is_offline_run) \
                 and (azure_util.is_cross_validation_child_run(RUN_CONTEXT)):

InnerEye/ML/runner.py

@@ -205,7 +205,7 @@ def run(self) -> Tuple[Optional[DeepLearningConfig], AzureRunInfo]:
         The main entry point for training and testing models from the commandline. This chooses a model to train
         via a commandline argument, runs training or testing, and writes all required info to disk and logs.
         :return: If submitting to AzureML, returns the model configuration that was used for training,
-        including commandline overrides applied (if any).
+            including commandline overrides applied (if any).
         """
         # Usually, when we set logging to DEBUG, we want diagnostics about the model
         # build itself, but not the tons of debug information that AzureML submissions create.
@@ -450,7 +450,7 @@ def run(project_root: Path,
     The main entry point for training and testing models from the commandline. This chooses a model to train
     via a commandline argument, runs training or testing, and writes all required info to disk and logs.
     :return: If submitting to AzureML, returns the model configuration that was used for training,
-    including commandline overrides applied (if any). For details on the arguments, see the constructor of Runner.
+        including commandline overrides applied (if any). For details on the arguments, see the constructor of Runner.
     """
     runner = Runner(project_root, yaml_config_file, post_cross_validation_hook, model_deployment_hook)
     return runner.run()

InnerEye/ML/utils/device_aware_module.py

@@ -25,7 +25,7 @@ def __init__(self) -> None:
     def get_devices(self) -> List[torch.device]:
         """
         :return a list of device ids on which this module
-        is deployed.
+            is deployed.
         """
         return list({x.device for x in self.parameters()})
 

InnerEye/ML/utils/features_util.py

@@ -32,7 +32,7 @@ def from_data_sources(sources: List[ScalarDataSource]) -> FeatureStatistics:
 
         :param sources: list of data sources
         :return: a Feature Statistics object storing mean and standard deviation for each non-imaging feature of
-        the dataset.
+            the dataset.
         """
         if len(sources) == 0:
             raise ValueError("sources must have a length greater than 0")

InnerEye/ML/utils/hdf5_util.py

@@ -75,7 +75,7 @@ def parse_acquisition_date(date: str) -> Optional[datetime]:
 
         :param date: string representing a date
         :return: converted date, None if the string is invalid for
-        date conversion.
+            date conversion.
         """
         try:
             return datetime.strptime(date, DATE_FORMAT)