Reformat (#86)

darwin/cli_functions.py

@@ -60,10 +60,7 @@ def authenticate(api_key: str, default_team: Optional[bool] = None, datasets_dir
         config_path.parent.mkdir(exist_ok=True)
 
         if default_team is None:
-            default_team = input(f"Make {client.default_team} the default team? [y/N] ") in [
-                "Y",
-                "y",
-            ]
+            default_team = input(f"Make {client.default_team} the default team? [y/N] ") in ["Y", "y"]
         if datasets_dir is None:
             datasets_dir = prompt("Datasets directory", "~/.darwin/datasets")
 

darwin/client.py

@@ -8,14 +8,8 @@
 from darwin.config import Config
 from darwin.dataset import RemoteDataset
 from darwin.dataset.identifier import DatasetIdentifier
-from darwin.exceptions import (
-    InsufficientStorage,
-    InvalidLogin,
-    MissingConfig,
-    NotFound,
-    Unauthorized,
-)
-from darwin.utils import is_project_dir, urljoin, is_deprecated_project_dir
+from darwin.exceptions import InsufficientStorage, InvalidLogin, MissingConfig, NotFound, Unauthorized
+from darwin.utils import is_deprecated_project_dir, is_project_dir, urljoin
 from darwin.validators import name_taken, validation_error
 
 
@@ -76,9 +70,7 @@ def get(
         else:
             return self._decode_response(response, debug)
 
-    def put(
-        self, endpoint: str, payload: Dict, team: Optional[str] = None, retry: bool = False, debug: bool = False
-    ):
+    def put(self, endpoint: str, payload: Dict, team: Optional[str] = None, retry: bool = False, debug: bool = False):
         """Put something on the server trough HTTP
 
         Parameters
@@ -437,11 +429,7 @@ def _decode_response(response, debug: bool = False):
             if debug:
                 print(f"[ERROR {response.status_code}] {response.text}")
             response.close()
-            return {
-                "error": "Response is not JSON encoded",
-                "status_code": response.status_code,
-                "text": response.text,
-            }
+            return {"error": "Response is not JSON encoded", "status_code": response.status_code, "text": response.text}
 
     def __str__(self):
         return f"Client(default_team={self.default_team})"

darwin/dataset/local_dataset.py

@@ -57,7 +57,7 @@ def __init__(
 
         # Get the list of classes
         self.classes = get_classes(
-            self.dataset_path, release_name, annotation_type=self.annotation_type, remove_background=True,
+            self.dataset_path, release_name, annotation_type=self.annotation_type, remove_background=True
         )
 
         # Get the list of stems

darwin/dataset/remote_dataset.py

@@ -414,9 +414,7 @@ def split(
             make_default_split=make_default_split,
         )
 
-    def classes(
-        self, annotation_type: str, release_name: Optional[str] = None
-    ):
+    def classes(self, annotation_type: str, release_name: Optional[str] = None):
         """
         Returns the list of `class_type` classes
 

darwin/dataset/upload_manager.py

@@ -333,7 +333,7 @@ def upload_annotations(
                             client=client,
                             team=team,
                             annotation_type_ids=["3"],  # TODO maybe in the future allow to use polygons and BB as well
-                            cropped_image={"image_id": image_dataset_id, "scale": 0.01, "x": "0", "y": "0",},
+                            cropped_image={"image_id": image_dataset_id, "scale": 0.01, "x": "0", "y": "0"},
                             dataset_id=dataset_id,
                             description="",
                             expected_occurrences=[0, 1],
@@ -387,7 +387,7 @@ def upload_annotations(
 
 
 def _upload_annotation(
-    class_mapping: Dict, client: "Client", team: str, data: Dict, image_dataset_id: int, output_file_path: Path,
+    class_mapping: Dict, client: "Client", team: str, data: Dict, image_dataset_id: int, output_file_path: Path
 ):
     """
 

darwin/dataset/utils.py

@@ -291,11 +291,7 @@ def _stratify_samples(idx_to_classes, split_seed, test_percentage, val_percentag
     # Remove duplicates within the same set
     # NOTE: doing that earlier (e.g. in remove_cross_contamination()) would produce mathematical
     # mistakes in the class balancing between validation and test sets.
-    return (
-        list(set(X_train.astype(np.int))),
-        list(set(X_val.astype(np.int))),
-        list(set(X_test.astype(np.int))),
-    )
+    return (list(set(X_train.astype(np.int))), list(set(X_val.astype(np.int))), list(set(X_test.astype(np.int))))
 
 
 def split_dataset(
@@ -365,10 +361,7 @@ def split_dataset(
 
     # Prepare the return value with the paths of the splits
     splits = {}
-    splits["random"] = {
-        "train": Path(split_path / "random_train.txt"),
-        "val": Path(split_path / "random_val.txt"),
-    }
+    splits["random"] = {"train": Path(split_path / "random_train.txt"), "val": Path(split_path / "random_val.txt")}
     splits["stratified_tag"] = {
         "train": Path(split_path / "stratified_tag_train.txt"),
         "val": Path(split_path / "stratified_tag_val.txt"),
@@ -394,15 +387,15 @@ def split_dataset(
         # RANDOM SPLIT
         # Compute split sizes
         dataset_size = sum(1 for _ in annotation_files)
-        val_size = int(dataset_size * (val_percentage / 100.))
-        test_size = int(dataset_size * (test_percentage / 100.))
+        val_size = int(dataset_size * (val_percentage / 100.0))
+        test_size = int(dataset_size * (test_percentage / 100.0))
         train_size = dataset_size - val_size - test_size
         # Slice a permuted array as big as the dataset
         np.random.seed(split_seed)
         indices = np.random.permutation(dataset_size)
         train_indices = list(indices[:train_size])
-        val_indices = list(indices[train_size: train_size + val_size])
-        test_indices = list(indices[train_size + val_size:])
+        val_indices = list(indices[train_size : train_size + val_size])
+        test_indices = list(indices[train_size + val_size :])
         # Write files
         _write_to_file(annotation_files, splits["random"]["train"], train_indices)
         _write_to_file(annotation_files, splits["random"]["val"], val_indices)
@@ -539,11 +532,7 @@ def get_coco_format_record(
             category = classes.index(obj["name"])
         else:
             category = obj["name"]
-        new_obj = {
-            "bbox_mode": box_mode,
-            "category_id": category,
-            "iscrowd": 0,
-        }
+        new_obj = {"bbox_mode": box_mode, "category_id": category, "iscrowd": 0}
 
         if annotation_type == "polygon":
             for point in obj["polygon"]["path"]:

darwin/exporter/exporter.py

@@ -34,7 +34,7 @@ def _parse_darwin_annotation(annotation):
     elif "bounding_box" in annotation:
         bounding_box = annotation["bounding_box"]
         main_annotation = dt.make_bounding_box(
-            name, bounding_box["x"], bounding_box["y"], bounding_box["w"], bounding_box["h"],
+            name, bounding_box["x"], bounding_box["y"], bounding_box["w"], bounding_box["h"]
         )
     elif "tag" in annotation:
         main_annotation = dt.make_tag(name)

darwin/exporter/formats/cvat.py

@@ -1,5 +1,5 @@
-import xml.etree.ElementTree as ET
 import datetime
+import xml.etree.ElementTree as ET
 from pathlib import Path
 from typing import Generator
 

darwin/importer/importer.py

@@ -104,7 +104,7 @@ def _import_annotations(client: "Client", id: int, remote_classes, annotations,
         annotation_class = annotation.annotation_class
         annotation_class_id = remote_classes[annotation_class.annotation_type][annotation_class.name]
         serialized_annotations.append(
-            {"annotation_class_id": annotation_class_id, "data": {annotation_class.annotation_type: annotation.data},}
+            {"annotation_class_id": annotation_class_id, "data": {annotation_class.annotation_type: annotation.data}}
         )
 
     if client.feature_enabled("WORKFLOW", dataset.team):

darwin/options.py

@@ -21,7 +21,7 @@ def __init__(self):
         parser_create = subparsers.add_parser("team", help="List or pick teams. ")
         parser_create.add_argument("team_name", nargs="?", type=str, help="Team name to use. ")
         parser_create.add_argument(
-            "-c", "--current", action="store_true", required=False, help="Shows only the current team. ",
+            "-c", "--current", action="store_true", required=False, help="Shows only the current team. "
         )
 
         parser_convert = subparsers.add_parser("convert", help="Converts darwin json to other annotation formats.")
@@ -33,7 +33,7 @@ def __init__(self):
 
         # DATASET
         dataset = subparsers.add_parser(
-            "dataset", help="Dataset related functions", description="Arguments to interact with datasets",
+            "dataset", help="Dataset related functions", description="Arguments to interact with datasets"
         )
         dataset_action = dataset.add_subparsers(dest="action")
 
@@ -76,7 +76,7 @@ def __init__(self):
             help="Excludes the files with the specified extension/s if a data folder is provided as data path. ",
         )
         parser_push.add_argument(
-            "-f", "--fps", type=int, default="1", help="Frames per second for video split (recommended: 1).",
+            "-f", "--fps", type=int, default="1", help="Frames per second for video split (recommended: 1)."
         )
 
         # Remove
@@ -87,7 +87,7 @@ def __init__(self):
         parser_report = dataset_action.add_parser("report", help="Report about the annotators ")
         parser_report.add_argument("dataset", type=str, help="Remote dataset name to report on.")
         parser_report.add_argument(
-            "-g", "--granularity", choices=["day", "week", "month", "total"], help="Granularity of the report",
+            "-g", "--granularity", choices=["day", "week", "month", "total"], help="Granularity of the report"
         )
 
         # Export
@@ -137,7 +137,7 @@ def __init__(self):
         parser_split.add_argument("dataset", type=str, help="Local dataset name to split.")
         parser_split.add_argument("-v", "--val-percentage", type=float, required=True, help="Validation percentage.")
         parser_split.add_argument(
-            "-t", "--test-percentage", type=float, required=False, default=0, help="Test percentage.",
+            "-t", "--test-percentage", type=float, required=False, default=0, help="Test percentage."
         )
         parser_split.add_argument("-s", "--seed", type=int, required=False, default=0, help="Split seed.")
 

darwin/torch/dataset.py

@@ -150,9 +150,7 @@ def _return_std(image_path, mean):
 
 
 class ClassificationDataset(DarwinDataset):
-    def __init__(
-        self, transform: Optional[List] = None, **kwargs,
-    ):
+    def __init__(self, transform: Optional[List] = None, **kwargs):
         """See class `LocalDataset` for documentation"""
         super().__init__(annotation_type="tag", **kwargs)
 
@@ -212,9 +210,7 @@ def measure_weights(self, **kwargs) -> np.ndarray:
 
 
 class InstanceSegmentationDataset(DarwinDataset):
-    def __init__(
-        self, transform: Optional[List] = None, convert_polygons_to_masks: Optional[bool] = True, **kwargs,
-    ):
+    def __init__(self, transform: Optional[List] = None, convert_polygons_to_masks: Optional[bool] = True, **kwargs):
         """See `LocalDataset` class for documentation"""
         super().__init__(annotation_type="polygon", **kwargs)
 
@@ -309,9 +305,7 @@ def measure_weights(self, **kwargs):
 
 
 class SemanticSegmentationDataset(DarwinDataset):
-    def __init__(
-        self, transform: Optional[List] = None, convert_polygons_to_masks: Optional[bool] = True, **kwargs,
-    ):
+    def __init__(self, transform: Optional[List] = None, convert_polygons_to_masks: Optional[bool] = True, **kwargs):
         """See `LocalDataset` class for documentation"""
         super().__init__(annotation_type="polygon", **kwargs)
 
@@ -346,9 +340,7 @@ def __getitem__(self, index: int):
             sequences[:] = [s for s in sequences if len(s) >= 6]
             if not sequences:
                 continue
-            annotations.append(
-                {"category_id": self.classes.index(obj["name"]), "segmentation": np.array(sequences),}
-            )
+            annotations.append({"category_id": self.classes.index(obj["name"]), "segmentation": np.array(sequences)})
         target["annotations"] = annotations
 
         if self.convert_polygons is not None:

darwin/utils.py

@@ -87,7 +87,7 @@ def prompt(msg: str, default: Optional[str] = None) -> str:
 
 
 def find_files(
-    files: List[Union[str, Path]] = [], recursive: bool = True, files_to_exclude: List[Union[str, Path]] = [],
+    files: List[Union[str, Path]] = [], recursive: bool = True, files_to_exclude: List[Union[str, Path]] = []
 ) -> List[Path]:
     """Retrieve a list of all files belonging to supported extensions. The exploration can be made
     recursive and a list of files can be excluded if desired.
@@ -150,9 +150,7 @@ def persist_client_configuration(
 
     team_config = client.config.get_default_team()
     config = Config(config_path)
-    config.set_team(
-        team=team_config["slug"], api_key=team_config["api_key"], datasets_dir=team_config["datasets_dir"],
-    )
+    config.set_team(team=team_config["slug"], api_key=team_config["api_key"], datasets_dir=team_config["datasets_dir"])
     config.set_global(api_endpoint=client.url, base_url=client.base_url, default_team=default_team)
 
     return config

darwin_demo.py

@@ -63,14 +63,12 @@ def run_demo(
         formatter_class=argparse.ArgumentDefaultsHelpFormatter,
         description="This script can be used to download a dataset from Darwin",
     )
-    parser.add_argument(
-        "--datasets-dir", help="Path to where the dataset will be downloaded", default=None, type=Path,
-    )
+    parser.add_argument("--datasets-dir", help="Path to where the dataset will be downloaded", default=None, type=Path)
     parser.add_argument("--dataset-slug", help="Dataset slug (see Darwin documentation)", default=None, type=str)
     parser.add_argument("--team-slug", help="Team slug (see Darwin documentation)", default=None, type=str)
     parser.add_argument("--api-key", help="API key to authenticate the client", default=None, type=str)
     parser.add_argument(
-        "--config-path", help="Path to the configuration file to authenticate the client", default=None, type=Path,
+        "--config-path", help="Path to the configuration file to authenticate the client", default=None, type=Path
     )
     args = parser.parse_args()
 

setup.py

@@ -27,6 +27,6 @@
     ],
     packages=setuptools.find_packages(),
     entry_points={"console_scripts": ["darwin=darwin.cli:main"]},
-    classifiers=["Programming Language :: Python :: 3", "License :: OSI Approved :: MIT License",],
+    classifiers=["Programming Language :: Python :: 3", "License :: OSI Approved :: MIT License"],
     python_requires=">=3.6",
 )