Rename dataset validator classes

Author: lochhh

CONTRIBUTING.md

@@ -190,8 +190,8 @@ raise logger.exception(ValueError("message")) # with traceback
 We aim to adhere to the [When to use logging guide](inv:python#logging-basic-tutorial) to ensure consistency in our logging practices.
 In general:
 * Use {func}`print` for simple, non-critical messages that do not need to be logged.
-* Use {func}`warnings.warn` for user input issues that are non-critical and can be addressed within `movement`, e.g. deprecated function calls that are redirected, invalid `fps` number in {class}`ValidPosesDataset<movement.validators.datasets.ValidPosesDataset>` that is implicitly set to `None`; or when processing data containing excessive NaNs, which the user can potentially address using appropriate methods, e.g. {func}`interpolate_over_time()<movement.filtering.interpolate_over_time>`
-* Use {meth}`logger.warning()<loguru._logger.Logger.warning>` for non-critical issues where default values are assigned to optional parameters, e.g. `individual_names`, `keypoint_names` in {class}`ValidPosesDataset<movement.validators.datasets.ValidPosesDataset>`.
+* Use {func}`warnings.warn` for user input issues that are non-critical and can be addressed within `movement`, e.g. deprecated function calls that are redirected, invalid `fps` number in {class}`PosesValidator<movement.validators.datasets.PosesValidator>` that is implicitly set to `None`; or when processing data containing excessive NaNs, which the user can potentially address using appropriate methods, e.g. {func}`interpolate_over_time()<movement.filtering.interpolate_over_time>`
+* Use {meth}`logger.warning()<loguru._logger.Logger.warning>` for non-critical issues where default values are assigned to optional parameters, e.g. `individual_names`, `keypoint_names` in {class}`PosesValidator<movement.validators.datasets.PosesValidator>`.
 
 ### Continuous integration
 All pushes and pull requests will be built by [GitHub actions](github-docs:actions).

movement/io/load_bboxes.py

@@ -11,7 +11,7 @@
 import xarray as xr
 
 from movement.utils.logging import logger
-from movement.validators.datasets import ValidBboxesDataset
+from movement.validators.datasets import BboxesValidator
 from movement.validators.files import (
     DEFAULT_FRAME_REGEXP,
     ValidFile,
@@ -136,7 +136,7 @@ def from_numpy(
     ... )
 
     """
-    valid_bboxes_data = ValidBboxesDataset(
+    valid_bboxes_data = BboxesValidator(
         position_array=position_array,
         shape_array=shape_array,
         confidence_array=confidence_array,
@@ -360,7 +360,7 @@ def from_via_tracks_file(
         ),
         fps=fps,
         source_software="VIA-tracks",
-    )  # it validates the dataset via ValidBboxesDataset
+    )  # it validates the dataset via BboxesValidator
 
     # Add metadata as attributes
     ds.attrs["source_software"] = "VIA-tracks"
@@ -650,13 +650,13 @@ def _via_attribute_column_to_numpy(
     return bbox_attr_array.squeeze()
 
 
-def _ds_from_valid_data(data: ValidBboxesDataset) -> xr.Dataset:
+def _ds_from_valid_data(data: BboxesValidator) -> xr.Dataset:
     """Convert a validated bounding boxes dataset to an xarray Dataset.
 
     Parameters
     ----------
-    data : movement.validators.datasets.ValidBboxesDataset
-        The validated bounding boxes dataset object.
+    data : movement.validators.datasets.BboxesValidator
+        The validator object containing the validated bounding boxes data.
 
     Returns
     -------
@@ -678,8 +678,8 @@ def _ds_from_valid_data(data: ValidBboxesDataset) -> xr.Dataset:
     # Store fps as a dataset attribute
     if data.fps:
         # Compute elapsed time from frame 0.
-        # Ignoring type error because `data.frame_array` is not None after
-        # ValidBboxesDataset.__attrs_post_init__()  # type: ignore
+        # Ignore type error as BboxesValidator ensures
+        # `data.frame_array` is not None
         time_coords = np.array(
             [frame / data.fps for frame in data.frame_array.squeeze()]  # type: ignore
         )
@@ -689,7 +689,7 @@ def _ds_from_valid_data(data: ValidBboxesDataset) -> xr.Dataset:
     dataset_attrs["time_unit"] = time_unit
     # Convert data to an xarray.Dataset
     # with dimensions ('time', 'space', 'individuals')
-    DIM_NAMES = ValidBboxesDataset.DIM_NAMES
+    DIM_NAMES = BboxesValidator.DIM_NAMES
     n_space = data.position_array.shape[1]
     return xr.Dataset(
         data_vars={

movement/io/load_poses.py

@@ -12,7 +12,7 @@
 from sleap_io.model.labels import Labels
 
 from movement.utils.logging import logger
-from movement.validators.datasets import ValidPosesDataset
+from movement.validators.datasets import PosesValidator
 from movement.validators.files import (
     ValidAniposeCSV,
     ValidDeepLabCutCSV,
@@ -82,7 +82,7 @@ def from_numpy(
     ... )
 
     """
-    valid_data = ValidPosesDataset(
+    valid_data = PosesValidator(
         position_array=position_array,
         confidence_array=confidence_array,
         individual_names=individual_names,
@@ -713,13 +713,13 @@ def _df_from_dlc_h5(file_path: Path) -> pd.DataFrame:
     return df
 
 
-def _ds_from_valid_data(data: ValidPosesDataset) -> xr.Dataset:
+def _ds_from_valid_data(data: PosesValidator) -> xr.Dataset:
     """Create a ``movement`` poses dataset from validated pose tracking data.
 
     Parameters
     ----------
-    data : movement.io.tracks_validators.ValidPosesDataset
-        The validated data object.
+    data : movement.io.tracks_validators.PosesValidator
+        The validator object containing the validated pose tracking data.
 
     Returns
     -------
@@ -746,7 +746,7 @@ def _ds_from_valid_data(data: ValidPosesDataset) -> xr.Dataset:
 
     dataset_attrs["time_unit"] = time_unit
 
-    DIM_NAMES = ValidPosesDataset.DIM_NAMES
+    DIM_NAMES = PosesValidator.DIM_NAMES
     # Convert data to an xarray.Dataset
     return xr.Dataset(
         data_vars={

movement/io/save_bboxes.py

@@ -10,7 +10,7 @@
 import xarray as xr
 
 from movement.utils.logging import logger
-from movement.validators.datasets import ValidBboxesDataset
+from movement.validators.datasets import BboxesValidator
 from movement.validators.files import _validate_file_path
 
 
@@ -124,7 +124,7 @@ def to_via_tracks_file(
     """
     # Validate file path and dataset
     file = _validate_file_path(file_path, expected_suffix=[".csv"])
-    ValidBboxesDataset.validate(ds)
+    BboxesValidator.validate(ds)
 
     # Check the number of digits required to represent the frame numbers
     frame_n_digits = _check_frame_required_digits(

movement/io/save_poses.py

@@ -15,7 +15,7 @@
     _write_processing_module,
 )
 from movement.utils.logging import logger
-from movement.validators.datasets import ValidPosesDataset
+from movement.validators.datasets import PosesValidator
 from movement.validators.files import _validate_file_path
 
 
@@ -126,7 +126,7 @@ def to_dlc_style_df(
     to_dlc_file : Save dataset directly to a DeepLabCut-style .h5 or .csv file.
 
     """
-    ValidPosesDataset.validate(ds)
+    PosesValidator.validate(ds)
     scorer = ["movement"]
     bodyparts = ds.coords["keypoints"].data.tolist()
     base_coords = ds.coords["space"].data.tolist()
@@ -265,7 +265,7 @@ def to_lp_file(
 
     """
     file = _validate_file_path(file_path=file_path, expected_suffix=[".csv"])
-    ValidPosesDataset.validate(ds)
+    PosesValidator.validate(ds)
     to_dlc_file(ds, file.path, split_individuals=True)
 
 
@@ -309,7 +309,7 @@ def to_sleap_analysis_file(ds: xr.Dataset, file_path: str | Path) -> None:
 
     """
     file = _validate_file_path(file_path=file_path, expected_suffix=[".h5"])
-    ValidPosesDataset.validate(ds)
+    PosesValidator.validate(ds)
 
     ds = _remove_unoccupied_tracks(ds)
 

movement/validators/datasets.py

@@ -248,7 +248,7 @@ def validate(cls, ds: xr.Dataset) -> None:
 
 
 @define(kw_only=True)
-class ValidPosesDataset(_BaseValidDataset):
+class PosesValidator(_BaseValidDataset):
     """Class for validating poses data intended for a ``movement`` dataset.
 
     The validator ensures that within the ``movement poses`` dataset:
@@ -336,7 +336,7 @@ def __attrs_post_init__(self):
 
 
 @define(kw_only=True)
-class ValidBboxesDataset(_BaseValidDataset):
+class BboxesValidator(_BaseValidDataset):
     """Class for validating bounding boxes data for a ``movement`` dataset.
 
     The validator considers 2D bounding boxes only. It ensures that

tests/fixtures/datasets.py

@@ -5,14 +5,14 @@
 import pytest
 import xarray as xr
 
-from movement.validators.datasets import ValidBboxesDataset, ValidPosesDataset
+from movement.validators.datasets import BboxesValidator, PosesValidator
 
 
 # -------------------- Valid bboxes datasets and arrays --------------------
 @pytest.fixture
 def valid_bboxes_arrays_all_zeros():
     """Return a dictionary of valid zero arrays (in terms of shape) for a
-    ValidBboxesDataset.
+    valid bboxes dataset.
     """
     # define the shape of the arrays
     n_frames, n_space, n_individuals = (10, 2, 2)
@@ -31,7 +31,7 @@ def valid_bboxes_arrays_all_zeros():
 @pytest.fixture
 def valid_bboxes_arrays():
     """Return a dictionary of valid arrays for a
-    ValidBboxesDataset representing a uniform linear motion.
+    BboxesValidator representing a uniform linear motion.
 
     It represents 2 individuals for 10 frames, in 2D space.
     - Individual 0 moves along the x=y line from the origin.
@@ -94,7 +94,7 @@ def valid_bboxes_dataset(valid_bboxes_arrays):
     - Individual 0 at frames 2, 3, 4
     - Individual 1 at frames 2, 3
     """
-    dim_names = ValidBboxesDataset.DIM_NAMES
+    dim_names = BboxesValidator.DIM_NAMES
 
     position_array = valid_bboxes_arrays["position"]
     shape_array = valid_bboxes_arrays["shape"]
@@ -152,7 +152,7 @@ def valid_bboxes_dataset_with_nan(valid_bboxes_dataset):
 @pytest.fixture
 def valid_poses_arrays():
     """Return a dictionary of valid arrays for a
-    ValidPosesDataset representing a uniform linear motion.
+    valid poses dataset representing a uniform linear motion.
 
     This fixture is a factory of fixtures.
     Depending on the ``array_type`` requested (``multi_individual_array``,
@@ -173,7 +173,7 @@ def valid_poses_arrays():
     """
 
     def _valid_poses_arrays(array_type):
-        """Return a dictionary of valid arrays for a ValidPosesDataset."""
+        """Return a dictionary of valid arrays for a PosesValidator."""
         # Unless specified, default is a ``multi_individual_array`` with
         # 10 frames, 3 keypoints, and 2 individuals in 2D space.
         n_frames, n_space, n_keypoints, n_individuals = (10, 2, 3, 2)
@@ -250,7 +250,7 @@ def valid_poses_dataset(valid_poses_arrays, request):
     Default is a ``multi_individual_array`` (2 individuals, 3 keypoints each).
     See the ``valid_poses_arrays`` fixture for details.
     """
-    dim_names = ValidPosesDataset.DIM_NAMES
+    dim_names = PosesValidator.DIM_NAMES
     # create a multi_individual_array by default unless overridden via param
     try:
         array_type = request.param

tests/test_unit/test_io/test_load_bboxes.py

@@ -10,7 +10,7 @@
 import pytest
 
 from movement.io import load_bboxes
-from movement.validators.datasets import ValidBboxesDataset
+from movement.validators.datasets import BboxesValidator
 
 
 @pytest.fixture()
@@ -269,7 +269,7 @@ def test_from_file(
 
 expected_values_bboxes = {
     "vars_dims": {"position": 3, "shape": 3, "confidence": 2},
-    "dim_names": ValidBboxesDataset.DIM_NAMES,
+    "dim_names": BboxesValidator.DIM_NAMES,
 }
 
 

tests/test_unit/test_io/test_load_poses.py

@@ -8,11 +8,11 @@
 from pytest import DATA_PATHS
 
 from movement.io import load_poses
-from movement.validators.datasets import ValidPosesDataset
+from movement.validators.datasets import PosesValidator
 
 expected_values_poses = {
     "vars_dims": {"position": 4, "confidence": 3},
-    "dim_names": ValidPosesDataset.DIM_NAMES,
+    "dim_names": PosesValidator.DIM_NAMES,
 }
 
 

tests/test_unit/test_validators/test_datasets_validators.py

@@ -6,8 +6,8 @@
 import xarray as xr
 
 from movement.validators.datasets import (
-    ValidBboxesDataset,
-    ValidPosesDataset,
+    BboxesValidator,
+    PosesValidator,
     _BaseValidDataset,
     _convert_fps_to_none_if_invalid,
     _convert_to_list_of_str,
@@ -279,8 +279,8 @@ def test_validate(self, dataset_fixture, expected_exception, request):
             )
 
 
-class TestValidPosesDataset:
-    """Test the ValidPosesDataset class."""
+class TestPosesValidator:
+    """Test the PosesValidator class."""
 
     @pytest.mark.parametrize(
         "position_array, keypoint_names, expected_context",
@@ -312,17 +312,17 @@ class TestValidPosesDataset:
     def test_keypoint_names(
         self, position_array, keypoint_names, expected_context
     ):
-        """Test keypoint_names validation in ValidPosesDataset."""
+        """Test keypoint_names validation in PosesValidator."""
         with expected_context as expected_keypoint_names:
-            ds = ValidPosesDataset(
+            data = PosesValidator(
                 position_array=position_array,
                 keypoint_names=keypoint_names,
             )
-            assert ds.keypoint_names == expected_keypoint_names
+            assert data.keypoint_names == expected_keypoint_names
 
 
-class TestValidBboxesDataset:
-    """Test the ValidBboxesDataset class."""
+class TestBboxesValidator:
+    """Test the BboxesValidator class."""
 
     @pytest.mark.parametrize(
         "shape_array, expected_context",
@@ -364,7 +364,7 @@ def test_shape_array(self, shape_array, expected_context):
         """Test shape_array validation."""
         position_array = np.zeros((5, 2, 3))  # time, space, individuals
         with expected_context:
-            ValidBboxesDataset(
+            BboxesValidator(
                 position_array=position_array,
                 shape_array=shape_array,
             )
@@ -417,9 +417,11 @@ def test_frame_array(self, frame_array, expected_context):
         position_array = np.zeros((5, 2, 3))  # time, space, individuals
         shape_array = np.zeros((5, 2, 3))
         with expected_context as expected_frame_array:
-            ds = ValidBboxesDataset(
+            data = BboxesValidator(
                 position_array=position_array,
                 shape_array=shape_array,
                 frame_array=frame_array,
             )
-            np.testing.assert_array_equal(ds.frame_array, expected_frame_array)
+            np.testing.assert_array_equal(
+                data.frame_array, expected_frame_array
+            )