feat: Add public dataset GazeOnFaces (#567)

Co-authored-by: prassepaul <[email protected]>

docs/source/bibliography.bib

@@ -65,3 +65,14 @@ @article{GazeBaseVR
     journal = {Scientific Data},
     doi = {10.1038/s41597-023-02075-5},
 }
+
+@article{GazeOnFaces,
+  title={Face exploration dynamics differentiate men and women},
+  author={Coutrot, Antoine and Binetti, Nicola and Harrison, Charlotte and Mareschal, Isabelle and Johnston, Alan},
+  journal={Journal of vision},
+  volume={16},
+  number={14},
+  pages={16--16},
+  year={2016},
+  publisher={The Association for Research in Vision and Ophthalmology}
+}

src/pymovements/datasets/__init__.py

@@ -27,6 +27,7 @@
 
     pymovements.datasets.GazeBase
     pymovements.datasets.GazeBaseVR
+    pymovements.datasets.GazeOnFaces
     pymovements.datasets.JuDo1000
 
 
@@ -39,6 +40,7 @@
     pymovements.datasets.ToyDataset
     pymovements.datasets.ToyDatasetEyeLink
 """
+from pymovements.datasets.gaze_on_faces import GazeOnFaces
 from pymovements.datasets.gazebase import GazeBase
 from pymovements.datasets.gazebasevr import GazeBaseVR
 from pymovements.datasets.judo1000 import JuDo1000
@@ -49,6 +51,7 @@
 __all__ = [
     'GazeBase',
     'GazeBaseVR',
+    'GazeOnFaces',
     'JuDo1000',
     'ToyDataset',
     'ToyDatasetEyeLink',

src/pymovements/datasets/gaze_on_faces.py

@@ -0,0 +1,149 @@
+# Copyright (c) 2022-2023 The pymovements Project Authors
+#
+# Permission is hereby granted, free of charge, to any person obtaining a copy
+# of this software and associated documentation files (the "Software"), to deal
+# in the Software without restriction, including without limitation the rights
+# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+# copies of the Software, and to permit persons to whom the Software is
+# furnished to do so, subject to the following conditions:
+#
+# The above copyright notice and this permission notice shall be included in all
+# copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+# SOFTWARE.
+"""This module provides an interface to the GazeOnFaces dataset."""
+from __future__ import annotations
+
+from dataclasses import dataclass
+from dataclasses import field
+from typing import Any
+
+import polars as pl
+
+from pymovements.dataset.dataset_definition import DatasetDefinition
+from pymovements.dataset.dataset_library import register_dataset
+from pymovements.gaze.experiment import Experiment
+
+
+@dataclass
+@register_dataset
+class GazeOnFaces(DatasetDefinition):
+    """GazeBaseVR dataset :cite:p:`GazeOnFaces`.
+
+    This dataset includes monocular eye tracking data from single participants in a single
+    session. Eye movements are recorded at a sampling frequency of 60 Hz
+    using an EyeLink 1000 video-based eye tracker and are provided as pixel coordinates.
+
+    Participants were sat 57 cm away from the screen (19inch LCD monitor,
+    screen res=1280×1024, 60 Hz). Recordings of the eye movements of one eye in monocular
+    pupil/corneal reflection tracking mode.
+
+    Check the respective paper for details :cite:p:`GazeOnFaces`.
+
+    Attributes
+    ----------
+    name : str
+        The name of the dataset.
+
+    mirrors : tuple[str, ...]
+        A tuple of mirrors of the dataset. Each entry must be of type `str` and end with a '/'.
+
+    resources : tuple[dict[str, str], ...]
+        A tuple of dataset resources. Each list entry must be a dictionary with the following keys:
+        - `resource`: The url suffix of the resource. This will be concatenated with the mirror.
+        - `filename`: The filename under which the file is saved as.
+        - `md5`: The MD5 checksum of the respective file.
+
+    experiment : Experiment
+        The experiment definition.
+
+    filename_format : str
+        Regular expression which will be matched before trying to load the file. Namedgroups will
+        appear in the `fileinfo` dataframe.
+
+    filename_format_dtypes : dict[str, type], optional
+        If named groups are present in the `filename_format`, this makes it possible to cast
+        specific named groups to a particular datatype.
+
+    column_map : dict[str, str]
+        The keys are the columns to read, the values are the names to which they should be renamed.
+
+    custom_read_kwargs : dict[str, Any], optional
+        If specified, these keyword arguments will be passed to the file reading function.
+
+    Examples
+    --------
+    Initialize your :py:class:`~pymovements.PublicDataset` object with the
+    :py:class:`~pymovements.GazeOnFaces` definition:
+
+    >>> import pymovements as pm
+    >>>
+    >>> dataset = pm.Dataset("GazeOnFaces", path='data/GazeOnFaces')
+
+    Download the dataset resources resources:
+
+    >>> dataset.download()# doctest: +SKIP
+
+    Load the data into memory:
+
+    >>> dataset.load()# doctest: +SKIP
+    """
+
+    # pylint: disable=similarities
+    # The PublicDatasetDefinition child classes potentially share code chunks for definitions.
+
+    name: str = 'GazeOnFaces'
+
+    mirrors: tuple[str, ...] = (
+        'https://uncloud.univ-nantes.fr/index.php/s/',
+    )
+
+    resources: tuple[dict[str, str], ...] = (
+        {
+            'resource': '8KW6dEdyBJqxpmo/download?path=%2F&files=gaze_csv.zip',
+            'filename': 'gaze_csv.zip',
+            'md5': 'fe219f07c9253cd9aaee6bd50233c034',
+        },
+    )
+
+    experiment: Experiment = Experiment(
+        screen_width_px=1280,
+        screen_height_px=1024,
+        screen_width_cm=38,
+        screen_height_cm=30,
+        distance_cm=57,
+        origin='center',
+        sampling_rate=60,
+    )
+
+    filename_format: str = r'gaze_sub{sub_id:d}_trial{trial_id:d}.csv'
+
+    filename_format_dtypes: dict[str, type] = field(
+        default_factory=lambda: {
+            'sub_id': int,
+            'trial_id': int,
+        },
+    )
+
+    trial_columns: list[str] = field(default_factory=lambda: ['sub_id', 'trial_id'])
+
+    time_column: Any = None
+
+    pixel_columns: list[str] = field(default_factory=lambda: ['x', 'y'])
+
+    column_map: dict[str, str] = field(default_factory=lambda: {})
+
+    custom_read_kwargs: dict[str, Any] = field(
+        default_factory=lambda: {
+            'separator': ',',
+            'has_header': False,
+            'new_columns': ['x', 'y'],
+            'dtypes': [pl.Float32, pl.Float32],
+        },
+    )

tests/datasets/datasets_test.py

@@ -31,6 +31,7 @@
         pytest.param(pm.datasets.ToyDataset, 'ToyDataset', id='ToyDataset'),
         pytest.param(pm.datasets.GazeBase, 'GazeBase', id='GazeBase'),
         pytest.param(pm.datasets.GazeBaseVR, 'GazeBaseVR', id='GazeBaseVR'),
+        pytest.param(pm.datasets.GazeOnFaces, 'GazeOnFaces', id='GazeOnFaces'),
         pytest.param(pm.datasets.JuDo1000, 'JuDo1000', id='JuDo1000'),
     ],
 )
@@ -46,6 +47,7 @@ def test_public_dataset_registered(definition_class, dataset_name):
         pytest.param(pm.datasets.ToyDataset, id='ToyDataset'),
         pytest.param(pm.datasets.GazeBase, id='GazeBase'),
         pytest.param(pm.datasets.GazeBaseVR, id='GazeBaseVR'),
+        pytest.param(pm.datasets.GazeOnFaces, id='GazeOnFaces'),
         pytest.param(pm.datasets.JuDo1000, id='JuDo1000'),
     ],
 )

tests/datasets/gaze_on_faces_test.py

@@ -0,0 +1,79 @@
+# Copyright (c) 2023 The pymovements Project Authors
+#
+# Permission is hereby granted, free of charge, to any person obtaining a copy
+# of this software and associated documentation files (the "Software"), to deal
+# in the Software without restriction, including without limitation the rights
+# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+# copies of the Software, and to permit persons to whom the Software is
+# furnished to do so, subject to the following conditions:
+#
+# The above copyright notice and this permission notice shall be included in all
+# copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+# SOFTWARE.
+"""Test all functionality in pymovements.dataset.gaze_on_faces."""
+from pathlib import Path
+
+import pytest
+
+import pymovements as pm
+
+
+@pytest.mark.parametrize(
+    'init_path, expected_paths',
+    [
+        pytest.param(
+            '/data/set/path',
+            {
+                'root': Path('/data/set/path/'),
+                'dataset': Path('/data/set/path/'),
+                'download': Path('/data/set/path/downloads'),
+            },
+        ),
+        pytest.param(
+            pm.DatasetPaths(root='/data/set/path'),
+            {
+                'root': Path('/data/set/path/'),
+                'dataset': Path('/data/set/path/GazeOnFaces'),
+                'download': Path('/data/set/path/GazeOnFaces/downloads'),
+            },
+        ),
+        pytest.param(
+            pm.DatasetPaths(root='/data/set/path', dataset='.'),
+            {
+                'root': Path('/data/set/path/'),
+                'dataset': Path('/data/set/path/'),
+                'download': Path('/data/set/path/downloads'),
+            },
+        ),
+        pytest.param(
+            pm.DatasetPaths(root='/data/set/path', dataset='dataset'),
+            {
+                'root': Path('/data/set/path/'),
+                'dataset': Path('/data/set/path/dataset'),
+                'download': Path('/data/set/path/dataset/downloads'),
+            },
+        ),
+        pytest.param(
+            pm.DatasetPaths(root='/data/set/path', downloads='custom_downloads'),
+            {
+                'root': Path('/data/set/path/'),
+                'dataset': Path('/data/set/path/GazeOnFaces'),
+                'download': Path('/data/set/path/GazeOnFaces/custom_downloads'),
+            },
+        ),
+    ],
+)
+def test_paths(init_path, expected_paths):
+    dataset = pm.Dataset(pm.datasets.GazeOnFaces, path=init_path)
+
+    assert dataset.paths.root == expected_paths['root']
+    assert dataset.path == expected_paths['dataset']
+    assert dataset.paths.dataset == expected_paths['dataset']
+    assert dataset.paths.downloads == expected_paths['download']