feat: Add public dataset GazeOnFaces

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

@@ -28,6 +28,7 @@
     pymovements.datasets.GazeBase
     pymovements.datasets.GazeBaseVR
     pymovements.datasets.JuDo1000
+    pymovements.datasets.GazeOnFaces
 
 
 .. rubric:: Example Datasets
@@ -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
@@ -50,6 +52,7 @@
     'GazeBase',
     'GazeBaseVR',
     'JuDo1000',
+    'GazeOnFaces',
     '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],
+        },
+    )

src/pymovements/gaze/__init__.py

@@ -62,6 +62,7 @@
 from pymovements.gaze.gaze_dataframe import GazeDataFrame
 from pymovements.gaze.integration import from_numpy
 from pymovements.gaze.integration import from_pandas
+from pymovements.gaze.io import from_csv
 from pymovements.gaze.screen import Screen
 
 
@@ -73,4 +74,5 @@
     'Screen',
     'transforms_numpy',
     'transforms',
+    'from_csv',
 ]

src/pymovements/gaze/io.py

@@ -0,0 +1,160 @@
+# 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.
+"""Functionality to load GazeDataFrame from a csv file."""
+from __future__ import annotations
+
+from pathlib import Path
+from typing import Any
+
+import polars as pl
+
+from pymovements.gaze import Experiment  # pylint: disable=cyclic-import
+from pymovements.gaze.gaze_dataframe import GazeDataFrame  # pylint: disable=cyclic-import
+
+
+def from_csv(
+        file: str | Path,
+        experiment: Experiment | None = None,
+        *,
+        trial_columns: list[str] | None = None,
+        time_column: str | None = None,
+        pixel_columns: list[str] | None = None,
+        position_columns: list[str] | None = None,
+        velocity_columns: list[str] | None = None,
+        acceleration_columns: list[str] | None = None,
+        **read_csv_kwargs: Any,
+) -> GazeDataFrame:
+    """Initialize a :py:class:`pymovements.gaze.gaze_dataframe.GazeDataFrame`.
+
+    Parameters
+    ----------
+    file:
+        Path of gaze file.
+    experiment : Experiment
+        The experiment definition.
+    trial_columns:
+        The name of the trial columns in the input data frame. If the list is empty or None,
+        the input data frame is assumed to contain only one trial. If the list is not empty,
+        the input data frame is assumed to contain multiple trials and the transformation
+        methods will be applied to each trial separately.
+    time_column:
+        The name of the timestamp column in the input data frame.
+    pixel_columns:
+        The name of the pixel position columns in the input data frame. These columns will be
+        nested into the column ``pixel``. If the list is empty or None, the nested ``pixel``
+        column will not be created.
+    position_columns:
+        The name of the dva position columns in the input data frame. These columns will be
+        nested into the column ``position``. If the list is empty or None, the nested
+        ``position`` column will not be created.
+    velocity_columns:
+        The name of the velocity columns in the input data frame. These columns will be nested
+        into the column ``velocity``. If the list is empty or None, the nested ``velocity``
+        column will not be created.
+    acceleration_columns:
+        The name of the acceleration columns in the input data frame. These columns will be
+        nested into the column ``acceleration``. If the list is empty or None, the nested
+        ``acceleration`` column will not be created.
+    **read_csv_kwargs:
+            Additional keyword arguments to be passed to polars to read in the csv.
+
+    Notes
+    -----
+    About using the arguments ``pixel_columns``, ``position_columns``, ``velocity_columns``,
+    and ``acceleration_columns``:
+
+    By passing a list of columns as any of these arguments, these columns will be merged into a
+    single column with the corresponding name , e.g. using `pixel_columns` will merge the
+    respective columns into the column `pixel`.
+
+    The supported number of component columns with the expected order are:
+
+    * zero columns: No nested component column will be created.
+    * two columns: monocular data; expected order: x-component, y-component
+    * four columns: binocular data; expected order: x-component left eye, y-component left eye,
+      x-component right eye, y-component right eye,
+    * six columns: binocular data with additional cyclopian data; expected order: x-component
+      left eye, y-component left eye, x-component right eye, y-component right eye,
+      x-component cyclopian eye, y-component cyclopian eye,
+
+
+    Examples
+    --------
+    First let's assume a CSV file stored `tests/gaze/io/files/monocular_example.csv`
+    with the following content:
+    shape: (10, 3)
+    ┌──────┬────────────┬────────────┐
+    │ time ┆ x_left_pix ┆ y_left_pix │
+    │ ---  ┆ ---        ┆ ---        │
+    │ i64  ┆ i64        ┆ i64        │
+    ╞══════╪════════════╪════════════╡
+    │ 0    ┆ 0          ┆ 0          │
+    │ 0    ┆ 0          ┆ 0          │
+    │ 0    ┆ 0          ┆ 0          │
+    │ 0    ┆ 0          ┆ 0          │
+    │ …    ┆ …          ┆ …          │
+    │ 0    ┆ 0          ┆ 0          │
+    │ 0    ┆ 0          ┆ 0          │
+    │ 0    ┆ 0          ┆ 0          │
+    │ 0    ┆ 0          ┆ 0          │
+    └──────┴────────────┴────────────┘
+
+    We can now load the data into a ``GazeDataFrame`` by specyfing the experimental setting
+    and the names of the pixel position columns.
+
+    >>> from pymovements.gaze.io import from_csv
+    >>> gaze = from_csv(
+    ...     file='tests/gaze/io/files/monocular_example.csv',
+    ...     time_column = 'time',
+    ...     pixel_columns = ['x_left_pix','y_left_pix'],)
+    >>> gaze.frame
+    shape: (10, 2)
+    ┌──────┬───────────┐
+    │ time ┆ pixel     │
+    │ ---  ┆ ---       │
+    │ i64  ┆ list[i64] │
+    ╞══════╪═══════════╡
+    │ 0    ┆ [0, 0]    │
+    │ 0    ┆ [0, 0]    │
+    │ 0    ┆ [0, 0]    │
+    │ 0    ┆ [0, 0]    │
+    │ …    ┆ …         │
+    │ 0    ┆ [0, 0]    │
+    │ 0    ┆ [0, 0]    │
+    │ 0    ┆ [0, 0]    │
+    │ 0    ┆ [0, 0]    │
+    └──────┴───────────┘
+
+    """
+    # read data
+    gaze_data = pl.read_csv(file, **read_csv_kwargs)
+
+    # create gaze data frame
+    gaze_df = GazeDataFrame(
+        gaze_data,
+        experiment=experiment,
+        trial_columns=trial_columns,
+        time_column=time_column,
+        pixel_columns=pixel_columns,
+        position_columns=position_columns,
+        velocity_columns=velocity_columns,
+        acceleration_columns=acceleration_columns,
+    )
+    return gaze_df