pymovements.datasets.GazeBase

class pymovements.datasets.GazeBase(name: str = 'GazeBase', mirrors: tuple[str] = ('https://figshare.com/ndownloader/files/', ), resources: tuple[dict[str, str]] = ({'filename': 'GazeBase_v2_0.zip', 'md5': 'cb7eb895fb48f8661decf038ab998c9a', 'resource': '27039812'}, ), experiment: Experiment = <pymovements.gaze.experiment.Experiment object>, filename_format: str = 'S_{round_id:1d}{subject_id:d}_S{session_id:d}_{task_name}.csv', filename_format_dtypes: dict[str, type] = <factory>, custom_read_kwargs: dict[str, Any] = <factory>, column_map: dict[str, str] = <factory>, trial_columns: list[str] = <factory>, time_column: str = 'n', time_unit: str = 'ms', pixel_columns: list[str] | None = None, position_columns: list[str] = <factory>, velocity_columns: list[str] | None = None, acceleration_columns: list[str] | None = None, distance_column: str | None = None)

GazeBase dataset [Griffith et al., 2021].

This dataset includes monocular (left eye) eye tracking data from 322 participants captured over a period of 37 months. Participants attended up to 9 rounds during this time frame, with each round consisting of two contiguous sessions.

Eye movements are recorded at a sampling frequency of 1000 Hz using an EyeLink 1000 video-based eye tracker and are provided as positional data in degrees of visual angle.

In each of the two sessions per round, participants are instructed to complete a series of tasks, including a fixation task (FIX), a horizontal saccade task (HSS), a random saccade task (RAN), a reading task (TEX), two free viewing video tasks (VD1 and VD2) and a gaze-driven gaming task (BLG).

Check the respective paper for details [Griffith et al., 2021].

name

The name of the dataset.

Type:

str

mirrors

A tuple of mirrors of the dataset. Each entry must be of type str and end with a ‘/’.

Type:

tuple[str, …]

resources

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.

Type:

tuple[dict[str, str], …]

experiment

The experiment definition.

Type:

Experiment

filename_format

Regular expression which will be matched before trying to load the file. Namedgroups will appear in the fileinfo dataframe.

Type:

str

filename_format_dtypes

If named groups are present in the filename_format, this makes it possible to cast specific named groups to a particular datatype.

Type:

dict[str, type], optional

column_map

The keys are the columns to read, the values are the names to which they should be renamed.

Type:

dict[str, str]

custom_read_kwargs

If specified, these keyword arguments will be passed to the file reading function.

Type:

dict[str, Any], optional

Examples

Initialize your PublicDataset object with the GazeBase definition:

>>> import pymovements as pm
>>>
>>> dataset = pm.Dataset("GazeBase", path='data/GazeBase')

Download the dataset resources:

>>> dataset.download()

Load the data into memory:

>>> dataset.load()

__init__(name: str = 'GazeBase', mirrors: tuple[str] = ('https://figshare.com/ndownloader/files/', ), resources: tuple[dict[str, str]] = ({'filename': 'GazeBase_v2_0.zip', 'md5': 'cb7eb895fb48f8661decf038ab998c9a', 'resource': '27039812'}, ), experiment: Experiment = <pymovements.gaze.experiment.Experiment object>, filename_format: str = 'S_{round_id:1d}{subject_id:d}_S{session_id:d}_{task_name}.csv', filename_format_dtypes: dict[str, type] = <factory>, custom_read_kwargs: dict[str, Any] = <factory>, column_map: dict[str, str] = <factory>, trial_columns: list[str] = <factory>, time_column: str = 'n', time_unit: str = 'ms', pixel_columns: list[str] | None = None, position_columns: list[str] = <factory>, velocity_columns: list[str] | None = None, acceleration_columns: list[str] | None = None, distance_column: str | None = None) → None

Methods

__init__([name, mirrors, resources, ...])

Attributes

acceleration_columns
distance_column
experiment
filename_format
mirrors
name
pixel_columns
position_columns
resources
time_column
time_unit
trial_columns
velocity_columns
filename_format_dtypes
column_map
custom_read_kwargs