DIDEC

class pymovements.datasets.DIDEC(name: str = 'DIDEC', long_name: str = 'Dutch Image Description and Eye-tracking Corpus', mirrors: dict[str, Sequence[str]] = <factory>, resources: ResourceDefinitions = <factory>, experiment: Experiment = <factory>, extract: dict[str, bool] | None = None, custom_read_kwargs: dict[str, dict[str, Any]] = <factory>, column_map: dict[str, str] = <factory>, trial_columns: list[str] = <factory>, time_column: str = 'Time', time_unit: str = 'ms', pixel_columns: list[str] = <factory>, position_columns: list[str] | None = None, velocity_columns: list[str] | None = None, acceleration_columns: list[str] | None = None, distance_column: str | None = None, filename_format: dict[str, str] | None = None, filename_format_schema_overrides: dict[str, dict[str, type]] | None = None)

DIDEC dataset [van Miltenburg et al., 2018].

The DIDEC eye-tracking data has two different data collections, (1) for the description viewing task is more coherent than for the free-viewing task; (2) variation in image descriptions. The data was collected using BeGaze eye-tracker with a sampling rate of 250 Hz. The data collection contains 112 Dutch students, 54 students completed the free viewing task, while 58 completed the image description task.

Check the respective paper for details [van Miltenburg et al., 2018].

name

The name of the dataset.

Type:

str

long_name

The entire name of the dataset.

Type:

str

resources

A list 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:

ResourceDefinitions

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:

dict[str, str] | None

filename_format_schema_overrides

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, dict[str, type]] | None

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.

Type:

list[str]

time_column

The name of the timestamp column in the input data frame. This column will be renamed to time.

Type:

str

time_unit

The unit of the timestamps in the timestamp column in the input data frame. Supported units are ‘s’ for seconds, ‘ms’ for milliseconds and ‘step’ for steps. If the unit is ‘step’ the experiment definition must be specified. All timestamps will be converted to milliseconds.

Type:

str

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.

Type:

list[str]

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, dict[str, Any]]

Examples

Initialize your Dataset object with the DIDEC definition:

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

Download the dataset resources:

>>> dataset.download()

Load the data into memory:

>>> dataset.load()

Methods

__init__([name, long_name, mirrors, ...])
from_yaml(path)	Load a dataset definition from a YAML file.
to_dict(*[, exclude_private, exclude_none])	Return dictionary representation.
to_yaml(path, *[, exclude_private, exclude_none])	Save a dataset definition to a YAML file.

Attributes

acceleration_columns
distance_column
extract
filename_format
filename_format_schema_overrides
has_resources	Checks for resources in resources.
long_name
name
pixel_columns
position_columns
time_column
time_unit
trial_columns
velocity_columns
resources
experiment
column_map
custom_read_kwargs
mirrors