pymovements.datasets.Provo

class pymovements.datasets.Provo(name: str = 'Provo', has_files: dict[str, bool] = <factory>, mirrors: dict[str, tuple[str, ...]] = <factory>, resources: dict[str, tuple[dict[str, str], ...]] = <factory>, experiment: Experiment = <pymovements.gaze.experiment.Experiment object>, extract: dict[str, bool] = <factory>, filename_format: dict[str, str] = <factory>, filename_format_schema_overrides: dict[str, dict[str, type]] = <factory>, custom_read_kwargs: dict[str, dict[str, Any]] = <factory>, column_map: dict[str, str] = <factory>, trial_columns: list[str] = <factory>, time_column: str = '', time_unit: str = '', 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)

Provo dataset [Luke and Christianson, 2018].

The Provo Corpus, a corpus of eye-tracking data with accompanying predictability norms. The predictability norms for the Provo Corpus differ from those of other corpora. In addition to traditional cloze scores that estimate the predictability of the full orthographic form of each word, the Provo Corpus also includes measures of the predictability of the morpho-syntactic and semantic information for each word. This makes the Provo Corpus ideal for studying predictive processes in reading.

Check the respective paper for details [Luke and Christianson, 2018].

name

The name of the dataset.

Type:

str

has_files

Indicate whether the dataset contains ‘gaze’, ‘precomputed_events’, and ‘precomputed_reading_measures’.

Type:

dict[str, bool]

mirrors

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

Type:

dict[str, tuple[str, …]]

resources

A tuple of dataset gaze_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:

dict[str, tuple[dict[str, str], …]]

extract

Decide whether to extract the data.

Type:

dict[str, bool]

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]

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]]

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 SBSAT definition:

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

Download the dataset resources:

>>> dataset.download()

Load the data into memory:

>>> dataset.load()

__init__(name: str = 'Provo', has_files: dict[str, bool] = <factory>, mirrors: dict[str, tuple[str, ...]] = <factory>, resources: dict[str, tuple[dict[str, str], ...]] = <factory>, experiment: Experiment = <pymovements.gaze.experiment.Experiment object>, extract: dict[str, bool] = <factory>, filename_format: dict[str, str] = <factory>, filename_format_schema_overrides: dict[str, dict[str, type]] = <factory>, custom_read_kwargs: dict[str, dict[str, Any]] = <factory>, column_map: dict[str, str] = <factory>, trial_columns: list[str] = <factory>, time_column: str = '', time_unit: str = '', 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) → None

Methods

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

Attributes

acceleration_columns
distance_column
experiment
name
pixel_columns
position_columns
time_column
time_unit
trial_columns
velocity_columns
has_files
mirrors
resources
extract
filename_format
filename_format_schema_overrides
column_map
custom_read_kwargs