diff --git a/src/pymovements/dataset/.dataset_definition.py.swp b/src/pymovements/dataset/.dataset_definition.py.swp new file mode 100644 index 00000000..2795a03c Binary files /dev/null and b/src/pymovements/dataset/.dataset_definition.py.swp differ diff --git a/src/pymovements/datasets/didec.py b/src/pymovements/datasets/didec.py index b9ead4c6..c27faddc 100644 --- a/src/pymovements/datasets/didec.py +++ b/src/pymovements/datasets/didec.py @@ -47,6 +47,10 @@ class DIDEC(DatasetDefinition): name: str The name of the dataset. + has_files: dict[str, bool] + Indicate whether the dataset contains 'gaze', 'precomputed_events', and + 'precomputed_reading_measures'. + mirrors: dict[str, tuple[str, ...]] A tuple of mirrors of the dataset. Each entry must be of type `str` and end with a '/'. @@ -59,6 +63,9 @@ class DIDEC(DatasetDefinition): experiment: Experiment The experiment definition. + extract: dict[str, bool] + Decide whether to extract the data. + filename_format: dict[str, str] Regular expression which will be matched before trying to load the file. Namedgroups will appear in the `fileinfo` dataframe. @@ -67,6 +74,27 @@ class DIDEC(DatasetDefinition): If named groups are present in the `filename_format`, this makes it possible to cast specific named groups to a particular datatype. + trial_columns: list[str] + 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: str + The name of the timestamp column in the input data frame. This column will be renamed to + ``time``. + + time_unit: str + 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. + + pixel_columns: list[str] + 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. + column_map: dict[str, str] The keys are the columns to read, the values are the names to which they should be renamed. @@ -122,8 +150,6 @@ class DIDEC(DatasetDefinition): }, ) - extract: dict[str, bool] = field(default_factory=lambda: {'gaze': True}) - experiment: Experiment = Experiment( screen_width_px=1680, screen_height_px=1050, @@ -134,6 +160,8 @@ class DIDEC(DatasetDefinition): sampling_rate=1000, ) + extract: dict[str, bool] = field(default_factory=lambda: {'gaze': True}) + filename_format: dict[str, str] = field( default_factory=lambda: { 'gaze':