dcase_framework.metadata.MetaDataContainer.load

MetaDataContainer.load(filename=None)

Load event list from delimited text file (csv-formated)

Preferred delimiter is tab, however, other delimiters are supported automatically (they are sniffed automatically).

Supported input formats:

• [file(string)]
• [file(string)][scene_label(string)]
• [file(string)][scene_label(string)][identifier(string)]
• [event_onset (float)][tab][event_offset (float)]
• [event_onset (float)][tab][event_offset (float)][tab][event_label (string)]
• [file(string)][event_onset (float)][tab][event_offset (float)][tab][event_label (string)]
• [file(string)[tab][scene_label(string)][tab][event_onset (float)][tab][event_offset (float)][tab][event_label (string)]
• [file(string)[tab][scene_label(string)][tab][event_onset (float)][tab][event_offset (float)][tab][event_label (string)][tab][source(single character)]
• [file(string)[tab][scene_label(string)][tab][event_onset (float)][tab][event_offset (float)][tab][event_label (string)][tab][source(string)]
• [file(string)[tab][tags (list of strings, delimited with ;)]
• [file(string)[tab][scene_label(string)][tab][tags (list of strings, delimited with ;)]
• [file(string)[tab][scene_label(string)][tab][tags (list of strings, delimited with ;)][tab][event_onset (float)][tab][event_offset (float)]

Parameters:

filename : str

Path to the event list in text format (csv). If none given, one given for class constructor is used. Default value “None”

Returns:

data : list of event dicts

List containing event dicts