gprediction.py 文件源码

def get_training_features(potential_event, fb_event, fb_event_attending):
    if 'owner' in fb_event['info']:
        owner_name = 'id%s' % fb_event['info']['owner']['id']
    else:
        owner_name = ''
    location = event_locations.get_address_for_fb_event(fb_event).encode('utf-8')

    def strip_text(s):
        return strip_punctuation(s.encode('utf8')).lower()

    name = strip_text(fb_event['info'].get('name', ''))
    description = strip_text(fb_event['info'].get('description', ''))

    attendee_list = ' '.join(['id%s' % x['id'] for x in fb_event_attending['attending']['data']])

    source_list = ' '.join('id%s' % x.id for x in potential_event.source_ids_only())

    #TODO(lambert): maybe include number-of-keywords and keyword-density?

    #TODO(lambert): someday write this as a proper mapreduce that reduces across languages and builds a classifier model per language?
    # for now we can just grep and build sub-models per-language on my client machine.
    return (attendee_list,)
    return (potential_event.language, owner_name, location, name, description, attendee_list, source_list)