def load_or_prepare_widgets()

in app.py [0:0]

• 28 lines of code
• 6 McCabe index (conditional complexity)

def load_or_prepare_widgets(dstats, load_prepare_list, show_perplexities, live=True, pull_cache_from_hub=False):
    """
     Takes the dataset arguments from the GUI and uses them to load a dataset from the Hub or, if
     a cache for those arguments is available, to load it from the cache.
     Widget data is loaded only when the system is live (deployed for users).
     Otherwise, the data is prepared if it doesn't yet exist.
     Args:
         ds_args (dict): the dataset arguments defined via the streamlit app GUI
         load_prepare_list (list): List of (widget_name, widget_load_or_prepare_function)
         show_perplexities (Bool): whether perplexities should be loaded and displayed for this dataset
         live (Bool): Whether the system is deployed for live use by users.
         pull_cache_from_hub (Bool): Whether the cache should be pulled from the hub (vs locally)
     Returns:
         dstats: the computed dataset statistics (from the dataset_statistics class)
     """

    # When we're "live" (tool is being used by users on our servers),
    # cache is used and the f'ns are instructed to only try to load cache,
    # not to prepare/compute anything anew.
    if live:
        # Only use what's cached; don't prepare anything
        load_only = True
        logs.info("Only using cache.")
    else:
        # Prepare things anew and cache them if we're not live.
        load_only = False
        logs.info("Making new calculations if cache is not there.")
    if pull_cache_from_hub:
        dataset_utils.pull_cache_from_hub(dstats.cache_path, dstats.dataset_cache_dir)

    # Data common across DMT:
    # Includes the dataset text/requested feature column,
    # the dataset tokenized, and the vocabulary
    dstats.load_or_prepare_text_dataset(load_only=load_only)
    # Just a snippet of the dataset
    dstats.load_or_prepare_dset_peek(load_only=load_only)
    # Tokenized dataset
    dstats.load_or_prepare_tokenized_df(load_only=load_only)
    # Vocabulary (uses tokenized dataset)
    dstats.load_or_prepare_vocab(load_only=load_only)
    # Custom widgets
    for widget_tuple in load_prepare_list:
        widget_name = widget_tuple[0]
        widget_fn = widget_tuple[1]
        try:
            widget_fn(load_only=load_only)
        except Exception as e:
            logs.warning("Issue with %s." % widget_name)
            logs.exception(e)
    # TODO: If these are cached, can't we just show them by default?
    # It won't take up computation time.
    if show_perplexities:
        try:
            dstats.load_or_prepare_text_perplexities(load_only=load_only)
        except Exception as e:
            logs.warning("Issue with %s." % "perplexities")
            logs.exception(e)
    return dstats