862f99942ce1eefe93f0cfd1bcf3ade031679cd4,pmlb/dataset_lists.py,,,#,26

Before Change

    "712_chscase_geyser1"
]

datasets_with_metadata = [
    "molecular_biology_promoters",
    "car",
    "connect_4",
    "dna",
    "542_pollution",
    "560_bodyfat",
    "poker",
    "USCrime",
    "pollen",
    "chess",
    "penguins",
    "bupa",
    "movement_libras",
    "adult",
    "waveform_21",
    "waveform_40",
    "saheart",
    "wine_quality_white",
    "wine_quality_red",
    "irish",
    "mushroom"
]

After Change

df_summary = pandas.read_csv("pmlb/all_summary_stats.tsv", sep="\t")
regression_dataset_names = df_summary.query("task=="regression"")["dataset"].tolist()
classification_dataset_names = df_summary.query("task=="classification"")["dataset"].tolist()
dataset_names = regression_dataset_names + classification_dataset_names

def get_datasets_with_metadata(dataset_names, local_cache_dir = "datasets/"):
    assert (local_cache_dir != None)

Instances