File size: 4,521 Bytes
80cbb1a |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 |
"""Pre-computed constants for ISLES24 dataset.
The ISLES24 challenge dataset is static (case IDs will never change).
Pre-computing these values avoids:
1. PyArrow streaming bug (apache/arrow#45214) that hangs on parquet iteration
2. Memory issues from downloading the full 99GB dataset
See docs/specs/08-bug-hf-spaces-dataset-loop.md for full investigation.
"""
# Pre-computed case IDs for ISLES24 dataset
# Extracted via HfFileSystem enumeration on 2025-12-08
# Order matches parquet file indices (train-00000-of-00149.parquet = index 0)
ISLES24_CASE_IDS: tuple[str, ...] = (
"sub-stroke0001",
"sub-stroke0002",
"sub-stroke0003",
"sub-stroke0004",
"sub-stroke0005",
"sub-stroke0006",
"sub-stroke0007",
"sub-stroke0008",
"sub-stroke0009",
"sub-stroke0010",
"sub-stroke0011",
"sub-stroke0012",
"sub-stroke0013",
"sub-stroke0014",
"sub-stroke0015",
"sub-stroke0016",
"sub-stroke0017",
"sub-stroke0019",
"sub-stroke0020",
"sub-stroke0021",
"sub-stroke0022",
"sub-stroke0025",
"sub-stroke0026",
"sub-stroke0027",
"sub-stroke0028",
"sub-stroke0030",
"sub-stroke0033",
"sub-stroke0036",
"sub-stroke0037",
"sub-stroke0038",
"sub-stroke0040",
"sub-stroke0043",
"sub-stroke0045",
"sub-stroke0047",
"sub-stroke0048",
"sub-stroke0049",
"sub-stroke0052",
"sub-stroke0053",
"sub-stroke0054",
"sub-stroke0055",
"sub-stroke0057",
"sub-stroke0062",
"sub-stroke0066",
"sub-stroke0068",
"sub-stroke0070",
"sub-stroke0071",
"sub-stroke0073",
"sub-stroke0074",
"sub-stroke0075",
"sub-stroke0076",
"sub-stroke0077",
"sub-stroke0078",
"sub-stroke0079",
"sub-stroke0080",
"sub-stroke0081",
"sub-stroke0082",
"sub-stroke0083",
"sub-stroke0084",
"sub-stroke0085",
"sub-stroke0086",
"sub-stroke0087",
"sub-stroke0088",
"sub-stroke0089",
"sub-stroke0090",
"sub-stroke0091",
"sub-stroke0092",
"sub-stroke0093",
"sub-stroke0094",
"sub-stroke0095",
"sub-stroke0096",
"sub-stroke0097",
"sub-stroke0098",
"sub-stroke0099",
"sub-stroke0100",
"sub-stroke0101",
"sub-stroke0102",
"sub-stroke0103",
"sub-stroke0104",
"sub-stroke0105",
"sub-stroke0106",
"sub-stroke0107",
"sub-stroke0108",
"sub-stroke0109",
"sub-stroke0110",
"sub-stroke0111",
"sub-stroke0112",
"sub-stroke0113",
"sub-stroke0114",
"sub-stroke0115",
"sub-stroke0116",
"sub-stroke0117",
"sub-stroke0118",
"sub-stroke0119",
"sub-stroke0133",
"sub-stroke0134",
"sub-stroke0135",
"sub-stroke0136",
"sub-stroke0137",
"sub-stroke0138",
"sub-stroke0139",
"sub-stroke0140",
"sub-stroke0141",
"sub-stroke0142",
"sub-stroke0143",
"sub-stroke0144",
"sub-stroke0145",
"sub-stroke0146",
"sub-stroke0147",
"sub-stroke0148",
"sub-stroke0149",
"sub-stroke0150",
"sub-stroke0151",
"sub-stroke0152",
"sub-stroke0153",
"sub-stroke0154",
"sub-stroke0155",
"sub-stroke0156",
"sub-stroke0157",
"sub-stroke0158",
"sub-stroke0159",
"sub-stroke0161",
"sub-stroke0162",
"sub-stroke0163",
"sub-stroke0164",
"sub-stroke0165",
"sub-stroke0166",
"sub-stroke0167",
"sub-stroke0168",
"sub-stroke0169",
"sub-stroke0170",
"sub-stroke0171",
"sub-stroke0172",
"sub-stroke0173",
"sub-stroke0174",
"sub-stroke0175",
"sub-stroke0176",
"sub-stroke0177",
"sub-stroke0178",
"sub-stroke0179",
"sub-stroke0180",
"sub-stroke0181",
"sub-stroke0182",
"sub-stroke0183",
"sub-stroke0184",
"sub-stroke0185",
"sub-stroke0186",
"sub-stroke0187",
"sub-stroke0188",
"sub-stroke0189",
)
# Mapping from case ID to parquet file index (0-indexed)
# train-00000-of-00149.parquet contains sub-stroke0001
# train-00001-of-00149.parquet contains sub-stroke0002
# etc.
ISLES24_CASE_INDEX: dict[str, int] = {case_id: idx for idx, case_id in enumerate(ISLES24_CASE_IDS)}
# Total number of parquet files in the dataset
ISLES24_NUM_FILES: int = 149
# Sanity check: ensure constants are consistent
assert len(ISLES24_CASE_IDS) == ISLES24_NUM_FILES, (
f"ISLES24_CASE_IDS has {len(ISLES24_CASE_IDS)} entries but ISLES24_NUM_FILES is {ISLES24_NUM_FILES}"
)
# Dataset identifier on HuggingFace Hub
ISLES24_DATASET_ID: str = "hugging-science/isles24-stroke"
|