{ "cells": [ { "cell_type": "code", "execution_count": 1, "id": "556cfb74", "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "/opt/conda/envs/antibody_datasets/lib/python3.13/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n", " from .autonotebook import tqdm as notebook_tqdm\n" ] } ], "source": [ "from datasets import load_dataset\n", "import pandas as pd" ] }, { "cell_type": "code", "execution_count": 2, "id": "8b8cea40", "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "Generating train split: 100%|██████████| 61/61 [00:00<00:00, 176.99 examples/s]\n" ] }, { "ename": "ValueError", "evalue": "Unknown split \"auto_submissions\". Should be one of ['train'].", "output_type": "error", "traceback": [ "\u001b[31m---------------------------------------------------------------------------\u001b[39m", "\u001b[31mValueError\u001b[39m Traceback (most recent call last)", "\u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[2]\u001b[39m\u001b[32m, line 2\u001b[39m\n\u001b[32m 1\u001b[39m \u001b[38;5;66;03m# access results dataset\u001b[39;00m\n\u001b[32m----> \u001b[39m\u001b[32m2\u001b[39m res = \u001b[43mload_dataset\u001b[49m\u001b[43m(\u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mginkgo-datapoints/abdev-bench-results\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43msplit\u001b[49m\u001b[43m=\u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mauto_submissions\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[32m 3\u001b[39m \u001b[38;5;28mprint\u001b[39m(res)\n", "\u001b[36mFile \u001b[39m\u001b[32m/opt/conda/envs/antibody_datasets/lib/python3.13/site-packages/datasets/load.py:2096\u001b[39m, in \u001b[36mload_dataset\u001b[39m\u001b[34m(path, name, data_dir, data_files, split, cache_dir, features, download_config, download_mode, verification_mode, keep_in_memory, save_infos, revision, token, streaming, num_proc, storage_options, trust_remote_code, **config_kwargs)\u001b[39m\n\u001b[32m 2092\u001b[39m \u001b[38;5;66;03m# Build dataset for splits\u001b[39;00m\n\u001b[32m 2093\u001b[39m keep_in_memory = (\n\u001b[32m 2094\u001b[39m keep_in_memory \u001b[38;5;28;01mif\u001b[39;00m keep_in_memory \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;28;01melse\u001b[39;00m is_small_dataset(builder_instance.info.dataset_size)\n\u001b[32m 2095\u001b[39m )\n\u001b[32m-> \u001b[39m\u001b[32m2096\u001b[39m ds = \u001b[43mbuilder_instance\u001b[49m\u001b[43m.\u001b[49m\u001b[43mas_dataset\u001b[49m\u001b[43m(\u001b[49m\u001b[43msplit\u001b[49m\u001b[43m=\u001b[49m\u001b[43msplit\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mverification_mode\u001b[49m\u001b[43m=\u001b[49m\u001b[43mverification_mode\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43min_memory\u001b[49m\u001b[43m=\u001b[49m\u001b[43mkeep_in_memory\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m 2097\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m save_infos:\n\u001b[32m 2098\u001b[39m builder_instance._save_infos()\n", "\u001b[36mFile \u001b[39m\u001b[32m/opt/conda/envs/antibody_datasets/lib/python3.13/site-packages/datasets/builder.py:1127\u001b[39m, in \u001b[36mDatasetBuilder.as_dataset\u001b[39m\u001b[34m(self, split, run_post_process, verification_mode, in_memory)\u001b[39m\n\u001b[32m 1124\u001b[39m verification_mode = VerificationMode(verification_mode \u001b[38;5;129;01mor\u001b[39;00m VerificationMode.BASIC_CHECKS)\n\u001b[32m 1126\u001b[39m \u001b[38;5;66;03m# Create a dataset for each of the given splits\u001b[39;00m\n\u001b[32m-> \u001b[39m\u001b[32m1127\u001b[39m datasets = \u001b[43mmap_nested\u001b[49m\u001b[43m(\u001b[49m\n\u001b[32m 1128\u001b[39m \u001b[43m \u001b[49m\u001b[43mpartial\u001b[49m\u001b[43m(\u001b[49m\n\u001b[32m 1129\u001b[39m \u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43m_build_single_dataset\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1130\u001b[39m \u001b[43m \u001b[49m\u001b[43mrun_post_process\u001b[49m\u001b[43m=\u001b[49m\u001b[43mrun_post_process\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1131\u001b[39m \u001b[43m \u001b[49m\u001b[43mverification_mode\u001b[49m\u001b[43m=\u001b[49m\u001b[43mverification_mode\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1132\u001b[39m \u001b[43m \u001b[49m\u001b[43min_memory\u001b[49m\u001b[43m=\u001b[49m\u001b[43min_memory\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1133\u001b[39m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1134\u001b[39m \u001b[43m \u001b[49m\u001b[43msplit\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1135\u001b[39m \u001b[43m \u001b[49m\u001b[43mmap_tuple\u001b[49m\u001b[43m=\u001b[49m\u001b[38;5;28;43;01mTrue\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[32m 1136\u001b[39m \u001b[43m \u001b[49m\u001b[43mdisable_tqdm\u001b[49m\u001b[43m=\u001b[49m\u001b[38;5;28;43;01mTrue\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[32m 1137\u001b[39m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m 1138\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(datasets, \u001b[38;5;28mdict\u001b[39m):\n\u001b[32m 1139\u001b[39m datasets = DatasetDict(datasets)\n", "\u001b[36mFile \u001b[39m\u001b[32m/opt/conda/envs/antibody_datasets/lib/python3.13/site-packages/datasets/utils/py_utils.py:494\u001b[39m, in \u001b[36mmap_nested\u001b[39m\u001b[34m(function, data_struct, dict_only, map_list, map_tuple, map_numpy, num_proc, parallel_min_length, batched, batch_size, types, disable_tqdm, desc)\u001b[39m\n\u001b[32m 492\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m batched:\n\u001b[32m 493\u001b[39m data_struct = [data_struct]\n\u001b[32m--> \u001b[39m\u001b[32m494\u001b[39m mapped = \u001b[43mfunction\u001b[49m\u001b[43m(\u001b[49m\u001b[43mdata_struct\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m 495\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m batched:\n\u001b[32m 496\u001b[39m mapped = mapped[\u001b[32m0\u001b[39m]\n", "\u001b[36mFile \u001b[39m\u001b[32m/opt/conda/envs/antibody_datasets/lib/python3.13/site-packages/datasets/builder.py:1157\u001b[39m, in \u001b[36mDatasetBuilder._build_single_dataset\u001b[39m\u001b[34m(self, split, run_post_process, verification_mode, in_memory)\u001b[39m\n\u001b[32m 1154\u001b[39m split = Split(split)\n\u001b[32m 1156\u001b[39m \u001b[38;5;66;03m# Build base dataset\u001b[39;00m\n\u001b[32m-> \u001b[39m\u001b[32m1157\u001b[39m ds = \u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43m_as_dataset\u001b[49m\u001b[43m(\u001b[49m\n\u001b[32m 1158\u001b[39m \u001b[43m \u001b[49m\u001b[43msplit\u001b[49m\u001b[43m=\u001b[49m\u001b[43msplit\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1159\u001b[39m \u001b[43m \u001b[49m\u001b[43min_memory\u001b[49m\u001b[43m=\u001b[49m\u001b[43min_memory\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1160\u001b[39m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m 1161\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m run_post_process:\n\u001b[32m 1162\u001b[39m \u001b[38;5;28;01mfor\u001b[39;00m resource_file_name \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m._post_processing_resources(split).values():\n", "\u001b[36mFile \u001b[39m\u001b[32m/opt/conda/envs/antibody_datasets/lib/python3.13/site-packages/datasets/builder.py:1231\u001b[39m, in \u001b[36mDatasetBuilder._as_dataset\u001b[39m\u001b[34m(self, split, in_memory)\u001b[39m\n\u001b[32m 1229\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m._check_legacy_cache():\n\u001b[32m 1230\u001b[39m dataset_name = \u001b[38;5;28mself\u001b[39m.name\n\u001b[32m-> \u001b[39m\u001b[32m1231\u001b[39m dataset_kwargs = \u001b[43mArrowReader\u001b[49m\u001b[43m(\u001b[49m\u001b[43mcache_dir\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43minfo\u001b[49m\u001b[43m)\u001b[49m\u001b[43m.\u001b[49m\u001b[43mread\u001b[49m\u001b[43m(\u001b[49m\n\u001b[32m 1232\u001b[39m \u001b[43m \u001b[49m\u001b[43mname\u001b[49m\u001b[43m=\u001b[49m\u001b[43mdataset_name\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1233\u001b[39m \u001b[43m \u001b[49m\u001b[43minstructions\u001b[49m\u001b[43m=\u001b[49m\u001b[43msplit\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1234\u001b[39m \u001b[43m \u001b[49m\u001b[43msplit_infos\u001b[49m\u001b[43m=\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43minfo\u001b[49m\u001b[43m.\u001b[49m\u001b[43msplits\u001b[49m\u001b[43m.\u001b[49m\u001b[43mvalues\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1235\u001b[39m \u001b[43m \u001b[49m\u001b[43min_memory\u001b[49m\u001b[43m=\u001b[49m\u001b[43min_memory\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 1236\u001b[39m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m 1237\u001b[39m fingerprint = \u001b[38;5;28mself\u001b[39m._get_dataset_fingerprint(split)\n\u001b[32m 1238\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m Dataset(fingerprint=fingerprint, **dataset_kwargs)\n", "\u001b[36mFile \u001b[39m\u001b[32m/opt/conda/envs/antibody_datasets/lib/python3.13/site-packages/datasets/arrow_reader.py:248\u001b[39m, in \u001b[36mBaseReader.read\u001b[39m\u001b[34m(self, name, instructions, split_infos, in_memory)\u001b[39m\n\u001b[32m 227\u001b[39m \u001b[38;5;28;01mdef\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34mread\u001b[39m(\n\u001b[32m 228\u001b[39m \u001b[38;5;28mself\u001b[39m,\n\u001b[32m 229\u001b[39m name,\n\u001b[32m (...)\u001b[39m\u001b[32m 232\u001b[39m in_memory=\u001b[38;5;28;01mFalse\u001b[39;00m,\n\u001b[32m 233\u001b[39m ):\n\u001b[32m 234\u001b[39m \u001b[38;5;250m \u001b[39m\u001b[33;03m\"\"\"Returns Dataset instance(s).\u001b[39;00m\n\u001b[32m 235\u001b[39m \n\u001b[32m 236\u001b[39m \u001b[33;03m Args:\u001b[39;00m\n\u001b[32m (...)\u001b[39m\u001b[32m 245\u001b[39m \u001b[33;03m kwargs to build a single Dataset instance.\u001b[39;00m\n\u001b[32m 246\u001b[39m \u001b[33;03m \"\"\"\u001b[39;00m\n\u001b[32m--> \u001b[39m\u001b[32m248\u001b[39m files = \u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43mget_file_instructions\u001b[49m\u001b[43m(\u001b[49m\u001b[43mname\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43minstructions\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43msplit_infos\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m 249\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m files:\n\u001b[32m 250\u001b[39m msg = \u001b[33mf\u001b[39m\u001b[33m'\u001b[39m\u001b[33mInstruction \u001b[39m\u001b[33m\"\u001b[39m\u001b[38;5;132;01m{\u001b[39;00minstructions\u001b[38;5;132;01m}\u001b[39;00m\u001b[33m\"\u001b[39m\u001b[33m corresponds to no data!\u001b[39m\u001b[33m'\u001b[39m\n", "\u001b[36mFile \u001b[39m\u001b[32m/opt/conda/envs/antibody_datasets/lib/python3.13/site-packages/datasets/arrow_reader.py:221\u001b[39m, in \u001b[36mBaseReader.get_file_instructions\u001b[39m\u001b[34m(self, name, instruction, split_infos)\u001b[39m\n\u001b[32m 219\u001b[39m \u001b[38;5;28;01mdef\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34mget_file_instructions\u001b[39m(\u001b[38;5;28mself\u001b[39m, name, instruction, split_infos):\n\u001b[32m 220\u001b[39m \u001b[38;5;250m \u001b[39m\u001b[33;03m\"\"\"Return list of dict {'filename': str, 'skip': int, 'take': int}\"\"\"\u001b[39;00m\n\u001b[32m--> \u001b[39m\u001b[32m221\u001b[39m file_instructions = \u001b[43mmake_file_instructions\u001b[49m\u001b[43m(\u001b[49m\n\u001b[32m 222\u001b[39m \u001b[43m \u001b[49m\u001b[43mname\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43msplit_infos\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43minstruction\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mfiletype_suffix\u001b[49m\u001b[43m=\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43m_filetype_suffix\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mprefix_path\u001b[49m\u001b[43m=\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43m_path\u001b[49m\n\u001b[32m 223\u001b[39m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m 224\u001b[39m files = file_instructions.file_instructions\n\u001b[32m 225\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m files\n", "\u001b[36mFile \u001b[39m\u001b[32m/opt/conda/envs/antibody_datasets/lib/python3.13/site-packages/datasets/arrow_reader.py:130\u001b[39m, in \u001b[36mmake_file_instructions\u001b[39m\u001b[34m(name, split_infos, instruction, filetype_suffix, prefix_path)\u001b[39m\n\u001b[32m 128\u001b[39m instruction = ReadInstruction.from_spec(instruction)\n\u001b[32m 129\u001b[39m \u001b[38;5;66;03m# Create the absolute instruction (per split)\u001b[39;00m\n\u001b[32m--> \u001b[39m\u001b[32m130\u001b[39m absolute_instructions = \u001b[43minstruction\u001b[49m\u001b[43m.\u001b[49m\u001b[43mto_absolute\u001b[49m\u001b[43m(\u001b[49m\u001b[43mname2len\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m 132\u001b[39m \u001b[38;5;66;03m# For each split, return the files instruction (skip/take)\u001b[39;00m\n\u001b[32m 133\u001b[39m file_instructions = []\n", "\u001b[36mFile \u001b[39m\u001b[32m/opt/conda/envs/antibody_datasets/lib/python3.13/site-packages/datasets/arrow_reader.py:620\u001b[39m, in \u001b[36mReadInstruction.to_absolute\u001b[39m\u001b[34m(self, name2len)\u001b[39m\n\u001b[32m 608\u001b[39m \u001b[38;5;28;01mdef\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34mto_absolute\u001b[39m(\u001b[38;5;28mself\u001b[39m, name2len):\n\u001b[32m 609\u001b[39m \u001b[38;5;250m \u001b[39m\u001b[33;03m\"\"\"Translate instruction into a list of absolute instructions.\u001b[39;00m\n\u001b[32m 610\u001b[39m \n\u001b[32m 611\u001b[39m \u001b[33;03m Those absolute instructions are then to be added together.\u001b[39;00m\n\u001b[32m (...)\u001b[39m\u001b[32m 618\u001b[39m \u001b[33;03m list of _AbsoluteInstruction instances (corresponds to the + in spec).\u001b[39;00m\n\u001b[32m 619\u001b[39m \u001b[33;03m \"\"\"\u001b[39;00m\n\u001b[32m--> \u001b[39m\u001b[32m620\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m [\u001b[43m_rel_to_abs_instr\u001b[49m\u001b[43m(\u001b[49m\u001b[43mrel_instr\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mname2len\u001b[49m\u001b[43m)\u001b[49m \u001b[38;5;28;01mfor\u001b[39;00m rel_instr \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m._relative_instructions]\n", "\u001b[36mFile \u001b[39m\u001b[32m/opt/conda/envs/antibody_datasets/lib/python3.13/site-packages/datasets/arrow_reader.py:437\u001b[39m, in \u001b[36m_rel_to_abs_instr\u001b[39m\u001b[34m(rel_instr, name2len)\u001b[39m\n\u001b[32m 435\u001b[39m split = rel_instr.splitname\n\u001b[32m 436\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m split \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m name2len:\n\u001b[32m--> \u001b[39m\u001b[32m437\u001b[39m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\u001b[33mf\u001b[39m\u001b[33m'\u001b[39m\u001b[33mUnknown split \u001b[39m\u001b[33m\"\u001b[39m\u001b[38;5;132;01m{\u001b[39;00msplit\u001b[38;5;132;01m}\u001b[39;00m\u001b[33m\"\u001b[39m\u001b[33m. Should be one of \u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;28mlist\u001b[39m(name2len)\u001b[38;5;132;01m}\u001b[39;00m\u001b[33m.\u001b[39m\u001b[33m'\u001b[39m)\n\u001b[32m 438\u001b[39m num_examples = name2len[split]\n\u001b[32m 439\u001b[39m from_ = rel_instr.from_\n", "\u001b[31mValueError\u001b[39m: Unknown split \"auto_submissions\". Should be one of ['train']." ] } ], "source": [ "# access results dataset\n", "res = load_dataset(\"ginkgo-datapoints/abdev-bench-results\", split=\"auto_submissions\")\n", "print(res)" ] }, { "cell_type": "code", "execution_count": 4, "id": "2b136f33", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
submission_idspearmantop_10_recalldatasetassaymodelusersubmission_time
0empty0.0000000.000000GDPa1emptyemptyanonymousNaN
108a9b21d-a06f-4c44-a2c2-2d7a03c558c30.1218060.125000GDPa1Tm2anonymoussubmissionsanonymoussubmissions2025-08-13T13:51:50.519786
208a9b21d-a06f-4c44-a2c2-2d7a03c558c30.1878770.083333GDPa1Titeranonymoussubmissionsanonymoussubmissions2025-08-13T13:51:50.519786
3134c9dfb-3b27-48ac-8f5d-c8663d8bebed0.1218060.125000GDPa1Tm2anonymoussubmissionsanonymoussubmissions2025-08-13T13:44:10.148599
4134c9dfb-3b27-48ac-8f5d-c8663d8bebed0.1878770.083333GDPa1Titeranonymoussubmissionsanonymoussubmissions2025-08-13T13:44:10.148599
53763ce44-0ec5-4eec-80a8-361b2bfe4ee00.1218060.125000GDPa1Tm2testtest2025-08-13T13:46:15.853105
63763ce44-0ec5-4eec-80a8-361b2bfe4ee00.1878770.083333GDPa1Titertesttest2025-08-13T13:46:15.853105
7378b4d52-4d96-40b6-b554-b8f5d8bc5fbd0.1218060.125000GDPa1Tm2testtest2025-08-07T19:10:24.934110
8378b4d52-4d96-40b6-b554-b8f5d8bc5fbd0.1878770.083333GDPa1Titertesttest2025-08-07T19:10:24.934110
956b4ab17-560e-474b-93f1-ff81fa14fb100.1218060.125000GDPa1Tm2testtest2025-08-12T17:49:22.380229
1056b4ab17-560e-474b-93f1-ff81fa14fb100.1878770.083333GDPa1Titertesttest2025-08-12T17:49:22.380229
117cdcae41-c32a-430a-8a39-be3f00fd315d0.1218060.125000GDPa1Tm2asdfasdfasdfasasdfasdfasdfas2025-08-12T17:53:35.204680
127cdcae41-c32a-430a-8a39-be3f00fd315d0.1878770.083333GDPa1Titerasdfasdfasdfasasdfasdfasdfas2025-08-12T17:53:35.204680
13afe237b4-97cf-4e81-a4c1-f4d6fa76aa040.1218060.125000GDPa1Tm2anonymoussubmissionsanonymoussubmissions2025-08-13T13:43:46.042660
14afe237b4-97cf-4e81-a4c1-f4d6fa76aa040.1878770.083333GDPa1Titeranonymoussubmissionsanonymoussubmissions2025-08-13T13:43:46.042660
15b84d6c6c-36d3-42d4-84ad-a91a3758199d0.1218060.125000GDPa1Tm2testtest2025-08-13T13:41:41.024660
16b84d6c6c-36d3-42d4-84ad-a91a3758199d0.1878770.083333GDPa1Titertesttest2025-08-13T13:41:41.024660
17d2804c50-33a8-4465-8e27-20762adda13e0.3585220.208333GDPa1HICnotmyusername_testnotmyusername_test2025-07-24T20:56:08.953098
18d2804c50-33a8-4465-8e27-20762adda13e0.3585220.208333GDPa1HICnotmyusername_testnotmyusername_test2025-07-24T20:56:08.953098
19d82e3ef6-e54c-4854-b8b7-bee28f04791e0.1218060.125000GDPa1Tm2testtest2025-08-12T17:47:17.935587
20d82e3ef6-e54c-4854-b8b7-bee28f04791e0.1878770.083333GDPa1Titertesttest2025-08-12T17:47:17.935587
21fa4d1c11-770d-40a8-b846-12e219b4b87a0.1218060.125000GDPa1Tm2testtest2025-08-12T17:49:20.145092
22fa4d1c11-770d-40a8-b846-12e219b4b87a0.1878770.083333GDPa1Titertesttest2025-08-12T17:49:20.145092
\n", "
" ], "text/plain": [ " submission_id spearman top_10_recall dataset \\\n", "0 empty 0.000000 0.000000 GDPa1 \n", "1 08a9b21d-a06f-4c44-a2c2-2d7a03c558c3 0.121806 0.125000 GDPa1 \n", "2 08a9b21d-a06f-4c44-a2c2-2d7a03c558c3 0.187877 0.083333 GDPa1 \n", "3 134c9dfb-3b27-48ac-8f5d-c8663d8bebed 0.121806 0.125000 GDPa1 \n", "4 134c9dfb-3b27-48ac-8f5d-c8663d8bebed 0.187877 0.083333 GDPa1 \n", "5 3763ce44-0ec5-4eec-80a8-361b2bfe4ee0 0.121806 0.125000 GDPa1 \n", "6 3763ce44-0ec5-4eec-80a8-361b2bfe4ee0 0.187877 0.083333 GDPa1 \n", "7 378b4d52-4d96-40b6-b554-b8f5d8bc5fbd 0.121806 0.125000 GDPa1 \n", "8 378b4d52-4d96-40b6-b554-b8f5d8bc5fbd 0.187877 0.083333 GDPa1 \n", "9 56b4ab17-560e-474b-93f1-ff81fa14fb10 0.121806 0.125000 GDPa1 \n", "10 56b4ab17-560e-474b-93f1-ff81fa14fb10 0.187877 0.083333 GDPa1 \n", "11 7cdcae41-c32a-430a-8a39-be3f00fd315d 0.121806 0.125000 GDPa1 \n", "12 7cdcae41-c32a-430a-8a39-be3f00fd315d 0.187877 0.083333 GDPa1 \n", "13 afe237b4-97cf-4e81-a4c1-f4d6fa76aa04 0.121806 0.125000 GDPa1 \n", "14 afe237b4-97cf-4e81-a4c1-f4d6fa76aa04 0.187877 0.083333 GDPa1 \n", "15 b84d6c6c-36d3-42d4-84ad-a91a3758199d 0.121806 0.125000 GDPa1 \n", "16 b84d6c6c-36d3-42d4-84ad-a91a3758199d 0.187877 0.083333 GDPa1 \n", "17 d2804c50-33a8-4465-8e27-20762adda13e 0.358522 0.208333 GDPa1 \n", "18 d2804c50-33a8-4465-8e27-20762adda13e 0.358522 0.208333 GDPa1 \n", "19 d82e3ef6-e54c-4854-b8b7-bee28f04791e 0.121806 0.125000 GDPa1 \n", "20 d82e3ef6-e54c-4854-b8b7-bee28f04791e 0.187877 0.083333 GDPa1 \n", "21 fa4d1c11-770d-40a8-b846-12e219b4b87a 0.121806 0.125000 GDPa1 \n", "22 fa4d1c11-770d-40a8-b846-12e219b4b87a 0.187877 0.083333 GDPa1 \n", "\n", " assay model user \\\n", "0 empty empty anonymous \n", "1 Tm2 anonymoussubmissions anonymoussubmissions \n", "2 Titer anonymoussubmissions anonymoussubmissions \n", "3 Tm2 anonymoussubmissions anonymoussubmissions \n", "4 Titer anonymoussubmissions anonymoussubmissions \n", "5 Tm2 test test \n", "6 Titer test test \n", "7 Tm2 test test \n", "8 Titer test test \n", "9 Tm2 test test \n", "10 Titer test test \n", "11 Tm2 asdfasdfasdfas asdfasdfasdfas \n", "12 Titer asdfasdfasdfas asdfasdfasdfas \n", "13 Tm2 anonymoussubmissions anonymoussubmissions \n", "14 Titer anonymoussubmissions anonymoussubmissions \n", "15 Tm2 test test \n", "16 Titer test test \n", "17 HIC notmyusername_test notmyusername_test \n", "18 HIC notmyusername_test notmyusername_test \n", "19 Tm2 test test \n", "20 Titer test test \n", "21 Tm2 test test \n", "22 Titer test test \n", "\n", " submission_time \n", "0 NaN \n", "1 2025-08-13T13:51:50.519786 \n", "2 2025-08-13T13:51:50.519786 \n", "3 2025-08-13T13:44:10.148599 \n", "4 2025-08-13T13:44:10.148599 \n", "5 2025-08-13T13:46:15.853105 \n", "6 2025-08-13T13:46:15.853105 \n", "7 2025-08-07T19:10:24.934110 \n", "8 2025-08-07T19:10:24.934110 \n", "9 2025-08-12T17:49:22.380229 \n", "10 2025-08-12T17:49:22.380229 \n", "11 2025-08-12T17:53:35.204680 \n", "12 2025-08-12T17:53:35.204680 \n", "13 2025-08-13T13:43:46.042660 \n", "14 2025-08-13T13:43:46.042660 \n", "15 2025-08-13T13:41:41.024660 \n", "16 2025-08-13T13:41:41.024660 \n", "17 2025-07-24T20:56:08.953098 \n", "18 2025-07-24T20:56:08.953098 \n", "19 2025-08-12T17:47:17.935587 \n", "20 2025-08-12T17:47:17.935587 \n", "21 2025-08-12T17:49:20.145092 \n", "22 2025-08-12T17:49:20.145092 " ] }, "execution_count": 4, "metadata": {}, "output_type": "execute_result" } ], "source": [ "pd.read_csv(\"hf://datasets/ginkgo-datapoints/abdev-bench-results/auto_submissions/metrics_all.csv\")" ] }, { "cell_type": "code", "execution_count": null, "id": "6c7e0ad6", "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "antibody_datasets", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.13.3" } }, "nbformat": 4, "nbformat_minor": 5 }