{
  "acquisition": {
    "acquired_at": "2026-06-26T09:05:23+00:00",
    "fetched_feature_columns": 10,
    "fetched_rows": 583,
    "openml_data_id": 41945,
    "openml_name": "ilpd-numeric",
    "openml_url": "https://www.openml.org/d/41945",
    "row_policy": "kept_all",
    "source": "openml",
    "source_rows_after_target_cleanup": 583,
    "stage_path": "/home/ubuntu/hyper/data/tabular/ilpd-numeric.csv",
    "staged_feature_columns": 10,
    "staged_rows": 583,
    "tool": "models.tools.acquire_real_binary_datasets"
  },
  "counts": {
    "dropped_feature_count": 0,
    "n_features": 10,
    "original_columns": 11,
    "original_rows": 583,
    "rows_after_target_cleanup": 583,
    "selected_rows": 583,
    "strata_count": 64,
    "test_rows": 98,
    "train_rows": 485
  },
  "created_at": "2026-06-26T09:05:23+00:00",
  "dataset_hash": "962a35a53b0803a8",
  "dropped_feature_columns": [],
  "feature_columns": [
    "V1",
    "V2",
    "V3",
    "V4",
    "V5",
    "V6",
    "V7",
    "V8",
    "V9",
    "V10"
  ],
  "feature_encodings": {
    "V1": {
      "impute_value": 45.0,
      "kind": "numeric"
    },
    "V10": {
      "impute_value": 0.947064,
      "kind": "numeric"
    },
    "V2": {
      "impute_value": 1.0,
      "kind": "numeric"
    },
    "V3": {
      "impute_value": 1.0,
      "kind": "numeric"
    },
    "V4": {
      "impute_value": 0.3,
      "kind": "numeric"
    },
    "V5": {
      "impute_value": 208.0,
      "kind": "numeric"
    },
    "V6": {
      "impute_value": 35.0,
      "kind": "numeric"
    },
    "V7": {
      "impute_value": 42.0,
      "kind": "numeric"
    },
    "V8": {
      "impute_value": 6.6,
      "kind": "numeric"
    },
    "V9": {
      "impute_value": 3.1,
      "kind": "numeric"
    }
  },
  "feature_scaling": {
    "constant_columns": [],
    "max": [
      90.0,
      1.0,
      75.0,
      19.7,
      2110.0,
      2000.0,
      4929.0,
      9.6,
      5.5,
      2.8
    ],
    "method": "minmax over cleaned source rows before sampling",
    "min": [
      4.0,
      0.0,
      0.4,
      0.1,
      63.0,
      10.0,
      10.0,
      2.7,
      0.9,
      0.3
    ],
    "range": [
      0.0,
      1.0
    ]
  },
  "hash_algorithm": "sha256:first16",
  "headers_removed_from_csv": true,
  "n_features": 10,
  "origin": "real",
  "original_headers": [
    "V1",
    "V2",
    "V3",
    "V4",
    "V5",
    "V6",
    "V7",
    "V8",
    "V9",
    "V10",
    "target"
  ],
  "output_headers": [
    "V1",
    "V2",
    "V3",
    "V4",
    "V5",
    "V6",
    "V7",
    "V8",
    "V9",
    "V10",
    "target"
  ],
  "sampling": {
    "final_max_rows": 2000,
    "method": "quota stratified by target distribution plus high-variance feature quantile bins",
    "minimum_final_rows": 101,
    "minimum_test_to_train_ratio_when_small": 0.2,
    "seed": 2535396008,
    "source_read_max_rows": null,
    "test_target_rows": 1000,
    "train_target_rows": 1000
  },
  "sha256": "962a35a53b0803a8095e26558454e90d4b950af21055195c86b46d71f63f3e13",
  "source": "openml",
  "source_file": "ilpd-numeric.csv",
  "source_modified_at": "2026-06-26T09:05:23+00:00",
  "source_openml_data_id": 41945,
  "source_openml_name": "ilpd-numeric",
  "source_path": "/home/ubuntu/hyper/data/tabular/ilpd-numeric.csv",
  "source_real_data": true,
  "source_size_bytes": 28985,
  "source_url": "https://www.openml.org/d/41945",
  "target_column": "target",
  "target_is_final_column": true,
  "target_names": [
    "target"
  ],
  "target_scaling": {
    "class_to_code": {
      "1.0": 0,
      "2.0": 1
    },
    "classes": [
      1.0,
      2.0
    ],
    "mode": "classification",
    "n_classes": 2,
    "range": [
      0.0,
      1.0
    ],
    "scaled_code_formula": "code / max(1, n_classes - 1)"
  },
  "target_source_encoding": {
    "kind": "numeric"
  },
  "task_type": "binary",
  "test_rows": 98,
  "train_rows": 485
}