{
  "acquisition": {
    "acquired_at": "2026-06-26T09:01:25+00:00",
    "fetched_feature_columns": 25,
    "fetched_rows": 205,
    "openml_data_id": 840,
    "openml_name": "autoHorse",
    "openml_url": "https://www.openml.org/d/840",
    "row_policy": "kept_all",
    "source": "openml",
    "source_rows_after_target_cleanup": 205,
    "stage_path": "/home/ubuntu/hyper/data/tabular/autohorse.csv",
    "staged_feature_columns": 25,
    "staged_rows": 205,
    "tool": "models.tools.acquire_real_binary_datasets"
  },
  "counts": {
    "dropped_feature_count": 0,
    "n_features": 25,
    "original_columns": 26,
    "original_rows": 205,
    "rows_after_target_cleanup": 205,
    "selected_rows": 205,
    "strata_count": 15,
    "test_rows": 35,
    "train_rows": 170
  },
  "created_at": "2026-06-26T09:01:25+00:00",
  "dataset_hash": "09c82f5b5cf9016d",
  "dropped_feature_columns": [],
  "feature_columns": [
    "symboling",
    "normalized-losses",
    "make",
    "fuel-type",
    "aspiration",
    "num-of-doors",
    "body-style",
    "drive-wheels",
    "engine-location",
    "wheel-base",
    "length",
    "width",
    "height",
    "curb-weight",
    "engine-type",
    "num-of-cylinders",
    "engine-size",
    "fuel-system",
    "bore",
    "stroke",
    "compression-ratio",
    "peak-rpm",
    "city-mpg",
    "highway-mpg",
    "price"
  ],
  "feature_encodings": {
    "aspiration": {
      "impute_value": 0.0,
      "kind": "numeric"
    },
    "body-style": {
      "impute_value": 2.0,
      "kind": "numeric"
    },
    "bore": {
      "impute_value": 3.31,
      "kind": "numeric"
    },
    "city-mpg": {
      "impute_value": 24.0,
      "kind": "numeric"
    },
    "compression-ratio": {
      "impute_value": 9.0,
      "kind": "numeric"
    },
    "curb-weight": {
      "impute_value": 2414.0,
      "kind": "numeric"
    },
    "drive-wheels": {
      "impute_value": 1.0,
      "kind": "numeric"
    },
    "engine-location": {
      "impute_value": 0.0,
      "kind": "numeric"
    },
    "engine-size": {
      "impute_value": 120.0,
      "kind": "numeric"
    },
    "engine-type": {
      "impute_value": 2.0,
      "kind": "numeric"
    },
    "fuel-system": {
      "impute_value": 1.0,
      "kind": "numeric"
    },
    "fuel-type": {
      "impute_value": 0.0,
      "kind": "numeric"
    },
    "height": {
      "impute_value": 54.1,
      "kind": "numeric"
    },
    "highway-mpg": {
      "impute_value": 30.0,
      "kind": "numeric"
    },
    "length": {
      "impute_value": 173.2,
      "kind": "numeric"
    },
    "make": {
      "impute_value": 12.0,
      "kind": "numeric"
    },
    "normalized-losses": {
      "impute_value": 115.0,
      "kind": "numeric"
    },
    "num-of-cylinders": {
      "impute_value": 4.0,
      "kind": "numeric"
    },
    "num-of-doors": {
      "impute_value": 4.0,
      "kind": "numeric"
    },
    "peak-rpm": {
      "impute_value": 5200.0,
      "kind": "numeric"
    },
    "price": {
      "impute_value": 10295.0,
      "kind": "numeric"
    },
    "stroke": {
      "impute_value": 3.29,
      "kind": "numeric"
    },
    "symboling": {
      "impute_value": 1.0,
      "kind": "numeric"
    },
    "wheel-base": {
      "impute_value": 97.0,
      "kind": "numeric"
    },
    "width": {
      "impute_value": 65.5,
      "kind": "numeric"
    }
  },
  "feature_scaling": {
    "constant_columns": [],
    "max": [
      3.0,
      256.0,
      21.0,
      1.0,
      1.0,
      4.0,
      4.0,
      2.0,
      1.0,
      120.9,
      208.1,
      72.3,
      59.8,
      4066.0,
      6.0,
      12.0,
      326.0,
      7.0,
      3.94,
      4.17,
      23.0,
      6600.0,
      49.0,
      54.0,
      45400.0
    ],
    "method": "minmax over cleaned source rows before sampling",
    "min": [
      -2.0,
      65.0,
      0.0,
      0.0,
      0.0,
      2.0,
      0.0,
      0.0,
      0.0,
      86.6,
      141.1,
      60.3,
      47.8,
      1488.0,
      0.0,
      2.0,
      61.0,
      0.0,
      2.54,
      2.07,
      7.0,
      4150.0,
      13.0,
      16.0,
      5118.0
    ],
    "range": [
      0.0,
      1.0
    ]
  },
  "hash_algorithm": "sha256:first16",
  "headers_removed_from_csv": true,
  "n_features": 25,
  "origin": "real",
  "original_headers": [
    "symboling",
    "normalized-losses",
    "make",
    "fuel-type",
    "aspiration",
    "num-of-doors",
    "body-style",
    "drive-wheels",
    "engine-location",
    "wheel-base",
    "length",
    "width",
    "height",
    "curb-weight",
    "engine-type",
    "num-of-cylinders",
    "engine-size",
    "fuel-system",
    "bore",
    "stroke",
    "compression-ratio",
    "peak-rpm",
    "city-mpg",
    "highway-mpg",
    "price",
    "target"
  ],
  "output_headers": [
    "symboling",
    "normalized-losses",
    "make",
    "fuel-type",
    "aspiration",
    "num-of-doors",
    "body-style",
    "drive-wheels",
    "engine-location",
    "wheel-base",
    "length",
    "width",
    "height",
    "curb-weight",
    "engine-type",
    "num-of-cylinders",
    "engine-size",
    "fuel-system",
    "bore",
    "stroke",
    "compression-ratio",
    "peak-rpm",
    "city-mpg",
    "highway-mpg",
    "price",
    "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": 150800470,
    "source_read_max_rows": null,
    "test_target_rows": 1000,
    "train_target_rows": 1000
  },
  "sha256": "09c82f5b5cf9016d45bc61dd7b89029db23adb07e9013d0dc48cdc8f234e4fff",
  "source": "openml",
  "source_file": "autohorse.csv",
  "source_modified_at": "2026-06-26T09:01:25+00:00",
  "source_openml_data_id": 840,
  "source_openml_name": "autoHorse",
  "source_path": "/home/ubuntu/hyper/data/tabular/autohorse.csv",
  "source_real_data": true,
  "source_size_bytes": 26014,
  "source_url": "https://www.openml.org/d/840",
  "target_column": "target",
  "target_is_final_column": true,
  "target_names": [
    "target"
  ],
  "target_scaling": {
    "class_to_code": {
      "0.0": 0,
      "1.0": 1
    },
    "classes": [
      0.0,
      1.0
    ],
    "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": 35,
  "train_rows": 170
}