{
  "acquisition": {
    "acquired_at": "2026-06-26T08:55:29+00:00",
    "fetched_feature_columns": 8,
    "fetched_rows": 782,
    "openml_data_id": 839,
    "openml_name": "kdd_el_nino-small",
    "openml_url": "https://www.openml.org/d/839",
    "row_policy": "kept_all",
    "source": "openml",
    "source_rows_after_target_cleanup": 782,
    "stage_path": "/home/ubuntu/hyper/data/tabular/kdd-el-nino-small.csv",
    "staged_feature_columns": 8,
    "staged_rows": 782,
    "tool": "models.tools.acquire_real_binary_datasets"
  },
  "counts": {
    "dropped_feature_count": 0,
    "n_features": 8,
    "original_columns": 9,
    "original_rows": 782,
    "rows_after_target_cleanup": 782,
    "selected_rows": 782,
    "strata_count": 51,
    "test_rows": 131,
    "train_rows": 651
  },
  "created_at": "2026-06-26T08:55:29+00:00",
  "dataset_hash": "c54974b740a392a3",
  "dropped_feature_columns": [],
  "feature_columns": [
    "buoy",
    "day",
    "latitude",
    "longitude",
    "zon_winds",
    "mer_winds",
    "humidity",
    "air_temp"
  ],
  "feature_encodings": {
    "air_temp": {
      "impute_value": 27.89,
      "kind": "numeric"
    },
    "buoy": {
      "impute_value": 31.0,
      "kind": "numeric"
    },
    "day": {
      "impute_value": 7.0,
      "kind": "numeric"
    },
    "humidity": {
      "impute_value": 84.1,
      "kind": "numeric"
    },
    "latitude": {
      "impute_value": 0.0,
      "kind": "numeric"
    },
    "longitude": {
      "impute_value": -124.89,
      "kind": "numeric"
    },
    "mer_winds": {
      "impute_value": -0.9,
      "kind": "numeric"
    },
    "zon_winds": {
      "impute_value": -4.2,
      "kind": "numeric"
    }
  },
  "feature_scaling": {
    "constant_columns": [],
    "max": [
      59.0,
      14.0,
      8.97,
      179.8,
      7.0,
      7.1,
      99.4,
      30.04
    ],
    "method": "minmax over cleaned source rows before sampling",
    "min": [
      1.0,
      1.0,
      -8.28,
      -179.97,
      -8.9,
      -6.4,
      27.58,
      22.72
    ],
    "range": [
      0.0,
      1.0
    ]
  },
  "hash_algorithm": "sha256:first16",
  "headers_removed_from_csv": true,
  "n_features": 8,
  "origin": "real",
  "original_headers": [
    "buoy",
    "day",
    "latitude",
    "longitude",
    "zon_winds",
    "mer_winds",
    "humidity",
    "air_temp",
    "target"
  ],
  "output_headers": [
    "buoy",
    "day",
    "latitude",
    "longitude",
    "zon_winds",
    "mer_winds",
    "humidity",
    "air_temp",
    "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": 3296482234,
    "source_read_max_rows": null,
    "test_target_rows": 1000,
    "train_target_rows": 1000
  },
  "sha256": "c54974b740a392a3672c6d0913cbdab7c7ef5e247a089782e367659598f5a2a9",
  "source": "openml",
  "source_file": "kdd-el-nino-small.csv",
  "source_modified_at": "2026-06-26T08:55:29+00:00",
  "source_openml_data_id": 839,
  "source_openml_name": "kdd_el_nino-small",
  "source_path": "/home/ubuntu/hyper/data/tabular/kdd-el-nino-small.csv",
  "source_real_data": true,
  "source_size_bytes": 34511,
  "source_url": "https://www.openml.org/d/839",
  "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": 131,
  "train_rows": 651
}