{
  "acquisition": {
    "acquired_at": "2026-06-26T09:10:42+00:00",
    "fetched_feature_columns": 7,
    "fetched_rows": 379,
    "openml_data_id": 1008,
    "openml_name": "analcatdata_reviewer",
    "openml_url": "https://www.openml.org/d/1008",
    "row_policy": "kept_all",
    "source": "openml",
    "source_rows_after_target_cleanup": 379,
    "stage_path": "/home/ubuntu/hyper/data/tabular/analcatdata-reviewer.csv",
    "staged_feature_columns": 6,
    "staged_rows": 379,
    "tool": "models.tools.acquire_real_binary_datasets"
  },
  "counts": {
    "dropped_feature_count": 0,
    "n_features": 6,
    "original_columns": 7,
    "original_rows": 379,
    "rows_after_target_cleanup": 379,
    "selected_rows": 379,
    "strata_count": 59,
    "test_rows": 64,
    "train_rows": 315
  },
  "created_at": "2026-06-26T09:10:42+00:00",
  "dataset_hash": "131bfb9d9a06f343",
  "dropped_feature_columns": [],
  "feature_columns": [
    "Roger_Ebert",
    "Jeffrey_Lyons",
    "Michael_Medved",
    "Rex_Reed",
    "Joel_Siegel",
    "Gene_Siskel"
  ],
  "feature_encodings": {
    "Gene_Siskel": {
      "impute_value": 3.0,
      "kind": "categorical_codes",
      "mapping": {
        "0.0": 0,
        "1.0": 1,
        "2.0": 2,
        "__MISSING__": 3
      }
    },
    "Jeffrey_Lyons": {
      "impute_value": 2.0,
      "kind": "numeric"
    },
    "Joel_Siegel": {
      "impute_value": 3.0,
      "kind": "categorical_codes",
      "mapping": {
        "0.0": 0,
        "1.0": 1,
        "2.0": 2,
        "__MISSING__": 3
      }
    },
    "Michael_Medved": {
      "impute_value": 3.0,
      "kind": "categorical_codes",
      "mapping": {
        "0.0": 0,
        "1.0": 1,
        "2.0": 2,
        "__MISSING__": 3
      }
    },
    "Rex_Reed": {
      "impute_value": 1.0,
      "kind": "numeric"
    },
    "Roger_Ebert": {
      "impute_value": 2.0,
      "kind": "numeric"
    }
  },
  "feature_scaling": {
    "constant_columns": [],
    "max": [
      2.0,
      2.0,
      3.0,
      2.0,
      3.0,
      3.0
    ],
    "method": "minmax over cleaned source rows before sampling",
    "min": [
      0.0,
      0.0,
      0.0,
      0.0,
      0.0,
      0.0
    ],
    "range": [
      0.0,
      1.0
    ]
  },
  "hash_algorithm": "sha256:first16",
  "headers_removed_from_csv": true,
  "n_features": 6,
  "origin": "real",
  "original_headers": [
    "Roger_Ebert",
    "Jeffrey_Lyons",
    "Michael_Medved",
    "Rex_Reed",
    "Joel_Siegel",
    "Gene_Siskel",
    "target"
  ],
  "output_headers": [
    "Roger_Ebert",
    "Jeffrey_Lyons",
    "Michael_Medved",
    "Rex_Reed",
    "Joel_Siegel",
    "Gene_Siskel",
    "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": 305061008,
    "source_read_max_rows": null,
    "test_target_rows": 1000,
    "train_target_rows": 1000
  },
  "sha256": "131bfb9d9a06f343db1fd4983c45e6c787693f136210b9b2b7e5d4f0c75d558f",
  "source": "openml",
  "source_file": "analcatdata-reviewer.csv",
  "source_modified_at": "2026-06-26T09:10:42+00:00",
  "source_openml_data_id": 1008,
  "source_openml_name": "analcatdata_reviewer",
  "source_path": "/home/ubuntu/hyper/data/tabular/analcatdata-reviewer.csv",
  "source_real_data": true,
  "source_size_bytes": 7543,
  "source_url": "https://www.openml.org/d/1008",
  "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": 64,
  "train_rows": 315
}