{
  "acquisition": {
    "acquired_at": "2026-06-26T09:52:31+00:00",
    "fetched_feature_columns": 20,
    "fetched_rows": 1000,
    "openml_data_id": 46532,
    "openml_name": "dataset_credit-g",
    "openml_url": "https://www.openml.org/d/46532",
    "row_policy": "kept_all",
    "source": "openml",
    "source_rows_after_target_cleanup": 1000,
    "stage_path": "/home/ubuntu/hyper/data/tabular/dataset-credit-g.csv",
    "staged_feature_columns": 20,
    "staged_rows": 1000,
    "tool": "models.tools.acquire_real_binary_datasets"
  },
  "counts": {
    "dropped_feature_count": 0,
    "n_features": 20,
    "original_columns": 21,
    "original_rows": 1000,
    "rows_after_target_cleanup": 1000,
    "selected_rows": 1000,
    "strata_count": 59,
    "test_rows": 167,
    "train_rows": 833
  },
  "created_at": "2026-06-26T09:52:31+00:00",
  "dataset_hash": "1b46745dbbcf9494",
  "dropped_feature_columns": [],
  "feature_columns": [
    "checking_status",
    "duration",
    "credit_history",
    "purpose",
    "credit_amount",
    "savings_status",
    "employment",
    "installment_commitment",
    "personal_status",
    "other_parties",
    "residence_since",
    "property_magnitude",
    "age",
    "other_payment_plans",
    "housing",
    "existing_credits",
    "job",
    "num_dependents",
    "own_telephone",
    "foreign_worker"
  ],
  "feature_encodings": {
    "age": {
      "impute_value": 33.0,
      "kind": "numeric"
    },
    "checking_status": {
      "impute_value": 1.0,
      "kind": "numeric"
    },
    "credit_amount": {
      "impute_value": 2319.5,
      "kind": "numeric"
    },
    "credit_history": {
      "impute_value": 3.0,
      "kind": "numeric"
    },
    "duration": {
      "impute_value": 18.0,
      "kind": "numeric"
    },
    "employment": {
      "impute_value": 1.0,
      "kind": "numeric"
    },
    "existing_credits": {
      "impute_value": 1.0,
      "kind": "numeric"
    },
    "foreign_worker": {
      "impute_value": 1.0,
      "kind": "numeric"
    },
    "housing": {
      "impute_value": 1.0,
      "kind": "numeric"
    },
    "installment_commitment": {
      "impute_value": 3.0,
      "kind": "numeric"
    },
    "job": {
      "impute_value": 1.0,
      "kind": "numeric"
    },
    "num_dependents": {
      "impute_value": 1.0,
      "kind": "numeric"
    },
    "other_parties": {
      "impute_value": 2.0,
      "kind": "numeric"
    },
    "other_payment_plans": {
      "impute_value": 1.0,
      "kind": "numeric"
    },
    "own_telephone": {
      "impute_value": 0.0,
      "kind": "numeric"
    },
    "personal_status": {
      "impute_value": 3.0,
      "kind": "numeric"
    },
    "property_magnitude": {
      "impute_value": 1.0,
      "kind": "numeric"
    },
    "purpose": {
      "impute_value": 4.0,
      "kind": "numeric"
    },
    "residence_since": {
      "impute_value": 3.0,
      "kind": "numeric"
    },
    "savings_status": {
      "impute_value": 2.0,
      "kind": "numeric"
    }
  },
  "feature_scaling": {
    "constant_columns": [],
    "max": [
      3.0,
      72.0,
      4.0,
      9.0,
      18424.0,
      4.0,
      4.0,
      4.0,
      3.0,
      2.0,
      4.0,
      3.0,
      75.0,
      2.0,
      2.0,
      4.0,
      3.0,
      2.0,
      1.0,
      1.0
    ],
    "method": "minmax over cleaned source rows before sampling",
    "min": [
      0.0,
      4.0,
      0.0,
      0.0,
      250.0,
      0.0,
      0.0,
      1.0,
      0.0,
      0.0,
      1.0,
      0.0,
      19.0,
      0.0,
      0.0,
      1.0,
      0.0,
      1.0,
      0.0,
      0.0
    ],
    "range": [
      0.0,
      1.0
    ]
  },
  "hash_algorithm": "sha256:first16",
  "headers_removed_from_csv": true,
  "n_features": 20,
  "origin": "real",
  "original_headers": [
    "checking_status",
    "duration",
    "credit_history",
    "purpose",
    "credit_amount",
    "savings_status",
    "employment",
    "installment_commitment",
    "personal_status",
    "other_parties",
    "residence_since",
    "property_magnitude",
    "age",
    "other_payment_plans",
    "housing",
    "existing_credits",
    "job",
    "num_dependents",
    "own_telephone",
    "foreign_worker",
    "target"
  ],
  "output_headers": [
    "checking_status",
    "duration",
    "credit_history",
    "purpose",
    "credit_amount",
    "savings_status",
    "employment",
    "installment_commitment",
    "personal_status",
    "other_parties",
    "residence_since",
    "property_magnitude",
    "age",
    "other_payment_plans",
    "housing",
    "existing_credits",
    "job",
    "num_dependents",
    "own_telephone",
    "foreign_worker",
    "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": 443765584,
    "source_read_max_rows": null,
    "test_target_rows": 1000,
    "train_target_rows": 1000
  },
  "sha256": "1b46745dbbcf9494d36b9eeabe0b84b5fb96778120df78e90263d4d60a64481a",
  "source": "openml",
  "source_file": "dataset-credit-g.csv",
  "source_modified_at": "2026-06-26T09:52:31+00:00",
  "source_openml_data_id": 46532,
  "source_openml_name": "dataset_credit-g",
  "source_path": "/home/ubuntu/hyper/data/tabular/dataset-credit-g.csv",
  "source_real_data": true,
  "source_size_bytes": 89061,
  "source_url": "https://www.openml.org/d/46532",
  "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": 167,
  "train_rows": 833
}