{
  "acquisition": {
    "acquired_at": "2026-06-27T23:51:25+00:00",
    "agent_id": "Claude-extra",
    "dedupe_fingerprint": "ab11c63c925be1e7248b74d024f8fef0357874bf",
    "source_dataset_id": "flights",
    "source_dataset_name": "Monthly airline passengers",
    "source_platform": "seaborn",
    "source_rows": 144,
    "source_target_column_original": "passengers",
    "source_url": "https://github.com/mwaskom/seaborn-data/blob/master/flights.csv",
    "staged_rows": 144,
    "staging_path": "/home/ubuntu/hyper/data/tabular/real_regression_sources/seaborn-flights-passengers.csv",
    "tool": "models.tools.acquire_regression_extra_sources"
  },
  "counts": {
    "dropped_feature_count": 0,
    "n_features": 2,
    "original_columns": 3,
    "original_rows": 144,
    "rows_after_target_cleanup": 144,
    "selected_rows": 144,
    "strata_count": 49,
    "test_rows": 24,
    "train_rows": 120
  },
  "created_at": "2026-06-27T23:51:25+00:00",
  "dataset_hash": "019de5d76a718163",
  "dedupe_fingerprint": "ab11c63c925be1e7248b74d024f8fef0357874bf",
  "dropped_feature_columns": [],
  "feature_columns": [
    "year",
    "month"
  ],
  "feature_encodings": {
    "month": {
      "impute_value": 5.5,
      "kind": "numeric"
    },
    "year": {
      "impute_value": 1954.5,
      "kind": "numeric"
    }
  },
  "feature_scaling": {
    "constant_columns": [],
    "max": [
      1960.0,
      11.0
    ],
    "method": "minmax over cleaned source rows before sampling",
    "min": [
      1949.0,
      0.0
    ],
    "range": [
      0.0,
      1.0
    ]
  },
  "hash_algorithm": "sha256:first16",
  "headers_removed_from_csv": true,
  "n_features": 2,
  "origin": "real",
  "original_headers": [
    "year",
    "month",
    "target"
  ],
  "output_headers": [
    "year",
    "month",
    "target"
  ],
  "retrieved_at": "2026-06-27T23:51:22+00:00",
  "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": 11059930,
    "source_read_max_rows": null,
    "test_target_rows": 1000,
    "train_target_rows": 1000
  },
  "sha256": "019de5d76a718163babc29e512211b9f419b6657f0e9074a585c19f23d7d95f0",
  "source_dataset_id": "flights",
  "source_dataset_name": "Monthly airline passengers",
  "source_family": "monthly-airline",
  "source_file": "seaborn-flights-passengers.csv",
  "source_license": "CC0 (seaborn-data)",
  "source_modified_at": "2026-06-27T23:51:25+00:00",
  "source_path": "/home/ubuntu/hyper/data/tabular/real_regression_sources/seaborn-flights-passengers.csv",
  "source_platform": "seaborn",
  "source_real_data": true,
  "source_resource_id": null,
  "source_rows": 144,
  "source_size_bytes": 2490,
  "source_target_column_original": "passengers",
  "source_url": "https://github.com/mwaskom/seaborn-data/blob/master/flights.csv",
  "staged_rows": 144,
  "staging_path": "/home/ubuntu/hyper/data/tabular/real_regression_sources/seaborn-flights-passengers.csv",
  "target_column": "target",
  "target_generation": "original_numeric_column",
  "target_is_final_column": true,
  "target_names": [
    "target"
  ],
  "target_scaling": {
    "max": 622.0,
    "min": 104.0,
    "mode": "regression",
    "range": [
      0.0,
      1.0
    ]
  },
  "target_source_encoding": {
    "kind": "numeric"
  },
  "task_type": "regression",
  "test_rows": 24,
  "train_rows": 120
}