{
  "acquisition": {
    "acquired_at": "2026-06-27T23:56:51+00:00",
    "agent_id": "Claude-extra",
    "dedupe_fingerprint": "864906f9bfef55dd9a8afb71450b9e984f34163b",
    "source_dataset_id": "stevedata/chile88",
    "source_dataset_name": "Voting Intentions in the 1988 Chilean Plebiscite",
    "source_platform": "rdatasets",
    "source_rows": 2700,
    "source_target_column_original": "sq",
    "source_url": "https://vincentarelbundock.github.io/Rdatasets/csv/stevedata/chile88.csv",
    "staged_rows": 1999,
    "staging_path": "/home/ubuntu/hyper/data/tabular/real_regression_sources/rdatasets-stevedata-chile88-sq.csv",
    "tool": "models.tools.acquire_regression_extra_sources"
  },
  "counts": {
    "dropped_feature_count": 0,
    "n_features": 7,
    "original_columns": 8,
    "original_rows": 1999,
    "rows_after_target_cleanup": 1999,
    "selected_rows": 1999,
    "strata_count": 178,
    "test_rows": 999,
    "train_rows": 1000
  },
  "created_at": "2026-06-27T23:56:51+00:00",
  "dataset_hash": "c7d815714ca52bce",
  "dedupe_fingerprint": "864906f9bfef55dd9a8afb71450b9e984f34163b",
  "downsampling": {
    "anchors_kept": 14,
    "corr_frob": 0.183653,
    "ks_features_mean": 0.021238,
    "ks_target": 0.009322,
    "method": "hybrid_coreset",
    "minmax_features_preserved": true,
    "minmax_target_preserved": true,
    "n_bins": 50,
    "original_rows": 2683,
    "selected_rows": 1999
  },
  "dropped_feature_columns": [],
  "feature_columns": [
    "region",
    "pop",
    "sex",
    "age",
    "educ",
    "income",
    "vote"
  ],
  "feature_encodings": {
    "age": {
      "impute_value": 37.0,
      "kind": "numeric"
    },
    "educ": {
      "impute_value": 1.0,
      "kind": "numeric"
    },
    "income": {
      "impute_value": 15000.0,
      "kind": "numeric"
    },
    "pop": {
      "impute_value": 175000.0,
      "kind": "numeric"
    },
    "region": {
      "impute_value": 3.0,
      "kind": "numeric"
    },
    "sex": {
      "impute_value": 1.0,
      "kind": "numeric"
    },
    "vote": {
      "impute_value": 2.0,
      "kind": "numeric"
    }
  },
  "feature_scaling": {
    "constant_columns": [],
    "max": [
      4.0,
      250000.0,
      1.0,
      70.0,
      2.0,
      200000.0,
      3.0
    ],
    "method": "minmax over cleaned source rows before sampling",
    "min": [
      0.0,
      3750.0,
      0.0,
      18.0,
      0.0,
      2500.0,
      0.0
    ],
    "range": [
      0.0,
      1.0
    ]
  },
  "hash_algorithm": "sha256:first16",
  "headers_removed_from_csv": true,
  "n_features": 7,
  "origin": "real",
  "original_headers": [
    "region",
    "pop",
    "sex",
    "age",
    "educ",
    "income",
    "vote",
    "target"
  ],
  "output_headers": [
    "region",
    "pop",
    "sex",
    "age",
    "educ",
    "income",
    "vote",
    "target"
  ],
  "retrieved_at": "2026-06-27T23:54:41+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": 3337433724,
    "source_read_max_rows": null,
    "test_target_rows": 1000,
    "train_target_rows": 1000
  },
  "sha256": "c7d815714ca52bce85630b39a3c3eadafcea97ddbedab3788f489423820eb850",
  "source_dataset_id": "stevedata/chile88",
  "source_dataset_name": "Voting Intentions in the 1988 Chilean Plebiscite",
  "source_family": "voting-intentions",
  "source_file": "rdatasets-stevedata-chile88-sq.csv",
  "source_license": "GPL (R package stevedata)",
  "source_modified_at": "2026-06-27T23:56:51+00:00",
  "source_path": "/home/ubuntu/hyper/data/tabular/real_regression_sources/rdatasets-stevedata-chile88-sq.csv",
  "source_platform": "rdatasets",
  "source_real_data": true,
  "source_resource_id": null,
  "source_rows": 2700,
  "source_size_bytes": 90778,
  "source_target_column_original": "sq",
  "source_url": "https://vincentarelbundock.github.io/Rdatasets/csv/stevedata/chile88.csv",
  "staged_rows": 1999,
  "staging_path": "/home/ubuntu/hyper/data/tabular/real_regression_sources/rdatasets-stevedata-chile88-sq.csv",
  "target_column": "target",
  "target_generation": "original_numeric_column",
  "target_is_final_column": true,
  "target_names": [
    "target"
  ],
  "target_scaling": {
    "max": 2.04859,
    "min": -1.80301,
    "mode": "regression",
    "range": [
      0.0,
      1.0
    ]
  },
  "target_source_encoding": {
    "kind": "numeric"
  },
  "task_type": "regression",
  "test_rows": 999,
  "train_rows": 1000
}