{
  "acquisition": {
    "acquired_at": "2026-06-27T23:53:57+00:00",
    "agent_id": "Claude-extra",
    "dedupe_fingerprint": "44e65b76a40d792987587cb3b044fbe700396d2d",
    "source_dataset_id": "MedDataSets/Pima_te_df",
    "source_dataset_name": "Diabetes in Pima Indian Women",
    "source_platform": "rdatasets",
    "source_rows": 332,
    "source_target_column_original": "ped",
    "source_url": "https://vincentarelbundock.github.io/Rdatasets/csv/MedDataSets/Pima_te_df.csv",
    "staged_rows": 332,
    "staging_path": "/home/ubuntu/hyper/data/tabular/real_regression_sources/rdatasets-meddatasets-pima-te-df-ped.csv",
    "tool": "models.tools.acquire_regression_extra_sources"
  },
  "counts": {
    "dropped_feature_count": 0,
    "n_features": 7,
    "original_columns": 8,
    "original_rows": 332,
    "rows_after_target_cleanup": 332,
    "selected_rows": 332,
    "strata_count": 73,
    "test_rows": 56,
    "train_rows": 276
  },
  "created_at": "2026-06-27T23:53:57+00:00",
  "dataset_hash": "11a7321bc045c456",
  "dedupe_fingerprint": "44e65b76a40d792987587cb3b044fbe700396d2d",
  "dropped_feature_columns": [],
  "feature_columns": [
    "npreg",
    "glu",
    "bp",
    "skin",
    "bmi",
    "age",
    "type"
  ],
  "feature_encodings": {
    "age": {
      "impute_value": 27.0,
      "kind": "numeric"
    },
    "bmi": {
      "impute_value": 32.9,
      "kind": "numeric"
    },
    "bp": {
      "impute_value": 72.0,
      "kind": "numeric"
    },
    "glu": {
      "impute_value": 112.0,
      "kind": "numeric"
    },
    "npreg": {
      "impute_value": 2.0,
      "kind": "numeric"
    },
    "skin": {
      "impute_value": 29.0,
      "kind": "numeric"
    },
    "type": {
      "impute_value": 0.0,
      "kind": "numeric"
    }
  },
  "feature_scaling": {
    "constant_columns": [],
    "max": [
      17.0,
      197.0,
      110.0,
      63.0,
      67.1,
      81.0,
      1.0
    ],
    "method": "minmax over cleaned source rows before sampling",
    "min": [
      0.0,
      65.0,
      24.0,
      7.0,
      19.4,
      21.0,
      0.0
    ],
    "range": [
      0.0,
      1.0
    ]
  },
  "hash_algorithm": "sha256:first16",
  "headers_removed_from_csv": true,
  "n_features": 7,
  "origin": "real",
  "original_headers": [
    "npreg",
    "glu",
    "bp",
    "skin",
    "bmi",
    "age",
    "type",
    "target"
  ],
  "output_headers": [
    "npreg",
    "glu",
    "bp",
    "skin",
    "bmi",
    "age",
    "type",
    "target"
  ],
  "retrieved_at": "2026-06-27T23:51:55+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": 278009110,
    "source_read_max_rows": null,
    "test_target_rows": 1000,
    "train_target_rows": 1000
  },
  "sha256": "11a7321bc045c456dfd1de5b0dd86a30027d2a22900507efa5b68c6f461a5426",
  "source_dataset_id": "MedDataSets/Pima_te_df",
  "source_dataset_name": "Diabetes in Pima Indian Women",
  "source_family": "diabetes-in",
  "source_file": "rdatasets-meddatasets-pima-te-df-ped.csv",
  "source_license": "GPL (R package MedDataSets)",
  "source_modified_at": "2026-06-27T23:53:57+00:00",
  "source_path": "/home/ubuntu/hyper/data/tabular/real_regression_sources/rdatasets-meddatasets-pima-te-df-ped.csv",
  "source_platform": "rdatasets",
  "source_real_data": true,
  "source_resource_id": null,
  "source_rows": 332,
  "source_size_bytes": 13207,
  "source_target_column_original": "ped",
  "source_url": "https://vincentarelbundock.github.io/Rdatasets/csv/MedDataSets/Pima_te_df.csv",
  "staged_rows": 332,
  "staging_path": "/home/ubuntu/hyper/data/tabular/real_regression_sources/rdatasets-meddatasets-pima-te-df-ped.csv",
  "target_column": "target",
  "target_generation": "original_numeric_column",
  "target_is_final_column": true,
  "target_names": [
    "target"
  ],
  "target_scaling": {
    "max": 2.42,
    "min": 0.085,
    "mode": "regression",
    "range": [
      0.0,
      1.0
    ]
  },
  "target_source_encoding": {
    "kind": "numeric"
  },
  "task_type": "regression",
  "test_rows": 56,
  "train_rows": 276
}