{
  "acquisition": {
    "acquired_at": "2026-06-27T23:24:34+00:00",
    "archive_member": null,
    "dedupe_fingerprint": "a00f17f27e77d9ca8574aff6b711ada7b8b19a91",
    "download_url": "https://archive.ics.uci.edu/ml/machine-learning-databases/parkinsons/telemonitoring/parkinsons_updrs.data",
    "dropped_feature_columns_for_cap": [],
    "fetched_columns": 22,
    "fetched_rows": 5875,
    "row_policy": "stratified_cap_to_final_max",
    "source_dataset_id": "parkinsons-telemonitoring",
    "source_dataset_name": "Parkinsons Telemonitoring",
    "source_platform": "uci",
    "source_resource_id": "parkinsons-telemonitoring",
    "source_rows_after_target_cleanup": 5875,
    "source_target_column_original": "total_UPDRS",
    "source_url": "https://archive.ics.uci.edu/ml/machine-learning-databases/parkinsons/telemonitoring/parkinsons_updrs.data",
    "staged_feature_columns": 21,
    "staged_rows": 1999,
    "staging_path": "/home/ubuntu/hyper/data/tabular/real_regression_sources/uci-parkinsons-telemonitoring-parkinsons-telemonitoring-parkinsons-telemonitoring-target-total-updrs.csv",
    "target_profile": {
      "column": "total_UPDRS",
      "finite_rows": 5875,
      "integer_like": false,
      "maximum": 54.992,
      "minimum": 7.0,
      "missing_fraction": 0.0,
      "numeric_valid_fraction": 1.0,
      "unique_values": 1129
    },
    "tool": "models.tools.acquire_real_regression_datasets"
  },
  "counts": {
    "dropped_feature_count": 0,
    "n_features": 21,
    "original_columns": 22,
    "original_rows": 1999,
    "rows_after_target_cleanup": 1999,
    "selected_rows": 1999,
    "strata_count": 98,
    "test_rows": 999,
    "train_rows": 1000
  },
  "created_at": "2026-06-27T23:24:34+00:00",
  "dataset_hash": "21fbfe8b53dbcd60",
  "dedupe_fingerprint": "a00f17f27e77d9ca8574aff6b711ada7b8b19a91",
  "dropped_feature_columns": [],
  "feature_columns": [
    "subject#",
    "age",
    "sex",
    "test_time",
    "motor_UPDRS",
    "Jitter(%)",
    "Jitter(Abs)",
    "Jitter:RAP",
    "Jitter:PPQ5",
    "Jitter:DDP",
    "Shimmer",
    "Shimmer(dB)",
    "Shimmer:APQ3",
    "Shimmer:APQ5",
    "Shimmer:APQ11",
    "Shimmer:DDA",
    "NHR",
    "HNR",
    "RPDE",
    "DFA",
    "PPE"
  ],
  "feature_encodings": {
    "DFA": {
      "impute_value": 0.64235,
      "kind": "numeric"
    },
    "HNR": {
      "impute_value": 21.929,
      "kind": "numeric"
    },
    "Jitter(%)": {
      "impute_value": 0.00493,
      "kind": "numeric"
    },
    "Jitter(Abs)": {
      "impute_value": 3.443e-05,
      "kind": "numeric"
    },
    "Jitter:DDP": {
      "impute_value": 0.0067,
      "kind": "numeric"
    },
    "Jitter:PPQ5": {
      "impute_value": 0.0025,
      "kind": "numeric"
    },
    "Jitter:RAP": {
      "impute_value": 0.00223,
      "kind": "numeric"
    },
    "NHR": {
      "impute_value": 0.018857,
      "kind": "numeric"
    },
    "PPE": {
      "impute_value": 0.20595,
      "kind": "numeric"
    },
    "RPDE": {
      "impute_value": 0.54534,
      "kind": "numeric"
    },
    "Shimmer": {
      "impute_value": 0.02728,
      "kind": "numeric"
    },
    "Shimmer(dB)": {
      "impute_value": 0.251,
      "kind": "numeric"
    },
    "Shimmer:APQ11": {
      "impute_value": 0.02246,
      "kind": "numeric"
    },
    "Shimmer:APQ3": {
      "impute_value": 0.01358,
      "kind": "numeric"
    },
    "Shimmer:APQ5": {
      "impute_value": 0.01573,
      "kind": "numeric"
    },
    "Shimmer:DDA": {
      "impute_value": 0.04075,
      "kind": "numeric"
    },
    "age": {
      "impute_value": 66.0,
      "kind": "numeric"
    },
    "motor_UPDRS": {
      "impute_value": 20.947,
      "kind": "numeric"
    },
    "sex": {
      "impute_value": 0.0,
      "kind": "numeric"
    },
    "subject#": {
      "impute_value": 21.0,
      "kind": "numeric"
    },
    "test_time": {
      "impute_value": 91.332,
      "kind": "numeric"
    }
  },
  "feature_scaling": {
    "constant_columns": [],
    "max": [
      42.0,
      85.0,
      1.0,
      215.49,
      37.957,
      0.09999,
      0.00039089,
      0.05754,
      0.06956,
      0.17263,
      0.22677,
      1.877,
      0.14428,
      0.16702,
      0.27546,
      0.43283,
      0.72537,
      36.448,
      0.96608,
      0.8656,
      0.73173
    ],
    "method": "minmax over cleaned source rows before sampling",
    "min": [
      1.0,
      36.0,
      0.0,
      -4.2618,
      5.0377,
      0.00113,
      3.79e-06,
      0.00043,
      0.00055,
      0.00128,
      0.00344,
      0.03,
      0.00172,
      0.00205,
      0.00299,
      0.00515,
      0.000993,
      2.206,
      0.20105,
      0.51782,
      0.02321
    ],
    "range": [
      0.0,
      1.0
    ]
  },
  "hash_algorithm": "sha256:first16",
  "headers_removed_from_csv": true,
  "n_features": 21,
  "origin": "real",
  "original_headers": [
    "subject#",
    "age",
    "sex",
    "test_time",
    "motor_UPDRS",
    "Jitter(%)",
    "Jitter(Abs)",
    "Jitter:RAP",
    "Jitter:PPQ5",
    "Jitter:DDP",
    "Shimmer",
    "Shimmer(dB)",
    "Shimmer:APQ3",
    "Shimmer:APQ5",
    "Shimmer:APQ11",
    "Shimmer:DDA",
    "NHR",
    "HNR",
    "RPDE",
    "DFA",
    "PPE",
    "target"
  ],
  "output_headers": [
    "subject#",
    "age",
    "sex",
    "test_time",
    "motor_UPDRS",
    "Jitter(%)",
    "Jitter(Abs)",
    "Jitter:RAP",
    "Jitter:PPQ5",
    "Jitter:DDP",
    "Shimmer",
    "Shimmer(dB)",
    "Shimmer:APQ3",
    "Shimmer:APQ5",
    "Shimmer:APQ11",
    "Shimmer:DDA",
    "NHR",
    "HNR",
    "RPDE",
    "DFA",
    "PPE",
    "target"
  ],
  "retrieved_at": "2026-06-27T23:24:34+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": 550427014,
    "source_read_max_rows": null,
    "test_target_rows": 1000,
    "train_target_rows": 1000
  },
  "sha256": "21fbfe8b53dbcd605d79486b6b1bf9624b7ab9a4e549fb2b63c74a7344c46460",
  "source_dataset_id": "parkinsons-telemonitoring",
  "source_dataset_name": "Parkinsons Telemonitoring",
  "source_family": "parkinsons-telemonitoring",
  "source_file": "uci-parkinsons-telemonitoring-parkinsons-telemonitoring-parkinsons-telemonitoring-target-total-updrs.csv",
  "source_license": null,
  "source_modified_at": "2026-06-27T23:24:34+00:00",
  "source_path": "/home/ubuntu/hyper/data/tabular/real_regression_sources/uci-parkinsons-telemonitoring-parkinsons-telemonitoring-parkinsons-telemonitoring-target-total-updrs.csv",
  "source_platform": "uci",
  "source_real_data": true,
  "source_resource_id": "parkinsons-telemonitoring",
  "source_rows": 5875,
  "source_size_bytes": 320880,
  "source_target_column_original": "total_UPDRS",
  "source_url": "https://archive.ics.uci.edu/ml/machine-learning-databases/parkinsons/telemonitoring/parkinsons_updrs.data",
  "staged_rows": 1999,
  "staging_path": "/home/ubuntu/hyper/data/tabular/real_regression_sources/uci-parkinsons-telemonitoring-parkinsons-telemonitoring-parkinsons-telemonitoring-target-total-updrs.csv",
  "target_column": "target",
  "target_generation": "original_numeric_column",
  "target_is_final_column": true,
  "target_names": [
    "target"
  ],
  "target_scaling": {
    "max": 54.948,
    "min": 7.0,
    "mode": "regression",
    "range": [
      0.0,
      1.0
    ]
  },
  "target_source_encoding": {
    "kind": "numeric"
  },
  "task_type": "regression",
  "test_rows": 999,
  "train_rows": 1000
}