{
  "counts": {
    "dropped_feature_count": 0,
    "n_features": 7,
    "original_columns": 8,
    "original_rows": 52,
    "rows_after_target_cleanup": 52,
    "selected_rows": 52,
    "strata_count": 10,
    "test_rows": 9,
    "train_rows": 43
  },
  "created_at": "2026-06-21T07:58:43+00:00",
  "dataset_hash": "b253fbfae8460dc1",
  "dropped_feature_columns": [],
  "feature_columns": [
    "pH_target",
    "Clay_target",
    "Altitude",
    "Slope",
    "B02",
    "B8A",
    "B11"
  ],
  "feature_encodings": {
    "Altitude": {
      "impute_value": 252.01750183105452,
      "kind": "numeric"
    },
    "B02": {
      "impute_value": 1585.5,
      "kind": "numeric"
    },
    "B11": {
      "impute_value": 3071.0,
      "kind": "numeric"
    },
    "B8A": {
      "impute_value": 2370.0,
      "kind": "numeric"
    },
    "Clay_target": {
      "impute_value": 46.2,
      "kind": "numeric"
    },
    "Slope": {
      "impute_value": 0.04599475860595705,
      "kind": "numeric"
    },
    "pH_target": {
      "impute_value": 8.295,
      "kind": "numeric"
    }
  },
  "feature_scaling": {
    "constant_columns": [],
    "max": [
      8.94,
      60.135,
      273.183990478516,
      0.186874389648438,
      2052.0,
      3778.0,
      5320.0
    ],
    "method": "minmax over cleaned source rows before sampling",
    "min": [
      5.6,
      1.2,
      225.75,
      0.0088729858398437,
      1334.0,
      1967.0,
      2345.0
    ],
    "range": [
      0.0,
      1.0
    ]
  },
  "hash_algorithm": "sha256:first16",
  "headers_removed_from_csv": true,
  "n_features": 7,
  "original_headers": [
    "pH_target",
    "Clay_target",
    "Altitude",
    "Slope",
    "B02",
    "B8A",
    "B11",
    "target"
  ],
  "output_headers": [
    "pH_target",
    "Clay_target",
    "Altitude",
    "Slope",
    "B02",
    "B8A",
    "B11",
    "target"
  ],
  "sampling": {
    "method": "quota stratified by target distribution plus high-variance feature quantile bins",
    "minimum_test_to_train_ratio_when_small": 0.2,
    "seed": 3009862903,
    "test_target_rows": 1000,
    "train_target_rows": 1000
  },
  "sha256": "b253fbfae8460dc167d180914926e10bdb468537a061dcb260ea9febb8f690ea",
  "source_file": "limesoda-nsw-52-dataset.csv",
  "source_modified_at": "2026-06-20T10:07:29+00:00",
  "source_path": "/home/ubuntu/hyper/data/tabular/limesoda-nsw-52-dataset.csv",
  "source_size_bytes": 3790,
  "target_column": "target",
  "target_is_final_column": true,
  "target_names": [
    "target"
  ],
  "target_scaling": {
    "max": 1.91,
    "min": 0.5,
    "mode": "regression",
    "range": [
      0.0,
      1.0
    ]
  },
  "target_source_encoding": {
    "kind": "numeric"
  },
  "task_type": "regression",
  "test_rows": 9,
  "train_rows": 43
}