{
  "acquisition": {
    "acquired_at": "2026-06-27T23:23:55+00:00",
    "archive_member": "day.csv",
    "dedupe_fingerprint": "404f8fa4b4104a2315ad5aabda2ef29471c8baf4",
    "download_url": "https://archive.ics.uci.edu/ml/machine-learning-databases/00275/Bike-Sharing-Dataset.zip",
    "dropped_feature_columns_for_cap": [],
    "fetched_columns": 16,
    "fetched_rows": 731,
    "row_policy": "kept_all",
    "source_dataset_id": "bike-sharing-day",
    "source_dataset_name": "Bike Sharing Day",
    "source_platform": "uci",
    "source_resource_id": "day.csv",
    "source_rows_after_target_cleanup": 731,
    "source_target_column_original": "cnt",
    "source_url": "https://archive.ics.uci.edu/ml/machine-learning-databases/00275/Bike-Sharing-Dataset.zip",
    "staged_feature_columns": 14,
    "staged_rows": 731,
    "staging_path": "/home/ubuntu/hyper/data/tabular/real_regression_sources/uci-bike-sharing-day-bike-sharing-day-day-target-cnt.csv",
    "target_profile": {
      "column": "cnt",
      "finite_rows": 731,
      "integer_like": true,
      "maximum": 8714.0,
      "minimum": 22.0,
      "missing_fraction": 0.0,
      "numeric_valid_fraction": 1.0,
      "unique_values": 696
    },
    "tool": "models.tools.acquire_real_regression_datasets"
  },
  "counts": {
    "dropped_feature_count": 0,
    "n_features": 14,
    "original_columns": 15,
    "original_rows": 731,
    "rows_after_target_cleanup": 731,
    "selected_rows": 731,
    "strata_count": 106,
    "test_rows": 122,
    "train_rows": 609
  },
  "created_at": "2026-06-27T23:23:55+00:00",
  "dataset_hash": "7af85a04de0c7018",
  "dedupe_fingerprint": "404f8fa4b4104a2315ad5aabda2ef29471c8baf4",
  "dropped_feature_columns": [],
  "feature_columns": [
    "instant",
    "season",
    "yr",
    "mnth",
    "holiday",
    "weekday",
    "workingday",
    "weathersit",
    "temp",
    "atemp",
    "hum",
    "windspeed",
    "casual",
    "registered"
  ],
  "feature_encodings": {
    "atemp": {
      "impute_value": 0.486733,
      "kind": "numeric"
    },
    "casual": {
      "impute_value": 713.0,
      "kind": "numeric"
    },
    "holiday": {
      "impute_value": 0.0,
      "kind": "numeric"
    },
    "hum": {
      "impute_value": 0.626667,
      "kind": "numeric"
    },
    "instant": {
      "impute_value": 366.0,
      "kind": "numeric"
    },
    "mnth": {
      "impute_value": 7.0,
      "kind": "numeric"
    },
    "registered": {
      "impute_value": 3662.0,
      "kind": "numeric"
    },
    "season": {
      "impute_value": 3.0,
      "kind": "numeric"
    },
    "temp": {
      "impute_value": 0.498333,
      "kind": "numeric"
    },
    "weathersit": {
      "impute_value": 1.0,
      "kind": "numeric"
    },
    "weekday": {
      "impute_value": 3.0,
      "kind": "numeric"
    },
    "windspeed": {
      "impute_value": 0.180975,
      "kind": "numeric"
    },
    "workingday": {
      "impute_value": 1.0,
      "kind": "numeric"
    },
    "yr": {
      "impute_value": 1.0,
      "kind": "numeric"
    }
  },
  "feature_scaling": {
    "constant_columns": [],
    "max": [
      731.0,
      4.0,
      1.0,
      12.0,
      1.0,
      6.0,
      1.0,
      3.0,
      0.861667,
      0.840896,
      0.9725,
      0.507463,
      3410.0,
      6946.0
    ],
    "method": "minmax over cleaned source rows before sampling",
    "min": [
      1.0,
      1.0,
      0.0,
      1.0,
      0.0,
      0.0,
      0.0,
      1.0,
      0.0591304,
      0.0790696,
      0.0,
      0.0223917,
      2.0,
      20.0
    ],
    "range": [
      0.0,
      1.0
    ]
  },
  "hash_algorithm": "sha256:first16",
  "headers_removed_from_csv": true,
  "n_features": 14,
  "origin": "real",
  "original_headers": [
    "instant",
    "season",
    "yr",
    "mnth",
    "holiday",
    "weekday",
    "workingday",
    "weathersit",
    "temp",
    "atemp",
    "hum",
    "windspeed",
    "casual",
    "registered",
    "target"
  ],
  "output_headers": [
    "instant",
    "season",
    "yr",
    "mnth",
    "holiday",
    "weekday",
    "workingday",
    "weathersit",
    "temp",
    "atemp",
    "hum",
    "windspeed",
    "casual",
    "registered",
    "target"
  ],
  "retrieved_at": "2026-06-27T23:23:55+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": 2077064457,
    "source_read_max_rows": null,
    "test_target_rows": 1000,
    "train_target_rows": 1000
  },
  "sha256": "7af85a04de0c7018feb0716fa1d7a26974b3390829e5e1cc81dd886c2ff7c9ab",
  "source_dataset_id": "bike-sharing-day",
  "source_dataset_name": "Bike Sharing Day",
  "source_family": "bike-sharing",
  "source_file": "uci-bike-sharing-day-bike-sharing-day-day-target-cnt.csv",
  "source_license": null,
  "source_modified_at": "2026-06-27T23:23:55+00:00",
  "source_path": "/home/ubuntu/hyper/data/tabular/real_regression_sources/uci-bike-sharing-day-bike-sharing-day-day-target-cnt.csv",
  "source_platform": "uci",
  "source_real_data": true,
  "source_resource_id": "day.csv",
  "source_rows": 731,
  "source_size_bytes": 64876,
  "source_target_column_original": "cnt",
  "source_url": "https://archive.ics.uci.edu/ml/machine-learning-databases/00275/Bike-Sharing-Dataset.zip",
  "staged_rows": 731,
  "staging_path": "/home/ubuntu/hyper/data/tabular/real_regression_sources/uci-bike-sharing-day-bike-sharing-day-day-target-cnt.csv",
  "target_column": "target",
  "target_generation": "original_numeric_column",
  "target_is_final_column": true,
  "target_names": [
    "target"
  ],
  "target_scaling": {
    "max": 8714.0,
    "min": 22.0,
    "mode": "regression",
    "range": [
      0.0,
      1.0
    ]
  },
  "target_source_encoding": {
    "kind": "numeric"
  },
  "task_type": "regression",
  "test_rows": 122,
  "train_rows": 609
}