{
  "schema_version": "gfis-gate3-ds03-v1",
  "source_workbook": "../../03_Datasets/01_Raw_Public_Datasets/DS03_Mendeley_gk3f363sfg_v1/extracted/Farm-scale_Biodigester_Perfromance_dataset/Farm-scale Biodigester 2024_Performance.xlsx",
  "source_workbook_sha256": "fbdd44fba2fae3dfa4de6ddd01781ffa0d9f03b05118db2f94e57af154787064",
  "weather_workbook": "../../03_Datasets/01_Raw_Public_Datasets/DS03_Mendeley_gk3f363sfg_v1/extracted/Farm-scale_Biodigester_Perfromance_dataset/Mazingira main(z6-02152)-1729245757_weather_data.xlsx",
  "weather_workbook_sha256": "2eada242b82439bc08a52a01022a3d68bfc18a881c335f87ae6fc1c92b9e4cf1",
  "processed_file": "../../03_Datasets/05_Processed_Final/DS03/gfis_ds03_canonical_v1.csv",
  "processed_sha256": "66d7dfc303f6197d3c5b96eaffb9bfbe5c351b0929461db7c13fe69a8f7e5654",
  "processing": [
    "Read four reactor sheets independently.",
    "Repair mixed Excel/string dates monotonically in source-row order; retain date_repaired flag.",
    "Parse numeric feed values without imputing raw observations.",
    "Preserve reactor identity and source row.",
    "Flag duplicate timestamps and non-daily intervals.",
    "Do not use zero-filled methane-derived source columns as measured methane.",
    "Aggregate 5-minute weather observations to daily summaries and left-join by calendar date."
  ],
  "quality": {
    "rows": 1167,
    "reactors": [
      "R1",
      "R2",
      "R3",
      "R4"
    ],
    "timestamp_start": "2024-01-04 00:00:00",
    "timestamp_end": "2025-01-14 00:00:00",
    "target_definition": "Total biogas meter increment between recorded observations, source-labelled mL",
    "target_is_methane": false,
    "by_reactor": {
      "R1": {
        "rows": 306,
        "start": "2024-01-04",
        "end": "2025-01-14",
        "duplicate_timestamps": 0,
        "non_daily_intervals": 55,
        "median_interval_days": 1.0,
        "target_missing": 1,
        "temperature_missing": 0,
        "digester_temperature_missing": 3,
        "methane_fraction_observations": 1,
        "date_repairs": 0
      },
      "R2": {
        "rows": 306,
        "start": "2024-01-04",
        "end": "2025-01-14",
        "duplicate_timestamps": 0,
        "non_daily_intervals": 54,
        "median_interval_days": 1.0,
        "target_missing": 1,
        "temperature_missing": 0,
        "digester_temperature_missing": 7,
        "methane_fraction_observations": 1,
        "date_repairs": 0
      },
      "R3": {
        "rows": 279,
        "start": "2024-01-10",
        "end": "2025-01-14",
        "duplicate_timestamps": 6,
        "non_daily_intervals": 50,
        "median_interval_days": 1.0,
        "target_missing": 1,
        "temperature_missing": 10,
        "digester_temperature_missing": 279,
        "methane_fraction_observations": 1,
        "date_repairs": 23
      },
      "R4": {
        "rows": 276,
        "start": "2024-01-10",
        "end": "2025-01-14",
        "duplicate_timestamps": 5,
        "non_daily_intervals": 48,
        "median_interval_days": 1.0,
        "target_missing": 1,
        "temperature_missing": 8,
        "digester_temperature_missing": 276,
        "methane_fraction_observations": 1,
        "date_repairs": 32
      }
    },
    "missing_fraction": {
      "total_biogas_interval_ml": 0.003427592116538132,
      "air_temperature_c": 0.015424164524421594,
      "digester_temperature_c": 0.48414738646101113,
      "manure_fed_kg": 0.01456726649528706,
      "methane_fraction_percent": 0.9965724078834619
    }
  }
}
