{
  "generated_at": "2026-06-30T21:55:02.911716+00:00",
  "round": "round2_size_matters",
  "description": "Size-bucket analysis derived from completed Round 2 single-file CSV benchmark results. No CSV files were reopened or re-benchmarked.",
  "source_data": {
    "input_path": "C:\\code\\projects\\data-reports\\numpy-vs-pyarrow-nyc-taxi\\output\\round2-read-csv\\data.json",
    "source_round": "round2_csv_pandas_default_vs_pandas_pyarrow",
    "source_generated_at": "2026-06-30T20:26:03.191719+00:00"
  },
  "bucket_definition": [
    {
      "bucket_id": "tiny",
      "label": "Tiny CSV files",
      "minimum_bytes": 0,
      "maximum_bytes_exclusive": 104857600
    },
    {
      "bucket_id": "small",
      "label": "Small CSV files",
      "minimum_bytes": 104857600,
      "maximum_bytes_exclusive": 262144000
    },
    {
      "bucket_id": "medium",
      "label": "Medium CSV files",
      "minimum_bytes": 262144000,
      "maximum_bytes_exclusive": 524288000
    },
    {
      "bucket_id": "large",
      "label": "Large CSV files",
      "minimum_bytes": 524288000,
      "maximum_bytes_exclusive": 786432000
    },
    {
      "bucket_id": "giant",
      "label": "Giant CSV files",
      "minimum_bytes": 786432000,
      "maximum_bytes_exclusive": null
    }
  ],
  "summary": {
    "files_total": 48,
    "files_comparable": 48,
    "pyarrow_wins": 48,
    "default_wins": 0,
    "ties_within_1_percent": 0,
    "source_single_file_overall_speedup_default_over_pyarrow": 8.888766882102267,
    "source_single_file_median_speedup_default_over_pyarrow": 10.43631073335132
  },
  "bucket_summaries": [
    {
      "bucket_id": "tiny",
      "bucket_label": "Tiny CSV files",
      "minimum_bytes": 0,
      "maximum_bytes_exclusive": 104857600,
      "file_count": 4,
      "total_csv_bytes": 206948094,
      "total_csv_mb": 197.36108207702637,
      "total_parquet_bytes": 33565620,
      "total_parquet_mb": 32.01066970825195,
      "total_rows": 1936697,
      "pyarrow_wins": 4,
      "default_wins": 0,
      "ties_within_1_percent": 0,
      "median_speedup_default_over_pyarrow": 8.7101150557012,
      "average_speedup_default_over_pyarrow": 8.667258094532897,
      "default_total_median_ms": 2911.6689,
      "pyarrow_total_median_ms": 333.437,
      "aggregate_speedup_default_over_pyarrow": 8.732290957512214,
      "smallest_csv_bytes": 25361579,
      "largest_csv_bytes": 85783914
    },
    {
      "bucket_id": "small",
      "bucket_label": "Small CSV files",
      "minimum_bytes": 104857600,
      "maximum_bytes_exclusive": 262144000,
      "file_count": 9,
      "total_csv_bytes": 1493312891,
      "total_csv_mb": 1424.134150505066,
      "total_parquet_bytes": 218383418,
      "total_parquet_mb": 208.26665687561035,
      "total_rows": 13838150,
      "pyarrow_wins": 9,
      "default_wins": 0,
      "ties_within_1_percent": 0,
      "median_speedup_default_over_pyarrow": 11.66417527404147,
      "average_speedup_default_over_pyarrow": 11.096369413932731,
      "default_total_median_ms": 25631.709,
      "pyarrow_total_median_ms": 2387.3325,
      "aggregate_speedup_default_over_pyarrow": 10.736547590249787,
      "smallest_csv_bytes": 108148348,
      "largest_csv_bytes": 236675669
    },
    {
      "bucket_id": "medium",
      "bucket_label": "Medium CSV files",
      "minimum_bytes": 262144000,
      "maximum_bytes_exclusive": 524288000,
      "file_count": 21,
      "total_csv_bytes": 7316867999,
      "total_csv_mb": 6977.909087181091,
      "total_parquet_bytes": 1031633245,
      "total_parquet_mb": 983.8421297073364,
      "total_rows": 66730276,
      "pyarrow_wins": 21,
      "default_wins": 0,
      "ties_within_1_percent": 0,
      "median_speedup_default_over_pyarrow": 11.621520091397123,
      "average_speedup_default_over_pyarrow": 11.516297607578503,
      "default_total_median_ms": 120808.0956,
      "pyarrow_total_median_ms": 10532.4694,
      "aggregate_speedup_default_over_pyarrow": 11.470063763014588,
      "smallest_csv_bytes": 270012679,
      "largest_csv_bytes": 404178000
    },
    {
      "bucket_id": "large",
      "bucket_label": "Large CSV files",
      "minimum_bytes": 524288000,
      "maximum_bytes_exclusive": 786432000,
      "file_count": 10,
      "total_csv_bytes": 7226851902,
      "total_csv_mb": 6892.063047409058,
      "total_parquet_bytes": 981155584,
      "total_parquet_mb": 935.702880859375,
      "total_rows": 66665188,
      "pyarrow_wins": 10,
      "default_wins": 0,
      "ties_within_1_percent": 0,
      "median_speedup_default_over_pyarrow": 8.049568709424536,
      "average_speedup_default_over_pyarrow": 7.447208115303313,
      "default_total_median_ms": 90876.4172,
      "pyarrow_total_median_ms": 12344.7068,
      "aggregate_speedup_default_over_pyarrow": 7.361569510909728,
      "smallest_csv_bytes": 657771137,
      "largest_csv_bytes": 782626216
    },
    {
      "bucket_id": "giant",
      "bucket_label": "Giant CSV files",
      "minimum_bytes": 786432000,
      "maximum_bytes_exclusive": null,
      "file_count": 4,
      "total_csv_bytes": 3297637512,
      "total_csv_mb": 3144.872200012207,
      "total_parquet_bytes": 448075086,
      "total_parquet_mb": 427.3177013397217,
      "total_rows": 30637631,
      "pyarrow_wins": 4,
      "default_wins": 0,
      "ties_within_1_percent": 0,
      "median_speedup_default_over_pyarrow": 6.516516293192856,
      "average_speedup_default_over_pyarrow": 7.237018562346181,
      "default_total_median_ms": 48323.6411,
      "pyarrow_total_median_ms": 6864.5472,
      "aggregate_speedup_default_over_pyarrow": 7.0395963043272545,
      "smallest_csv_bytes": 810387251,
      "largest_csv_bytes": 852779445
    }
  ],
  "files": [
    {
      "bucket_id": "tiny",
      "bucket_label": "Tiny CSV files",
      "input_id": "yellow_2020_04",
      "taxi_type": "yellow",
      "year": 2020,
      "month": "04",
      "csv_path": "data/derived-csv/yellow/2020/yellow_tripdata_2020-04.csv",
      "csv_size_bytes": 25361579,
      "csv_size_mb": 24.186686515808105,
      "parquet_size_bytes": 4442620,
      "parquet_size_mb": 4.236812591552734,
      "csv_over_parquet_ratio": 5.708699,
      "expected_rows": 238073,
      "expected_columns": 19,
      "default_status": "ok",
      "pyarrow_status": "ok",
      "default_median_ms": 346.2451,
      "pyarrow_median_ms": 40.0772,
      "speedup_default_over_pyarrow": 8.639453355024802,
      "winner": "pandas_pyarrow"
    },
    {
      "bucket_id": "tiny",
      "bucket_label": "Tiny CSV files",
      "input_id": "yellow_2020_05",
      "taxi_type": "yellow",
      "year": 2020,
      "month": "05",
      "csv_path": "data/derived-csv/yellow/2020/yellow_tripdata_2020-05.csv",
      "csv_size_bytes": 36997127,
      "csv_size_mb": 35.283209800720215,
      "parquet_size_bytes": 6229864,
      "parquet_size_mb": 5.941261291503906,
      "csv_over_parquet_ratio": 5.938673,
      "expected_rows": 348415,
      "expected_columns": 19,
      "default_status": "ok",
      "pyarrow_status": "ok",
      "default_median_ms": 475.6898,
      "pyarrow_median_ms": 54.174,
      "speedup_default_over_pyarrow": 8.780776756377598,
      "winner": "pandas_pyarrow"
    },
    {
      "bucket_id": "tiny",
      "bucket_label": "Tiny CSV files",
      "input_id": "yellow_2020_06",
      "taxi_type": "yellow",
      "year": 2020,
      "month": "06",
      "csv_path": "data/derived-csv/yellow/2020/yellow_tripdata_2020-06.csv",
      "csv_size_bytes": 58805474,
      "csv_size_mb": 56.08127021789551,
      "parquet_size_bytes": 9505358,
      "parquet_size_mb": 9.06501579284668,
      "csv_over_parquet_ratio": 6.186561,
      "expected_rows": 549797,
      "expected_columns": 19,
      "default_status": "ok",
      "pyarrow_status": "ok",
      "default_median_ms": 790.3183,
      "pyarrow_median_ms": 99.2429,
      "speedup_default_over_pyarrow": 7.963474465175846,
      "winner": "pandas_pyarrow"
    },
    {
      "bucket_id": "tiny",
      "bucket_label": "Tiny CSV files",
      "input_id": "yellow_2020_07",
      "taxi_type": "yellow",
      "year": 2020,
      "month": "07",
      "csv_path": "data/derived-csv/yellow/2020/yellow_tripdata_2020-07.csv",
      "csv_size_bytes": 85783914,
      "csv_size_mb": 81.80991554260254,
      "parquet_size_bytes": 13387778,
      "parquet_size_mb": 12.767580032348633,
      "csv_over_parquet_ratio": 6.407629,
      "expected_rows": 800412,
      "expected_columns": 19,
      "default_status": "ok",
      "pyarrow_status": "ok",
      "default_median_ms": 1299.4157,
      "pyarrow_median_ms": 139.9429,
      "speedup_default_over_pyarrow": 9.285327801553347,
      "winner": "pandas_pyarrow"
    },
    {
      "bucket_id": "small",
      "bucket_label": "Small CSV files",
      "input_id": "yellow_2020_08",
      "taxi_type": "yellow",
      "year": 2020,
      "month": "08",
      "csv_path": "data/derived-csv/yellow/2020/yellow_tripdata_2020-08.csv",
      "csv_size_bytes": 108148348,
      "csv_size_mb": 103.13830184936523,
      "parquet_size_bytes": 16601463,
      "parquet_size_mb": 15.832388877868652,
      "csv_over_parquet_ratio": 6.514387,
      "expected_rows": 1007286,
      "expected_columns": 19,
      "default_status": "ok",
      "pyarrow_status": "ok",
      "default_median_ms": 2002.3821,
      "pyarrow_median_ms": 156.1267,
      "speedup_default_over_pyarrow": 12.825366192970197,
      "winner": "pandas_pyarrow"
    },
    {
      "bucket_id": "small",
      "bucket_label": "Small CSV files",
      "input_id": "yellow_2020_09",
      "taxi_type": "yellow",
      "year": 2020,
      "month": "09",
      "csv_path": "data/derived-csv/yellow/2020/yellow_tripdata_2020-09.csv",
      "csv_size_bytes": 144379540,
      "csv_size_mb": 137.69105911254883,
      "parquet_size_bytes": 21381938,
      "parquet_size_mb": 20.39140510559082,
      "csv_over_parquet_ratio": 6.752407,
      "expected_rows": 1341017,
      "expected_columns": 19,
      "default_status": "ok",
      "pyarrow_status": "ok",
      "default_median_ms": 2322.4796,
      "pyarrow_median_ms": 199.1122,
      "speedup_default_over_pyarrow": 11.66417527404147,
      "winner": "pandas_pyarrow"
    },
    {
      "bucket_id": "small",
      "bucket_label": "Small CSV files",
      "input_id": "yellow_2021_01",
      "taxi_type": "yellow",
      "year": 2021,
      "month": "01",
      "csv_path": "data/derived-csv/yellow/2021/yellow_tripdata_2021-01.csv",
      "csv_size_bytes": 147424437,
      "csv_size_mb": 140.59489917755127,
      "parquet_size_bytes": 21686067,
      "parquet_size_mb": 20.681445121765137,
      "csv_over_parquet_ratio": 6.798118,
      "expected_rows": 1369769,
      "expected_columns": 19,
      "default_status": "ok",
      "pyarrow_status": "ok",
      "default_median_ms": 2494.9725,
      "pyarrow_median_ms": 275.4021,
      "speedup_default_over_pyarrow": 9.059380810821702,
      "winner": "pandas_pyarrow"
    },
    {
      "bucket_id": "small",
      "bucket_label": "Small CSV files",
      "input_id": "yellow_2021_02",
      "taxi_type": "yellow",
      "year": 2021,
      "month": "02",
      "csv_path": "data/derived-csv/yellow/2021/yellow_tripdata_2021-02.csv",
      "csv_size_bytes": 147690594,
      "csv_size_mb": 140.848726272583,
      "parquet_size_bytes": 21777258,
      "parquet_size_mb": 20.76841163635254,
      "csv_over_parquet_ratio": 6.781873,
      "expected_rows": 1371709,
      "expected_columns": 19,
      "default_status": "ok",
      "pyarrow_status": "ok",
      "default_median_ms": 2689.7707,
      "pyarrow_median_ms": 282.3121,
      "speedup_default_over_pyarrow": 9.527649363948623,
      "winner": "pandas_pyarrow"
    },
    {
      "bucket_id": "small",
      "bucket_label": "Small CSV files",
      "input_id": "yellow_2020_12",
      "taxi_type": "yellow",
      "year": 2020,
      "month": "12",
      "csv_path": "data/derived-csv/yellow/2020/yellow_tripdata_2020-12.csv",
      "csv_size_bytes": 157403868,
      "csv_size_mb": 150.1120262145996,
      "parquet_size_bytes": 23020036,
      "parquet_size_mb": 21.953617095947266,
      "csv_over_parquet_ratio": 6.83769,
      "expected_rows": 1461898,
      "expected_columns": 19,
      "default_status": "ok",
      "pyarrow_status": "ok",
      "default_median_ms": 2848.187,
      "pyarrow_median_ms": 228.2159,
      "speedup_default_over_pyarrow": 12.480230343284582,
      "winner": "pandas_pyarrow"
    },
    {
      "bucket_id": "small",
      "bucket_label": "Small CSV files",
      "input_id": "yellow_2020_11",
      "taxi_type": "yellow",
      "year": 2020,
      "month": "11",
      "csv_path": "data/derived-csv/yellow/2020/yellow_tripdata_2020-11.csv",
      "csv_size_bytes": 162630572,
      "csv_size_mb": 155.09659957885742,
      "parquet_size_bytes": 23583368,
      "parquet_size_mb": 22.49085235595703,
      "csv_over_parquet_ratio": 6.895986,
      "expected_rows": 1509000,
      "expected_columns": 19,
      "default_status": "ok",
      "pyarrow_status": "ok",
      "default_median_ms": 2779.742,
      "pyarrow_median_ms": 243.9536,
      "speedup_default_over_pyarrow": 11.39455207875596,
      "winner": "pandas_pyarrow"
    },
    {
      "bucket_id": "small",
      "bucket_label": "Small CSV files",
      "input_id": "yellow_2020_10",
      "taxi_type": "yellow",
      "year": 2020,
      "month": "10",
      "csv_path": "data/derived-csv/yellow/2020/yellow_tripdata_2020-10.csv",
      "csv_size_bytes": 181252408,
      "csv_size_mb": 172.85576629638672,
      "parquet_size_bytes": 26306876,
      "parquet_size_mb": 25.088191986083984,
      "csv_over_parquet_ratio": 6.889925,
      "expected_rows": 1681132,
      "expected_columns": 19,
      "default_status": "ok",
      "pyarrow_status": "ok",
      "default_median_ms": 3095.567,
      "pyarrow_median_ms": 248.1375,
      "speedup_default_over_pyarrow": 12.475208301848774,
      "winner": "pandas_pyarrow"
    },
    {
      "bucket_id": "small",
      "bucket_label": "Small CSV files",
      "input_id": "yellow_2021_03",
      "taxi_type": "yellow",
      "year": 2021,
      "month": "03",
      "csv_path": "data/derived-csv/yellow/2021/yellow_tripdata_2021-03.csv",
      "csv_size_bytes": 207707455,
      "csv_size_mb": 198.08526515960693,
      "parquet_size_bytes": 30007852,
      "parquet_size_mb": 28.617717742919922,
      "csv_over_parquet_ratio": 6.92177,
      "expected_rows": 1925152,
      "expected_columns": 19,
      "default_status": "ok",
      "pyarrow_status": "ok",
      "default_median_ms": 3537.3801,
      "pyarrow_median_ms": 293.2896,
      "speedup_default_over_pyarrow": 12.061048533599553,
      "winner": "pandas_pyarrow"
    },
    {
      "bucket_id": "small",
      "bucket_label": "Small CSV files",
      "input_id": "yellow_2021_04",
      "taxi_type": "yellow",
      "year": 2021,
      "month": "04",
      "csv_path": "data/derived-csv/yellow/2021/yellow_tripdata_2021-04.csv",
      "csv_size_bytes": 236675669,
      "csv_size_mb": 225.7115068435669,
      "parquet_size_bytes": 34018560,
      "parquet_size_mb": 32.442626953125,
      "csv_over_parquet_ratio": 6.957251,
      "expected_rows": 2171187,
      "expected_columns": 19,
      "default_status": "ok",
      "pyarrow_status": "ok",
      "default_median_ms": 3861.228,
      "pyarrow_median_ms": 460.7828,
      "speedup_default_over_pyarrow": 8.379713826123718,
      "winner": "pandas_pyarrow"
    },
    {
      "bucket_id": "medium",
      "bucket_label": "Medium CSV files",
      "input_id": "yellow_2022_01",
      "taxi_type": "yellow",
      "year": 2022,
      "month": "01",
      "csv_path": "data/derived-csv/yellow/2022/yellow_tripdata_2022-01.csv",
      "csv_size_bytes": 270012679,
      "csv_size_mb": 257.5041570663452,
      "parquet_size_bytes": 38139949,
      "parquet_size_mb": 36.37308979034424,
      "csv_over_parquet_ratio": 7.079524,
      "expected_rows": 2463931,
      "expected_columns": 19,
      "default_status": "ok",
      "pyarrow_status": "ok",
      "default_median_ms": 4546.3909,
      "pyarrow_median_ms": 373.905,
      "speedup_default_over_pyarrow": 12.159213971463341,
      "winner": "pandas_pyarrow"
    },
    {
      "bucket_id": "medium",
      "bucket_label": "Medium CSV files",
      "input_id": "yellow_2021_05",
      "taxi_type": "yellow",
      "year": 2021,
      "month": "05",
      "csv_path": "data/derived-csv/yellow/2021/yellow_tripdata_2021-05.csv",
      "csv_size_bytes": 273903047,
      "csv_size_mb": 261.21430110931396,
      "parquet_size_bytes": 38743682,
      "parquet_size_mb": 36.94885444641113,
      "csv_over_parquet_ratio": 7.069618,
      "expected_rows": 2507109,
      "expected_columns": 19,
      "default_status": "ok",
      "pyarrow_status": "ok",
      "default_median_ms": 4528.1895,
      "pyarrow_median_ms": 481.5687,
      "speedup_default_over_pyarrow": 9.402997952317085,
      "winner": "pandas_pyarrow"
    },
    {
      "bucket_id": "medium",
      "bucket_label": "Medium CSV files",
      "input_id": "yellow_2021_08",
      "taxi_type": "yellow",
      "year": 2021,
      "month": "08",
      "csv_path": "data/derived-csv/yellow/2021/yellow_tripdata_2021-08.csv",
      "csv_size_bytes": 305166477,
      "csv_size_mb": 291.0294313430786,
      "parquet_size_bytes": 43425907,
      "parquet_size_mb": 41.41417217254639,
      "csv_over_parquet_ratio": 7.027291,
      "expected_rows": 2788757,
      "expected_columns": 19,
      "default_status": "ok",
      "pyarrow_status": "ok",
      "default_median_ms": 4961.8812,
      "pyarrow_median_ms": 439.8339,
      "speedup_default_over_pyarrow": 11.281261403452529,
      "winner": "pandas_pyarrow"
    },
    {
      "bucket_id": "medium",
      "bucket_label": "Medium CSV files",
      "input_id": "yellow_2021_07",
      "taxi_type": "yellow",
      "year": 2021,
      "month": "07",
      "csv_path": "data/derived-csv/yellow/2021/yellow_tripdata_2021-07.csv",
      "csv_size_bytes": 308727112,
      "csv_size_mb": 294.4251174926758,
      "parquet_size_bytes": 43697690,
      "parquet_size_mb": 41.67336463928223,
      "csv_over_parquet_ratio": 7.065067,
      "expected_rows": 2821746,
      "expected_columns": 19,
      "default_status": "ok",
      "pyarrow_status": "ok",
      "default_median_ms": 5175.6259,
      "pyarrow_median_ms": 425.5638,
      "speedup_default_over_pyarrow": 12.161809580608125,
      "winner": "pandas_pyarrow"
    },
    {
      "bucket_id": "medium",
      "bucket_label": "Medium CSV files",
      "input_id": "yellow_2021_06",
      "taxi_type": "yellow",
      "year": 2021,
      "month": "06",
      "csv_path": "data/derived-csv/yellow/2021/yellow_tripdata_2021-06.csv",
      "csv_size_bytes": 310122373,
      "csv_size_mb": 295.7557420730591,
      "parquet_size_bytes": 44071592,
      "parquet_size_mb": 42.029945373535156,
      "csv_over_parquet_ratio": 7.036786,
      "expected_rows": 2834264,
      "expected_columns": 19,
      "default_status": "ok",
      "pyarrow_status": "ok",
      "default_median_ms": 5172.6549,
      "pyarrow_median_ms": 469.8434,
      "speedup_default_over_pyarrow": 11.009316934110387,
      "winner": "pandas_pyarrow"
    },
    {
      "bucket_id": "medium",
      "bucket_label": "Medium CSV files",
      "input_id": "yellow_2021_09",
      "taxi_type": "yellow",
      "year": 2021,
      "month": "09",
      "csv_path": "data/derived-csv/yellow/2021/yellow_tripdata_2021-09.csv",
      "csv_size_bytes": 324577596,
      "csv_size_mb": 309.541316986084,
      "parquet_size_bytes": 46125883,
      "parquet_size_mb": 43.98906993865967,
      "csv_over_parquet_ratio": 7.036778,
      "expected_rows": 2963793,
      "expected_columns": 19,
      "default_status": "ok",
      "pyarrow_status": "ok",
      "default_median_ms": 5608.3371,
      "pyarrow_median_ms": 503.4574,
      "speedup_default_over_pyarrow": 11.139645777378583,
      "winner": "pandas_pyarrow"
    },
    {
      "bucket_id": "medium",
      "bucket_label": "Medium CSV files",
      "input_id": "yellow_2020_03",
      "taxi_type": "yellow",
      "year": 2020,
      "month": "03",
      "csv_path": "data/derived-csv/yellow/2020/yellow_tripdata_2020-03.csv",
      "csv_size_bytes": 325651957,
      "csv_size_mb": 310.5659074783325,
      "parquet_size_bytes": 44442590,
      "parquet_size_mb": 42.38375663757324,
      "csv_over_parquet_ratio": 7.327475,
      "expected_rows": 3007687,
      "expected_columns": 19,
      "default_status": "ok",
      "pyarrow_status": "ok",
      "default_median_ms": 5659.8397,
      "pyarrow_median_ms": 438.2143,
      "speedup_default_over_pyarrow": 12.915689195902555,
      "winner": "pandas_pyarrow"
    },
    {
      "bucket_id": "medium",
      "bucket_label": "Medium CSV files",
      "input_id": "yellow_2022_02",
      "taxi_type": "yellow",
      "year": 2022,
      "month": "02",
      "csv_path": "data/derived-csv/yellow/2022/yellow_tripdata_2022-02.csv",
      "csv_size_bytes": 326821364,
      "csv_size_mb": 311.6811408996582,
      "parquet_size_bytes": 45616512,
      "parquet_size_mb": 43.5032958984375,
      "csv_over_parquet_ratio": 7.164541,
      "expected_rows": 2979431,
      "expected_columns": 19,
      "default_status": "ok",
      "pyarrow_status": "ok",
      "default_median_ms": 5346.3172,
      "pyarrow_median_ms": 498.4264,
      "speedup_default_over_pyarrow": 10.726392502483819,
      "winner": "pandas_pyarrow"
    },
    {
      "bucket_id": "medium",
      "bucket_label": "Medium CSV files",
      "input_id": "yellow_2022_08",
      "taxi_type": "yellow",
      "year": 2022,
      "month": "08",
      "csv_path": "data/derived-csv/yellow/2022/yellow_tripdata_2022-08.csv",
      "csv_size_bytes": 346312499,
      "csv_size_mb": 330.26933574676514,
      "parquet_size_bytes": 49717159,
      "parquet_size_mb": 47.41397762298584,
      "csv_over_parquet_ratio": 6.965653,
      "expected_rows": 3152677,
      "expected_columns": 19,
      "default_status": "ok",
      "pyarrow_status": "ok",
      "default_median_ms": 5849.5732,
      "pyarrow_median_ms": 525.8246,
      "speedup_default_over_pyarrow": 11.124571197315605,
      "winner": "pandas_pyarrow"
    },
    {
      "bucket_id": "medium",
      "bucket_label": "Medium CSV files",
      "input_id": "yellow_2022_07",
      "taxi_type": "yellow",
      "year": 2022,
      "month": "07",
      "csv_path": "data/derived-csv/yellow/2022/yellow_tripdata_2022-07.csv",
      "csv_size_bytes": 348545532,
      "csv_size_mb": 332.39892196655273,
      "parquet_size_bytes": 49367712,
      "parquet_size_mb": 47.080718994140625,
      "csv_over_parquet_ratio": 7.060192,
      "expected_rows": 3174394,
      "expected_columns": 19,
      "default_status": "ok",
      "pyarrow_status": "ok",
      "default_median_ms": 5676.1596,
      "pyarrow_median_ms": 488.418,
      "speedup_default_over_pyarrow": 11.621520091397123,
      "winner": "pandas_pyarrow"
    },
    {
      "bucket_id": "medium",
      "bucket_label": "Medium CSV files",
      "input_id": "yellow_2022_09",
      "taxi_type": "yellow",
      "year": 2022,
      "month": "09",
      "csv_path": "data/derived-csv/yellow/2022/yellow_tripdata_2022-09.csv",
      "csv_size_bytes": 350072567,
      "csv_size_mb": 333.85521602630615,
      "parquet_size_bytes": 49619957,
      "parquet_size_mb": 47.32127857208252,
      "csv_over_parquet_ratio": 7.055076,
      "expected_rows": 3183767,
      "expected_columns": 19,
      "default_status": "ok",
      "pyarrow_status": "ok",
      "default_median_ms": 5670.3058,
      "pyarrow_median_ms": 475.325,
      "speedup_default_over_pyarrow": 11.929323725871772,
      "winner": "pandas_pyarrow"
    },
    {
      "bucket_id": "medium",
      "bucket_label": "Medium CSV files",
      "input_id": "yellow_2021_12",
      "taxi_type": "yellow",
      "year": 2021,
      "month": "12",
      "csv_path": "data/derived-csv/yellow/2021/yellow_tripdata_2021-12.csv",
      "csv_size_bytes": 352682357,
      "csv_size_mb": 336.34410572052,
      "parquet_size_bytes": 49639052,
      "parquet_size_mb": 47.3394889831543,
      "csv_over_parquet_ratio": 7.104937,
      "expected_rows": 3214369,
      "expected_columns": 19,
      "default_status": "ok",
      "pyarrow_status": "ok",
      "default_median_ms": 5702.9868,
      "pyarrow_median_ms": 581.2945,
      "speedup_default_over_pyarrow": 9.810839084147537,
      "winner": "pandas_pyarrow"
    },
    {
      "bucket_id": "medium",
      "bucket_label": "Medium CSV files",
      "input_id": "yellow_2022_11",
      "taxi_type": "yellow",
      "year": 2022,
      "month": "11",
      "csv_path": "data/derived-csv/yellow/2022/yellow_tripdata_2022-11.csv",
      "csv_size_bytes": 357766338,
      "csv_size_mb": 341.1925678253174,
      "parquet_size_bytes": 50106631,
      "parquet_size_mb": 47.785407066345215,
      "csv_over_parquet_ratio": 7.1401,
      "expected_rows": 3252717,
      "expected_columns": 19,
      "default_status": "ok",
      "pyarrow_status": "ok",
      "default_median_ms": 5703.1971,
      "pyarrow_median_ms": 461.4,
      "speedup_default_over_pyarrow": 12.360635240572172,
      "winner": "pandas_pyarrow"
    },
    {
      "bucket_id": "medium",
      "bucket_label": "Medium CSV files",
      "input_id": "yellow_2022_12",
      "taxi_type": "yellow",
      "year": 2022,
      "month": "12",
      "csv_path": "data/derived-csv/yellow/2022/yellow_tripdata_2022-12.csv",
      "csv_size_bytes": 372035222,
      "csv_size_mb": 354.80043601989746,
      "parquet_size_bytes": 53640739,
      "parquet_size_mb": 51.155795097351074,
      "csv_over_parquet_ratio": 6.935684,
      "expected_rows": 3399549,
      "expected_columns": 19,
      "default_status": "ok",
      "pyarrow_status": "ok",
      "default_median_ms": 5811.4804,
      "pyarrow_median_ms": 472.8537,
      "speedup_default_over_pyarrow": 12.29022930348224,
      "winner": "pandas_pyarrow"
    },
    {
      "bucket_id": "medium",
      "bucket_label": "Medium CSV files",
      "input_id": "yellow_2021_10",
      "taxi_type": "yellow",
      "year": 2021,
      "month": "10",
      "csv_path": "data/derived-csv/yellow/2021/yellow_tripdata_2021-10.csv",
      "csv_size_bytes": 379854989,
      "csv_size_mb": 362.2579469680786,
      "parquet_size_bytes": 53286464,
      "parquet_size_mb": 50.81793212890625,
      "csv_over_parquet_ratio": 7.128546,
      "expected_rows": 3463504,
      "expected_columns": 19,
      "default_status": "ok",
      "pyarrow_status": "ok",
      "default_median_ms": 5954.2838,
      "pyarrow_median_ms": 562.5511,
      "speedup_default_over_pyarrow": 10.584431885387835,
      "winner": "pandas_pyarrow"
    },
    {
      "bucket_id": "medium",
      "bucket_label": "Medium CSV files",
      "input_id": "yellow_2021_11",
      "taxi_type": "yellow",
      "year": 2021,
      "month": "11",
      "csv_path": "data/derived-csv/yellow/2021/yellow_tripdata_2021-11.csv",
      "csv_size_bytes": 381161041,
      "csv_size_mb": 363.50349521636963,
      "parquet_size_bytes": 53100722,
      "parquet_size_mb": 50.64079475402832,
      "csv_over_parquet_ratio": 7.178076,
      "expected_rows": 3472949,
      "expected_columns": 19,
      "default_status": "ok",
      "pyarrow_status": "ok",
      "default_median_ms": 6903.204,
      "pyarrow_median_ms": 512.0456,
      "speedup_default_over_pyarrow": 13.481619605753862,
      "winner": "pandas_pyarrow"
    },
    {
      "bucket_id": "medium",
      "bucket_label": "Medium CSV files",
      "input_id": "yellow_2022_06",
      "taxi_type": "yellow",
      "year": 2022,
      "month": "06",
      "csv_path": "data/derived-csv/yellow/2022/yellow_tripdata_2022-06.csv",
      "csv_size_bytes": 390939980,
      "csv_size_mb": 372.82941818237305,
      "parquet_size_bytes": 55365184,
      "parquet_size_mb": 52.80035400390625,
      "csv_over_parquet_ratio": 7.061116,
      "expected_rows": 3558124,
      "expected_columns": 19,
      "default_status": "ok",
      "pyarrow_status": "ok",
      "default_median_ms": 6385.0686,
      "pyarrow_median_ms": 582.7307,
      "speedup_default_over_pyarrow": 10.95715156246273,
      "winner": "pandas_pyarrow"
    },
    {
      "bucket_id": "medium",
      "bucket_label": "Medium CSV files",
      "input_id": "yellow_2022_05",
      "taxi_type": "yellow",
      "year": 2022,
      "month": "05",
      "csv_path": "data/derived-csv/yellow/2022/yellow_tripdata_2022-05.csv",
      "csv_size_bytes": 394404241,
      "csv_size_mb": 376.1331949234009,
      "parquet_size_bytes": 55558821,
      "parquet_size_mb": 52.98502063751221,
      "csv_over_parquet_ratio": 7.098859,
      "expected_rows": 3588295,
      "expected_columns": 19,
      "default_status": "ok",
      "pyarrow_status": "ok",
      "default_median_ms": 6416.1768,
      "pyarrow_median_ms": 526.1517,
      "speedup_default_over_pyarrow": 12.194537811053353,
      "winner": "pandas_pyarrow"
    },
    {
      "bucket_id": "medium",
      "bucket_label": "Medium CSV files",
      "input_id": "yellow_2022_04",
      "taxi_type": "yellow",
      "year": 2022,
      "month": "04",
      "csv_path": "data/derived-csv/yellow/2022/yellow_tripdata_2022-04.csv",
      "csv_size_bytes": 395468333,
      "csv_size_mb": 377.14799213409424,
      "parquet_size_bytes": 55222692,
      "parquet_size_mb": 52.66446304321289,
      "csv_over_parquet_ratio": 7.161337,
      "expected_rows": 3599920,
      "expected_columns": 19,
      "default_status": "ok",
      "pyarrow_status": "ok",
      "default_median_ms": 6715.4548,
      "pyarrow_median_ms": 574.2942,
      "speedup_default_over_pyarrow": 11.69340522679839,
      "winner": "pandas_pyarrow"
    },
    {
      "bucket_id": "medium",
      "bucket_label": "Medium CSV files",
      "input_id": "yellow_2022_03",
      "taxi_type": "yellow",
      "year": 2022,
      "month": "03",
      "csv_path": "data/derived-csv/yellow/2022/yellow_tripdata_2022-03.csv",
      "csv_size_bytes": 398464295,
      "csv_size_mb": 380.00516414642334,
      "parquet_size_bytes": 55682369,
      "parquet_size_mb": 53.102845191955566,
      "csv_over_parquet_ratio": 7.156023,
      "expected_rows": 3627882,
      "expected_columns": 19,
      "default_status": "ok",
      "pyarrow_status": "ok",
      "default_median_ms": 6159.7442,
      "pyarrow_median_ms": 599.4416,
      "speedup_default_over_pyarrow": 10.275803681292723,
      "winner": "pandas_pyarrow"
    },
    {
      "bucket_id": "medium",
      "bucket_label": "Medium CSV files",
      "input_id": "yellow_2022_10",
      "taxi_type": "yellow",
      "year": 2022,
      "month": "10",
      "csv_path": "data/derived-csv/yellow/2022/yellow_tripdata_2022-10.csv",
      "csv_size_bytes": 404178000,
      "csv_size_mb": 385.4541778564453,
      "parquet_size_bytes": 57061938,
      "parquet_size_mb": 54.41850471496582,
      "csv_over_parquet_ratio": 7.083145,
      "expected_rows": 3675411,
      "expected_columns": 19,
      "default_status": "ok",
      "pyarrow_status": "ok",
      "default_median_ms": 6861.2241,
      "pyarrow_median_ms": 539.3258,
      "speedup_default_over_pyarrow": 12.721854025896778,
      "winner": "pandas_pyarrow"
    },
    {
      "bucket_id": "large",
      "bucket_label": "Large CSV files",
      "input_id": "yellow_2019_08",
      "taxi_type": "yellow",
      "year": 2019,
      "month": "08",
      "csv_path": "data/derived-csv/yellow/2019/yellow_tripdata_2019-08.csv",
      "csv_size_bytes": 657771137,
      "csv_size_mb": 627.2994394302368,
      "parquet_size_bytes": 89999675,
      "parquet_size_mb": 85.83037853240967,
      "csv_over_parquet_ratio": 7.308595,
      "expected_rows": 6073357,
      "expected_columns": 19,
      "default_status": "ok",
      "pyarrow_status": "ok",
      "default_median_ms": 9741.2564,
      "pyarrow_median_ms": 1075.7147,
      "speedup_default_over_pyarrow": 9.055613351755815,
      "winner": "pandas_pyarrow"
    },
    {
      "bucket_id": "large",
      "bucket_label": "Large CSV files",
      "input_id": "yellow_2020_02",
      "taxi_type": "yellow",
      "year": 2020,
      "month": "02",
      "csv_path": "data/derived-csv/yellow/2020/yellow_tripdata_2020-02.csv",
      "csv_size_bytes": 683448811,
      "csv_size_mb": 651.7875776290894,
      "parquet_size_bytes": 92134881,
      "parquet_size_mb": 87.86666965484619,
      "csv_over_parquet_ratio": 7.417916,
      "expected_rows": 6299367,
      "expected_columns": 19,
      "default_status": "ok",
      "pyarrow_status": "ok",
      "default_median_ms": 7075.965,
      "pyarrow_median_ms": 1575.8032,
      "speedup_default_over_pyarrow": 4.49038623604775,
      "winner": "pandas_pyarrow"
    },
    {
      "bucket_id": "large",
      "bucket_label": "Large CSV files",
      "input_id": "yellow_2019_07",
      "taxi_type": "yellow",
      "year": 2019,
      "month": "07",
      "csv_path": "data/derived-csv/yellow/2019/yellow_tripdata_2019-07.csv",
      "csv_size_bytes": 683547392,
      "csv_size_mb": 651.881591796875,
      "parquet_size_bytes": 93877343,
      "parquet_size_mb": 89.52841091156006,
      "csv_over_parquet_ratio": 7.281282,
      "expected_rows": 6310419,
      "expected_columns": 19,
      "default_status": "ok",
      "pyarrow_status": "ok",
      "default_median_ms": 7703.8931,
      "pyarrow_median_ms": 1217.9116,
      "speedup_default_over_pyarrow": 6.325494477595911,
      "winner": "pandas_pyarrow"
    },
    {
      "bucket_id": "large",
      "bucket_label": "Large CSV files",
      "input_id": "yellow_2020_01",
      "taxi_type": "yellow",
      "year": 2020,
      "month": "01",
      "csv_path": "data/derived-csv/yellow/2020/yellow_tripdata_2020-01.csv",
      "csv_size_bytes": 694483010,
      "csv_size_mb": 662.3106098175049,
      "parquet_size_bytes": 93562858,
      "parquet_size_mb": 89.22849464416504,
      "csv_over_parquet_ratio": 7.422636,
      "expected_rows": 6405008,
      "expected_columns": 19,
      "default_status": "ok",
      "pyarrow_status": "ok",
      "default_median_ms": 7176.7811,
      "pyarrow_median_ms": 908.8489,
      "speedup_default_over_pyarrow": 7.896561353597942,
      "winner": "pandas_pyarrow"
    },
    {
      "bucket_id": "large",
      "bucket_label": "Large CSV files",
      "input_id": "yellow_2019_09",
      "taxi_type": "yellow",
      "year": 2019,
      "month": "09",
      "csv_path": "data/derived-csv/yellow/2019/yellow_tripdata_2019-09.csv",
      "csv_size_bytes": 712192048,
      "csv_size_mb": 679.1992645263672,
      "parquet_size_bytes": 97110325,
      "parquet_size_mb": 92.61162281036377,
      "csv_over_parquet_ratio": 7.333845,
      "expected_rows": 6567788,
      "expected_columns": 19,
      "default_status": "ok",
      "pyarrow_status": "ok",
      "default_median_ms": 10317.5938,
      "pyarrow_median_ms": 1210.5999,
      "speedup_default_over_pyarrow": 8.522711591170626,
      "winner": "pandas_pyarrow"
    },
    {
      "bucket_id": "large",
      "bucket_label": "Large CSV files",
      "input_id": "yellow_2019_11",
      "taxi_type": "yellow",
      "year": 2019,
      "month": "11",
      "csv_path": "data/derived-csv/yellow/2019/yellow_tripdata_2019-11.csv",
      "csv_size_bytes": 746063129,
      "csv_size_mb": 711.5012445449829,
      "parquet_size_bytes": 100872983,
      "parquet_size_mb": 96.19997310638428,
      "csv_over_parquet_ratio": 7.396065,
      "expected_rows": 6878111,
      "expected_columns": 19,
      "default_status": "ok",
      "pyarrow_status": "ok",
      "default_median_ms": 7627.9525,
      "pyarrow_median_ms": 1169.4443,
      "speedup_default_over_pyarrow": 6.52271553249693,
      "winner": "pandas_pyarrow"
    },
    {
      "bucket_id": "large",
      "bucket_label": "Large CSV files",
      "input_id": "yellow_2019_12",
      "taxi_type": "yellow",
      "year": 2019,
      "month": "12",
      "csv_path": "data/derived-csv/yellow/2019/yellow_tripdata_2019-12.csv",
      "csv_size_bytes": 747730328,
      "csv_size_mb": 713.0912094116211,
      "parquet_size_bytes": 101044777,
      "parquet_size_mb": 96.36380863189697,
      "csv_over_parquet_ratio": 7.39999,
      "expected_rows": 6896317,
      "expected_columns": 19,
      "default_status": "ok",
      "pyarrow_status": "ok",
      "default_median_ms": 7724.0117,
      "pyarrow_median_ms": 1168.9606,
      "speedup_default_over_pyarrow": 6.607589426025137,
      "winner": "pandas_pyarrow"
    },
    {
      "bucket_id": "large",
      "bucket_label": "Large CSV files",
      "input_id": "yellow_2019_06",
      "taxi_type": "yellow",
      "year": 2019,
      "month": "06",
      "csv_path": "data/derived-csv/yellow/2019/yellow_tripdata_2019-06.csv",
      "csv_size_bytes": 755671945,
      "csv_size_mb": 720.6649255752563,
      "parquet_size_bytes": 102903344,
      "parquet_size_mb": 98.13627624511719,
      "csv_over_parquet_ratio": 7.343512,
      "expected_rows": 6971560,
      "expected_columns": 19,
      "default_status": "ok",
      "pyarrow_status": "ok",
      "default_median_ms": 10558.2765,
      "pyarrow_median_ms": 1232.0711,
      "speedup_default_over_pyarrow": 8.569535069851083,
      "winner": "pandas_pyarrow"
    },
    {
      "bucket_id": "large",
      "bucket_label": "Large CSV files",
      "input_id": "yellow_2019_02",
      "taxi_type": "yellow",
      "year": 2019,
      "month": "02",
      "csv_path": "data/derived-csv/yellow/2019/yellow_tripdata_2019-02.csv",
      "csv_size_bytes": 763317886,
      "csv_size_mb": 727.9566631317139,
      "parquet_size_bytes": 103356025,
      "parquet_size_mb": 98.56798648834229,
      "csv_over_parquet_ratio": 7.385325,
      "expected_rows": 7049370,
      "expected_columns": 19,
      "default_status": "ok",
      "pyarrow_status": "ok",
      "default_median_ms": 11710.5365,
      "pyarrow_median_ms": 1427.6657,
      "speedup_default_over_pyarrow": 8.20257606525113,
      "winner": "pandas_pyarrow"
    },
    {
      "bucket_id": "large",
      "bucket_label": "Large CSV files",
      "input_id": "yellow_2019_10",
      "taxi_type": "yellow",
      "year": 2019,
      "month": "10",
      "csv_path": "data/derived-csv/yellow/2019/yellow_tripdata_2019-10.csv",
      "csv_size_bytes": 782626216,
      "csv_size_mb": 746.3705215454102,
      "parquet_size_bytes": 106293373,
      "parquet_size_mb": 101.36925983428955,
      "csv_over_parquet_ratio": 7.362888,
      "expected_rows": 7213891,
      "expected_columns": 19,
      "default_status": "ok",
      "pyarrow_status": "ok",
      "default_median_ms": 11240.1506,
      "pyarrow_median_ms": 1357.6868,
      "speedup_default_over_pyarrow": 8.278898049240812,
      "winner": "pandas_pyarrow"
    },
    {
      "bucket_id": "giant",
      "bucket_label": "Giant CSV files",
      "input_id": "yellow_2019_04",
      "taxi_type": "yellow",
      "year": 2019,
      "month": "04",
      "csv_path": "data/derived-csv/yellow/2019/yellow_tripdata_2019-04.csv",
      "csv_size_bytes": 810387251,
      "csv_size_mb": 772.8455076217651,
      "parquet_size_bytes": 110139137,
      "parquet_size_mb": 105.03686618804932,
      "csv_over_parquet_ratio": 7.35785,
      "expected_rows": 7475949,
      "expected_columns": 19,
      "default_status": "ok",
      "pyarrow_status": "ok",
      "default_median_ms": 14127.9014,
      "pyarrow_median_ms": 1373.2155,
      "speedup_default_over_pyarrow": 10.288189581314805,
      "winner": "pandas_pyarrow"
    },
    {
      "bucket_id": "giant",
      "bucket_label": "Giant CSV files",
      "input_id": "yellow_2019_01",
      "taxi_type": "yellow",
      "year": 2019,
      "month": "01",
      "csv_path": "data/derived-csv/yellow/2019/yellow_tripdata_2019-01.csv",
      "csv_size_bytes": 810646679,
      "csv_size_mb": 773.0929174423218,
      "parquet_size_bytes": 110439634,
      "parquet_size_mb": 105.32344245910645,
      "csv_over_parquet_ratio": 7.340179,
      "expected_rows": 7696617,
      "expected_columns": 19,
      "default_status": "ok",
      "pyarrow_status": "ok",
      "default_median_ms": 9593.4812,
      "pyarrow_median_ms": 1704.9464,
      "speedup_default_over_pyarrow": 5.62685208168421,
      "winner": "pandas_pyarrow"
    },
    {
      "bucket_id": "giant",
      "bucket_label": "Giant CSV files",
      "input_id": "yellow_2019_05",
      "taxi_type": "yellow",
      "year": 2019,
      "month": "05",
      "csv_path": "data/derived-csv/yellow/2019/yellow_tripdata_2019-05.csv",
      "csv_size_bytes": 823824137,
      "csv_size_mb": 785.6599206924438,
      "parquet_size_bytes": 111478943,
      "parquet_size_mb": 106.31460475921631,
      "csv_over_parquet_ratio": 7.389953,
      "expected_rows": 7598445,
      "expected_columns": 19,
      "default_status": "ok",
      "pyarrow_status": "ok",
      "default_median_ms": 11417.6338,
      "pyarrow_median_ms": 1947.9705,
      "speedup_default_over_pyarrow": 5.861297078164172,
      "winner": "pandas_pyarrow"
    },
    {
      "bucket_id": "giant",
      "bucket_label": "Giant CSV files",
      "input_id": "yellow_2019_03",
      "taxi_type": "yellow",
      "year": 2019,
      "month": "03",
      "csv_path": "data/derived-csv/yellow/2019/yellow_tripdata_2019-03.csv",
      "csv_size_bytes": 852779445,
      "csv_size_mb": 813.2738542556763,
      "parquet_size_bytes": 116017372,
      "parquet_size_mb": 110.64278793334961,
      "csv_over_parquet_ratio": 7.350446,
      "expected_rows": 7866620,
      "expected_columns": 19,
      "default_status": "ok",
      "pyarrow_status": "ok",
      "default_median_ms": 13184.6247,
      "pyarrow_median_ms": 1838.4148,
      "speedup_default_over_pyarrow": 7.1717355082215395,
      "winner": "pandas_pyarrow"
    }
  ]
}