{ "python": "3.11.16", "os": "Darwin 25.6.0", "architecture": "arm64", "cpu": "Apple M5 Max", "logical_cpus": 18, "ram_gib": 48.0, "threads_requested": 4, "rows": 5000000, "parquet_bytes": 114386913, "uncompressed_parquet_page_bytes": 228863315, "pyarrow_version": "26.0.0", "execution_order": [ "polars", "pandas", "dask", "duckdb" ], "measurements": [ { "engine": "polars", "version": "2.0.0", "first_seconds": 0.017662208003457636, "repeat_seconds": 0.015462541981833056, "peak_rss_mib": 140.375, "result": [ [ "C27", 6952347.9 ], [ "C08", 6899831.350000001 ], [ "C22", 6885085.93 ], [ "C03", 6879975.68 ], [ "C02", 6861261.3 ], [ "C21", 6853752.640000001 ], [ "C24", 6850547.76 ], [ "C01", 6847024.71 ], [ "C26", 6845673.640000001 ], [ "C13", 6836699.29 ] ] }, { "engine": "pandas", "version": "3.0.6", "first_seconds": 0.06699004201800562, "repeat_seconds": 0.04151404098956846, "peak_rss_mib": 389.375, "result": [ [ "C27", 6952347.9 ], [ "C08", 6899831.35 ], [ "C22", 6885085.93 ], [ "C03", 6879975.68 ], [ "C02", 6861261.3 ], [ "C21", 6853752.64 ], [ "C24", 6850547.76 ], [ "C01", 6847024.71 ], [ "C26", 6845673.64 ], [ "C13", 6836699.29 ] ] }, { "engine": "dask", "version": "2026.8.0", "first_seconds": 0.03206379199400544, "repeat_seconds": 0.02364529197802767, "peak_rss_mib": 390.234375, "result": [ [ "C27", 6952347.9 ], [ "C08", 6899831.35 ], [ "C22", 6885085.93 ], [ "C03", 6879975.68 ], [ "C02", 6861261.3 ], [ "C21", 6853752.64 ], [ "C24", 6850547.76 ], [ "C01", 6847024.71 ], [ "C26", 6845673.64 ], [ "C13", 6836699.29 ] ] }, { "engine": "duckdb", "version": "1.4.5", "first_seconds": 0.17827337500057183, "repeat_seconds": 0.01829333300702274, "peak_rss_mib": 129.078125, "result": [ [ "C27", 6952347.9 ], [ "C08", 6899831.35 ], [ "C22", 6885085.93 ], [ "C03", 6879975.68 ], [ "C02", 6861261.3 ], [ "C21", 6853752.64 ], [ "C24", 6850547.76 ], [ "C01", 6847024.71 ], [ "C26", 6845673.64 ], [ "C13", 6836699.29 ] ] } ], "duckdb_profile": "\u250c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2510\n\u2502\u250c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2510\u2502\n\u2502\u2502 Query Profiling Information \u2502\u2502\n\u2502\u2514\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2518\u2502\n\u2514\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2518\nEXPLAIN ANALYZE SELECT country, SUM(amount_cents) / 100.0 AS revenue FROM read_parquet(?) WHERE event_time >= TIMESTAMP '2026-09-01' AND event_time < TIMESTAMP '2026-10-01' AND event_type = 'purchase' GROUP BY country ORDER BY revenue DESC, country LIMIT 10 \n\u250c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2510\n\u2502\u250c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2510\u2502\n\u2502\u2502 Total Time: 0.0195s \u2502\u2502\n\u2502\u2514\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2518\u2502\n\u2514\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2518\n\u250c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2510\n\u2502 QUERY \u2502\n\u2514\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u252c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2518\n\u250c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2534\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2510\n\u2502 EXPLAIN_ANALYZE \u2502\n\u2502 \u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500 \u2502\n\u2502 0 rows \u2502\n\u2502 (0.00s) \u2502\n\u2514\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u252c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2518\n\u250c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2534\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2510\n\u2502 TOP_N \u2502\n\u2502 \u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500 \u2502\n\u2502 Top: 10 \u2502\n\u2502 \u2502\n\u2502 Order By: \u2502\n\u2502 (sum(read_parquet \u2502\n\u2502 .amount_cents) / 100.0) \u2502\n\u2502 DESC \u2502\n\u2502 read_parquet.country ASC \u2502\n\u2502 \u2502\n\u2502 10 rows \u2502\n\u2502 (0.00s) \u2502\n\u2514\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u252c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2518\n\u250c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2534\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2510\n\u2502 PROJECTION \u2502\n\u2502 \u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500 \u2502\n\u2502 country \u2502\n\u2502 revenue \u2502\n\u2502 \u2502\n\u2502 30 rows \u2502\n\u2502 (0.00s) \u2502\n\u2514\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u252c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2518\n\u250c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2534\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2510\n\u2502 HASH_GROUP_BY \u2502\n\u2502 \u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500 \u2502\n\u2502 Groups: #0 \u2502\n\u2502 Aggregates: sum(#1) \u2502\n\u2502 \u2502\n\u2502 30 rows \u2502\n\u2502 (0.00s) \u2502\n\u2514\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u252c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2518\n\u250c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2534\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2510\n\u2502 PROJECTION \u2502\n\u2502 \u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500 \u2502\n\u2502 country \u2502\n\u2502 amount_cents \u2502\n\u2502 \u2502\n\u2502 407,208 rows \u2502\n\u2502 (0.00s) \u2502\n\u2514\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u252c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2518\n\u250c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2534\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2510\n\u2502 TABLE_SCAN \u2502\n\u2502 \u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500 \u2502\n\u2502 Function: \u2502\n\u2502 READ_PARQUET \u2502\n\u2502 \u2502\n\u2502 Projections: \u2502\n\u2502 country \u2502\n\u2502 amount_cents \u2502\n\u2502 \u2502\n\u2502 Filters: \u2502\n\u2502 event_time>='2026-09-01 00\u2502\n\u2502 :00:00'::TIMESTAMP AND \u2502\n\u2502 event_time<'2026-10-01 00\u2502\n\u2502 :00:00'::TIMESTAMP \u2502\n\u2502 event_type='purchase' \u2502\n\u2502 \u2502\n\u2502 Total Files Read: 4 \u2502\n\u2502 \u2502\n\u2502 407,208 rows \u2502\n\u2502 (0.07s) \u2502\n\u2514\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2518\n", "method": "One fresh process per engine; two read/filter/group/sort/materialize runs after imports; no OS cache flush. RSS is lifetime peak including imports. Four files, null-free synthetic rows, low-cardinality aggregation. pandas/PyArrow and Dask receive column selections and scan filters; Polars uses lazy streaming; Dask uses Arrow filesystem and local threads. Not a spill test. Sorted results compared with relative tolerance 1e-12, absolute 1e-8 for final floating-point currency conversion." }