[ { "id": "preview", "label": "Read observations", "sql": "SELECT * FROM data ORDER BY observation_id", "columns": [ { "name": "observation_id", "type": "BIGINT" }, { "name": "station", "type": "VARCHAR" }, { "name": "observed_at", "type": "TIMESTAMP" }, { "name": "temperature_c", "type": "DOUBLE" } ], "rows": [ [ "1", "North", "2026-01-01 00:00:00", "5.0" ], [ "2", "South", "2026-01-01 03:00:00", "6.0" ], [ "3", "North", "2026-01-01 06:00:00", "7.0" ], [ "4", "South", "2026-01-01 09:00:00", "8.0" ], [ "5", "North", "2026-01-01 12:00:00", "9.0" ], [ "6", "South", "2026-01-01 15:00:00", "10.0" ], [ "7", "North", "2026-01-02 00:00:00", "11.0" ], [ "8", "South", "2026-01-02 03:00:00", "12.0" ], [ "9", "North", "2026-01-02 06:00:00", "13.0" ], [ "10", "South", "2026-01-02 09:00:00", "14.0" ], [ "11", "North", "2026-01-02 12:00:00", "15.0" ], [ "12", "South", "2026-01-02 15:00:00", "16.0" ], [ "13", "North", "2026-01-01 21:00:00", "17.0" ], [ "14", "South", "2026-01-03 03:00:00", "18.0" ], [ "15", "North", "2026-01-03 06:00:00", "19.0" ], [ "16", "South", "2026-01-03 09:00:00", "20.0" ], [ "17", "North", "2026-01-03 12:00:00", "21.0" ], [ "18", "South", "2026-01-03 15:00:00", "22.0" ] ], "duckdb": "\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 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__internal_decompress_integ\u2502\n\u2502 ral_bigint(#0, 1) \u2502\n\u2502 #1 \u2502\n\u2502 #2 \u2502\n\u2502 #3 \u2502\n\u2502 \u2502\n\u2502 ~0 rows \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 ORDER_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 memory.main.\"data\" \u2502\n\u2502 .observation_id ASC \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__internal_compress_integra\u2502\n\u2502 l_utinyint(#0, 1) \u2502\n\u2502 #1 \u2502\n\u2502 #2 \u2502\n\u2502 #3 \u2502\n\u2502 \u2502\n\u2502 ~18 rows \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 PARQUET_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 PARQUET_SCAN \u2502\n\u2502 \u2502\n\u2502 Projections: \u2502\n\u2502 observation_id \u2502\n\u2502 station \u2502\n\u2502 observed_at \u2502\n\u2502 temperature_c \u2502\n\u2502 \u2502\n\u2502 ~18 rows \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", "datafusion": { "logical": "Sort: data.observation_id ASC NULLS LAST\n Projection: data.observation_id, data.station, data.observed_at, data.temperature_c\n TableScan: data", "optimized": "Sort: data.observation_id ASC NULLS LAST\n TableScan: data projection=[observation_id, station, observed_at, temperature_c]", "physical": "SortExec: expr=[observation_id@0 ASC NULLS LAST], preserve_partitioning=[false]\n DataSourceExec: file_groups={1 group: [[var/folders/sh/6ynfpx_s4j1cd_s7rrtdx2040000gn/T/columnar-engines-ts_c6fjj/weather.parquet]]}, projection=[observation_id, station, observed_at, temperature_c], file_type=parquet, sort_order_for_reorder=[observation_id@0 ASC NULLS LAST]\n" } }, { "id": "filter", "label": "Select warm observations", "sql": "SELECT observation_id, station, temperature_c FROM data WHERE temperature_c >= 18 ORDER BY observation_id", "columns": [ { "name": "observation_id", "type": "BIGINT" }, { "name": "station", "type": "VARCHAR" }, { "name": "temperature_c", "type": "DOUBLE" } ], "rows": [ [ "14", "South", "18.0" ], [ "15", "North", "19.0" ], [ "16", "South", "20.0" ], [ "17", "North", "21.0" ], [ "18", "South", "22.0" ] ], "duckdb": "\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 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__internal_decompress_integ\u2502\n\u2502 ral_bigint(#0, 1) \u2502\n\u2502 #1 \u2502\n\u2502 #2 \u2502\n\u2502 \u2502\n\u2502 ~0 rows \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 ORDER_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 memory.main.\"data\" \u2502\n\u2502 .observation_id ASC \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__internal_compress_integra\u2502\n\u2502 l_utinyint(#0, 1) \u2502\n\u2502 #1 \u2502\n\u2502 #2 \u2502\n\u2502 \u2502\n\u2502 ~3 rows \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 PARQUET_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 PARQUET_SCAN \u2502\n\u2502 \u2502\n\u2502 Projections: \u2502\n\u2502 observation_id \u2502\n\u2502 station \u2502\n\u2502 temperature_c \u2502\n\u2502 \u2502\n\u2502 Filters: \u2502\n\u2502 temperature_c>=18.0 \u2502\n\u2502 \u2502\n\u2502 ~3 rows \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", "datafusion": { "logical": "Sort: data.observation_id ASC NULLS LAST\n Projection: data.observation_id, data.station, data.temperature_c\n Filter: data.temperature_c >= Int64(18)\n TableScan: data", "optimized": "Sort: data.observation_id ASC NULLS LAST\n Filter: data.temperature_c >= Float64(18)\n TableScan: data projection=[observation_id, station, temperature_c], partial_filters=[data.temperature_c >= Float64(18)]", "physical": "SortPreservingMergeExec: [observation_id@0 ASC NULLS LAST]\n SortExec: expr=[observation_id@0 ASC NULLS LAST], preserve_partitioning=[true]\n FilterExec: temperature_c@2 >= 18\n RepartitionExec: partitioning=RoundRobinBatch(2), input_partitions=1\n DataSourceExec: file_groups={1 group: [[var/folders/sh/6ynfpx_s4j1cd_s7rrtdx2040000gn/T/columnar-engines-ts_c6fjj/weather.parquet]]}, projection=[observation_id, station, temperature_c], file_type=parquet, predicate=temperature_c@3 >= 18, pruning_predicate=temperature_c_null_count@1 != row_count@2 AND temperature_c_max@0 >= 18, required_guarantees=[]\n" } }, { "id": "aggregate", "label": "Group by station", "sql": "SELECT station, count(*) AS observations, avg(temperature_c) AS average_c FROM data GROUP BY station ORDER BY station", "columns": [ { "name": "station", "type": "VARCHAR" }, { "name": "observations", "type": "BIGINT" }, { "name": "average_c", "type": "DOUBLE" } ], "rows": [ [ "North", "9", "13.0" ], [ "South", "9", "14.0" ] ], "duckdb": "\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 ORDER_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 memory.main.\"data\".station\u2502\n\u2502 ASC \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 \u2502\n\u2502 Aggregates: \u2502\n\u2502 count_star() \u2502\n\u2502 avg(#1) \u2502\n\u2502 \u2502\n\u2502 ~11 rows \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 station \u2502\n\u2502 temperature_c \u2502\n\u2502 \u2502\n\u2502 ~18 rows \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 PARQUET_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 PARQUET_SCAN \u2502\n\u2502 \u2502\n\u2502 Projections: \u2502\n\u2502 station \u2502\n\u2502 temperature_c \u2502\n\u2502 \u2502\n\u2502 ~18 rows \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", "datafusion": { "logical": "Sort: data.station ASC NULLS LAST\n Projection: data.station, count(Int64(1)) AS count(*) AS observations, avg(data.temperature_c) AS average_c\n Aggregate: groupBy=[[data.station]], aggr=[[count(Int64(1)), avg(data.temperature_c)]]\n TableScan: data", "optimized": "Sort: data.station ASC NULLS LAST\n Projection: data.station, count(Int64(1)) AS count(*) AS observations, avg(data.temperature_c) AS average_c\n Aggregate: groupBy=[[data.station]], aggr=[[count(Int64(1)), avg(data.temperature_c)]]\n TableScan: data projection=[station, temperature_c]", "physical": "SortPreservingMergeExec: [station@0 ASC NULLS LAST]\n SortExec: expr=[station@0 ASC NULLS LAST], preserve_partitioning=[true]\n ProjectionExec: expr=[station@0 as station, count(Int64(1))@1 as observations, avg(data.temperature_c)@2 as average_c]\n AggregateExec: mode=FinalPartitioned, gby=[station@0 as station], aggr=[count(Int64(1)), avg(data.temperature_c)]\n RepartitionExec: partitioning=Hash([station@0], 2), input_partitions=1\n AggregateExec: mode=Partial, gby=[station@0 as station], aggr=[count(Int64(1)), avg(data.temperature_c)]\n DataSourceExec: file_groups={1 group: [[var/folders/sh/6ynfpx_s4j1cd_s7rrtdx2040000gn/T/columnar-engines-ts_c6fjj/weather.parquet]]}, projection=[station, temperature_c], file_type=parquet\n" } }, { "id": "join", "label": "Join station descriptions", "sql": "SELECT d.observation_id, s.description, d.temperature_c FROM data d JOIN stations s USING (station) WHERE d.temperature_c >= 18 ORDER BY d.observation_id", "columns": [ { "name": "observation_id", "type": "BIGINT" }, { "name": "description", "type": "VARCHAR" }, { "name": "temperature_c", "type": "DOUBLE" } ], "rows": [ [ "14", "Southern site", "18.0" ], [ "15", "Northern site", "19.0" ], [ "16", "Southern site", "20.0" ], [ "17", "Northern site", "21.0" ], [ "18", "Southern site", "22.0" ] ], "duckdb": "\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 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__internal_decompress_integ\u2502\n\u2502 ral_bigint(#0, 1) \u2502\n\u2502 #1 \u2502\n\u2502 #2 \u2502\n\u2502 \u2502\n\u2502 ~0 rows \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 ORDER_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 d.observation_id ASC \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__internal_compress_integra\u2502\n\u2502 l_utinyint(#0, 1) \u2502\n\u2502 #1 \u2502\n\u2502 #2 \u2502\n\u2502 \u2502\n\u2502 ~3 rows \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 observation_id \u2502\n\u2502 description \u2502\n\u2502 temperature_c \u2502\n\u2502 \u2502\n\u2502 ~3 rows \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_JOIN \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 Join Type: INNER \u2502\n\u2502 \u2502\n\u2502 Conditions: \u251c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2510\n\u2502 station = station \u2502 \u2502\n\u2502 \u2502 \u2502\n\u2502 ~3 rows \u2502 \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 \u2502\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\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 PARQUET_SCAN \u2502\u2502 COLUMN_DATA_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\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\u2502 \u2502\n\u2502 PARQUET_SCAN \u2502\u2502 \u2502\n\u2502 \u2502\u2502 \u2502\n\u2502 Projections: \u2502\u2502 \u2502\n\u2502 observation_id \u2502\u2502 \u2502\n\u2502 station \u2502\u2502 \u2502\n\u2502 temperature_c \u2502\u2502 \u2502\n\u2502 \u2502\u2502 \u2502\n\u2502 Filters: \u2502\u2502 \u2502\n\u2502 temperature_c>=18.0 \u2502\u2502 \u2502\n\u2502 \u2502\u2502 \u2502\n\u2502 ~3 rows \u2502\u2502 ~2 rows \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\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", "datafusion": { "logical": "Sort: d.observation_id ASC NULLS LAST\n Projection: d.observation_id, s.description, d.temperature_c\n Filter: d.temperature_c >= Int64(18)\n Inner Join: Using d.station = s.station\n SubqueryAlias: d\n TableScan: data\n SubqueryAlias: s\n TableScan: stations", "optimized": "Sort: d.observation_id ASC NULLS LAST\n Projection: d.observation_id, s.description, d.temperature_c\n Inner Join: d.station = CAST(s.station AS Utf8View)\n SubqueryAlias: d\n Filter: data.temperature_c >= Float64(18)\n TableScan: data projection=[observation_id, station, temperature_c], partial_filters=[data.temperature_c >= Float64(18)]\n SubqueryAlias: s\n TableScan: stations projection=[station, description]", "physical": "SortPreservingMergeExec: [observation_id@0 ASC NULLS LAST]\n SortExec: expr=[observation_id@0 ASC NULLS LAST], preserve_partitioning=[true]\n HashJoinExec: mode=CollectLeft, join_type=Inner, on=[(CAST(s.station AS Utf8View)@2, station@1)], projection=[observation_id@3, description@1, temperature_c@5]\n ProjectionExec: expr=[station@0 as station, description@1 as description, CAST(station@0 AS Utf8View) as CAST(s.station AS Utf8View)]\n DataSourceExec: partitions=1, partition_sizes=[1]\n FilterExec: temperature_c@2 >= 18\n RepartitionExec: partitioning=RoundRobinBatch(2), input_partitions=1\n DataSourceExec: file_groups={1 group: [[var/folders/sh/6ynfpx_s4j1cd_s7rrtdx2040000gn/T/columnar-engines-ts_c6fjj/weather.parquet]]}, projection=[observation_id, station, temperature_c], file_type=parquet, predicate=temperature_c@3 >= 18 AND DynamicFilter [ empty ], pruning_predicate=temperature_c_null_count@1 != row_count@2 AND temperature_c_max@0 >= 18, required_guarantees=[]\n" } } ]