task2 - Details for Query 6

Details for Query 6

Submitted Time: 2024/12/04 20:22:49
Duration: 21 s
Succeeded Jobs: 8 9

Show the Stage ID and Task ID that corresponds to the max metric

digraph G { 0 [labelType="html" label="Execute InsertIntoHadoopFsRelationCommand number of written files: 1 written output: 661.0 B number of output rows: 30 number of dynamic part: 0"]; 1 [labelType="html" label=" Coalesce "]; subgraph cluster2 { isCluster="true"; label="WholeStageCodegen (8)\n \nduration: 2 ms"; 3 [labelType="html" label="Sort sort time: 0 ms peak memory: 1921.9 MiB spill size: 0.0 B"]; } 4 [labelType="html" label="Exchange shuffle records written: 30 shuffle write time total (min, med, max (stageId: taskId)) 12 ms (0 ms, 0 ms, 0 ms (stage 26.0: task 1638)) records read: 30 local bytes read: 2.5 KiB fetch wait time: 0 ms local blocks read: 30 data size total (min, med, max (stageId: taskId)) 1440.0 B (0.0 B, 0.0 B, 144.0 B (stage 26.0: task 1676)) shuffle bytes written total (min, med, max (stageId: taskId)) 2.5 KiB (0.0 B, 0.0 B, 258.0 B (stage 26.0: task 1676))"]; subgraph cluster5 { isCluster="true"; label="WholeStageCodegen (7)\n \nduration: total (min, med, max (stageId: taskId))\n372 ms (0 ms, 1 ms, 5 ms (stage 21.0: task 1438))"; 6 [labelType="html" label="HashAggregate time in aggregation build total (min, med, max (stageId: taskId)) 103 ms (0 ms, 0 ms, 3 ms (stage 21.0: task 1438)) peak memory total (min, med, max (stageId: taskId)) 3.2 GiB (256.0 KiB, 256.0 KiB, 64.3 MiB (stage 21.0: task 1438)) number of output rows: 60 avg hash probe bucket list iters (min, med, max (stageId: taskId)): (1, 1, 1 (stage 21.0: task 1438))"]; } 7 [labelType="html" label="Exchange shuffle records written: 6,000 shuffle write time total (min, med, max (stageId: taskId)) 665 ms (3 ms, 3 ms, 4 ms (stage 20.0: task 1290)) records read: 12,000 local bytes read total (min, med, max (stageId: taskId)) 860.1 KiB (0.0 B, 0.0 B, 24.0 KiB (stage 21.0: task 1479)) fetch wait time total (min, med, max (stageId: taskId)) 0 ms (0 ms, 0 ms, 0 ms (stage 21.0: task 1438)) local blocks read: 10,000 data size total (min, med, max (stageId: taskId)) 281.3 KiB (1440.0 B, 1440.0 B, 1440.0 B (stage 20.0: task 1238)) shuffle bytes written total (min, med, max (stageId: taskId)) 430.0 KiB (2.1 KiB, 2.2 KiB, 2.2 KiB (stage 20.0: task 1326))"]; subgraph cluster8 { isCluster="true"; label="WholeStageCodegen (6)\n \nduration: total (min, med, max (stageId: taskId))\n1.6 s (7 ms, 8 ms, 13 ms (stage 20.0: task 1249))"; 9 [labelType="html" label="HashAggregate time in aggregation build total (min, med, max (stageId: taskId)) 608 ms (3 ms, 3 ms, 5 ms (stage 20.0: task 1370)) peak memory total (min, med, max (stageId: taskId)) 50.0 MiB (256.0 KiB, 256.0 KiB, 256.0 KiB (stage 20.0: task 1238)) number of output rows: 6,000"]; 10 [labelType="html" label="HashAggregate time in aggregation build total (min, med, max (stageId: taskId)) 462 ms (2 ms, 2 ms, 4 ms (stage 20.0: task 1283)) peak memory total (min, med, max (stageId: taskId)) 12.5 GiB (64.3 MiB, 64.3 MiB, 64.3 MiB (stage 20.0: task 1238)) number of output rows: 81,749 avg hash probe bucket list iters (min, med, max (stageId: taskId)): (1, 1, 1 (stage 20.0: task 1238))"]; } 11 [labelType="html" label="Exchange shuffle records written: 139,568 shuffle write time total (min, med, max (stageId: taskId)) 2.0 s (9 ms, 9 ms, 13 ms (stage 19.0: task 1229)) records read: 139,568 local bytes read total (min, med, max (stageId: taskId)) 8.7 MiB (32.7 KiB, 43.8 KiB, 67.9 KiB (stage 20.0: task 1402)) fetch wait time total (min, med, max (stageId: taskId)) 0 ms (0 ms, 0 ms, 0 ms (stage 20.0: task 1238)) local blocks read: 38,743 data size total (min, med, max (stageId: taskId)) 11.4 MiB (43.3 KiB, 57.9 KiB, 75.1 KiB (stage 19.0: task 1136)) shuffle bytes written total (min, med, max (stageId: taskId)) 8.7 MiB (35.9 KiB, 44.0 KiB, 52.7 KiB (stage 19.0: task 1136))"]; subgraph cluster12 { isCluster="true"; label="WholeStageCodegen (5)\n \nduration: total (min, med, max (stageId: taskId))\n2.9 s (12 ms, 14 ms, 52 ms (stage 19.0: task 1128))"; 13 [labelType="html" label="HashAggregate time in aggregation build total (min, med, max (stageId: taskId)) 389 ms (1 ms, 2 ms, 4 ms (stage 19.0: task 1043)) peak memory total (min, med, max (stageId: taskId)) 12.5 GiB (64.3 MiB, 64.3 MiB, 64.3 MiB (stage 19.0: task 1038)) number of output rows: 139,568 avg hash probe bucket list iters (min, med, max (stageId: taskId)): (1, 1, 1.1 (stage 19.0: task 1103))"]; 14 [labelType="html" label="Expand number of output rows: 347,610"]; 15 [labelType="html" label=" Project "]; 16 [labelType="html" label="SortMergeJoin number of output rows: 173,805"]; } subgraph cluster17 { isCluster="true"; label="WholeStageCodegen (2)\n \nduration: total (min, med, max (stageId: taskId))\n545 ms (0 ms, 4 ms, 9 ms (stage 19.0: task 1038))"; 18 [labelType="html" label="Sort sort time total (min, med, max (stageId: taskId)) 2 ms (0 ms, 0 ms, 1 ms (stage 19.0: task 1043)) peak memory total (min, med, max (stageId: taskId)) 12.5 GiB (64.1 MiB, 64.1 MiB, 64.1 MiB (stage 19.0: task 1039)) spill size total (min, med, max (stageId: taskId)) 0.0 B (0.0 B, 0.0 B, 0.0 B (stage 19.0: task 1038))"]; } 19 [labelType="html" label="Exchange shuffle records written: 504,708 shuffle write time total (min, med, max (stageId: taskId)) 51 ms (25 ms, 26 ms, 26 ms (stage 18.0: task 1036)) records read: 504,708 local bytes read total (min, med, max (stageId: taskId)) 21.2 MiB (97.1 KiB, 108.2 KiB, 122.0 KiB (stage 19.0: task 1069)) fetch wait time total (min, med, max (stageId: taskId)) 0 ms (0 ms, 0 ms, 0 ms (stage 19.0: task 1038)) local blocks read: 400 data size total (min, med, max (stageId: taskId)) 69.3 MiB (32.5 MiB, 36.8 MiB, 36.8 MiB (stage 18.0: task 1036)) shuffle bytes written total (min, med, max (stageId: taskId)) 21.2 MiB (10.0 MiB, 11.2 MiB, 11.2 MiB (stage 18.0: task 1036))"]; subgraph cluster20 { isCluster="true"; label="WholeStageCodegen (1)\n \nduration: total (min, med, max (stageId: taskId))\n2.9 s (1.4 s, 1.5 s, 1.5 s (stage 18.0: task 1036))"; 21 [labelType="html" label=" Project "]; 22 [labelType="html" label="Filter number of output rows: 504,708"]; } 23 [labelType="html" label="Scan csv number of files read: 1 metadata time: 0 ms size of files read: 173.6 MiB number of output rows: 504,708"]; subgraph cluster24 { isCluster="true"; label="WholeStageCodegen (4)\n \nduration: total (min, med, max (stageId: taskId))\n522 ms (0 ms, 3 ms, 8 ms (stage 19.0: task 1096))"; 25 [labelType="html" label="Sort sort time total (min, med, max (stageId: taskId)) 0 ms (0 ms, 0 ms, 0 ms (stage 19.0: task 1038)) peak memory total (min, med, max (stageId: taskId)) 12.5 GiB (64.1 MiB, 64.1 MiB, 64.1 MiB (stage 19.0: task 1038)) spill size total (min, med, max (stageId: taskId)) 0.0 B (0.0 B, 0.0 B, 0.0 B (stage 19.0: task 1038))"]; } 26 [labelType="html" label="Exchange shuffle records written: 144,178 shuffle write time total (min, med, max (stageId: taskId)) 41 ms (0 ms, 0 ms, 26 ms (stage 17.0: task 1032)) records read: 144,178 local bytes read total (min, med, max (stageId: taskId)) 4.7 MiB (20.1 KiB, 24.3 KiB, 28.5 KiB (stage 19.0: task 1065)) fetch wait time total (min, med, max (stageId: taskId)) 1 ms (0 ms, 0 ms, 1 ms (stage 19.0: task 1053)) remote bytes read total (min, med, max (stageId: taskId)) 5.4 MiB (23.1 KiB, 27.3 KiB, 31.6 KiB (stage 19.0: task 1117)) local blocks read: 200 remote blocks read: 200 data size total (min, med, max (stageId: taskId)) 16.5 MiB (0.0 B, 0.0 B, 8.8 MiB (stage 17.0: task 1032)) shuffle bytes written total (min, med, max (stageId: taskId)) 10.1 MiB (0.0 B, 0.0 B, 5.4 MiB (stage 17.0: task 1032))"]; subgraph cluster27 { isCluster="true"; label="WholeStageCodegen (3)\n \nduration: total (min, med, max (stageId: taskId))\n8.7 s (136 ms, 1.7 s, 2.7 s (stage 17.0: task 1032))"; 28 [labelType="html" label=" Project "]; 29 [labelType="html" label="Filter number of output rows: 144,178"]; } 30 [labelType="html" label="Scan csv number of files read: 1 metadata time: 0 ms size of files read: 519.0 MiB number of output rows: 500,001"]; 1->0; 3->1; 4->3; 6->4; 7->6; 9->7; 10->9; 11->10; 13->11; 14->13; 15->14; 16->15; 18->16; 19->18; 21->19; 22->21; 23->22; 25->16; 26->25; 28->26; 29->28; 30->29; }

Execute InsertIntoHadoopFsRelationCommand s3a://object-bucket-ec22981-9bc23785-4078-4ea5-b872-e6c98a05d411/04-12-2024_20:22:49, false, CSV, Map(header -> true, path -> s3a://object-bucket-ec22981-9bc23785-4078-4ea5-b872-e6c98a05d411/04-12-2024_20:22:49/), ErrorIfExists, [formatted_date, block_count, unique_senders_count_number]

Coalesce 1

Sort [formatted_date#136 ASC NULLS FIRST], true, 0

WholeStageCodegen (8)

Exchange rangepartitioning(formatted_date#136 ASC NULLS FIRST, 200), true, [id=#355]

HashAggregate(keys=[formatted_date#136], functions=[count(if ((gid#386 = 1)) `number`#387 else null), count(if ((gid#386 = 2)) `from_address`#388 else null)])

WholeStageCodegen (7)

Exchange hashpartitioning(formatted_date#136, 200), true, [id=#351]

HashAggregate(keys=[formatted_date#136], functions=[partial_count(if ((gid#386 = 1)) `number`#387 else null), partial_count(if ((gid#386 = 2)) `from_address`#388 else null)])

HashAggregate(keys=[formatted_date#136, `number`#387, `from_address`#388, gid#386], functions=[])

WholeStageCodegen (6)

Exchange hashpartitioning(formatted_date#136, `number`#387, `from_address`#388, gid#386, 200), true, [id=#346]

HashAggregate(keys=[formatted_date#136, `number`#387, `from_address`#388, gid#386], functions=[])

Expand [ArrayBuffer(formatted_date#136, number#16, null, 1), ArrayBuffer(formatted_date#136, null, from_address#75, 2)], [formatted_date#136, `number`#387, `from_address`#388, gid#386]

Project [from_address#75, number#16, formatted_date#136]

SortMergeJoin [block_hash#72], [hash#17], Inner

WholeStageCodegen (5)

Sort [block_hash#72 ASC NULLS FIRST], false, 0

WholeStageCodegen (2)

Exchange hashpartitioning(block_hash#72, 200), true, [id=#327]

Project [block_hash#72, from_address#75]

Filter isnotnull(block_hash#72)

WholeStageCodegen (1)

FileScan csv [block_hash#72,from_address#75] Batched: false, DataFilters: [isnotnull(block_hash#72)], Format: CSV, Location: InMemoryFileIndex[s3a://data-repository-bkt/ECS765/ethereum/transactions.csv], PartitionFilters: [], PushedFilters: [IsNotNull(block_hash)], ReadSchema: struct<block_hash:string,from_address:string>

Sort [hash#17 ASC NULLS FIRST], false, 0

WholeStageCodegen (4)

Exchange hashpartitioning(hash#17, 200), true, [id=#336]

Project [number#16, hash#17, date_format(cast(from_unixtime(cast(timestamp#32 as bigint), yyyy-MM-dd HH:mm:ss, Some(GMT)) as timestamp), yyyy-MM-dd, Some(GMT)) AS formatted_date#136]

Filter ((date_format(cast(from_unixtime(cast(timestamp#32 as bigint), yyyy-MM-dd HH:mm:ss, Some(GMT)) as timestamp), yyyy-MM, Some(GMT)) = 2015-09) AND isnotnull(hash#17))

WholeStageCodegen (3)

FileScan csv [number#16,hash#17,timestamp#32] Batched: false, DataFilters: [(date_format(cast(from_unixtime(cast(timestamp#32 as bigint), yyyy-MM-dd HH:mm:ss, Some(GMT)) as..., Format: CSV, Location: InMemoryFileIndex[s3a://data-repository-bkt/ECS765/ethereum/blocks.csv], PartitionFilters: [], PushedFilters: [IsNotNull(hash)], ReadSchema: struct<number:int,hash:string,timestamp:int>

Details

== Parsed Logical Plan ==
InsertIntoHadoopFsRelationCommand s3a://object-bucket-ec22981-9bc23785-4078-4ea5-b872-e6c98a05d411/04-12-2024_20:22:49, false, CSV, Map(header -> true, path -> s3a://object-bucket-ec22981-9bc23785-4078-4ea5-b872-e6c98a05d411/04-12-2024_20:22:49/), ErrorIfExists, [formatted_date, block_count, unique_senders_count_number]
+- Repartition 1, false
   +- Sort [formatted_date#136 ASC NULLS FIRST], true
      +- Aggregate [formatted_date#136], [formatted_date#136, count(distinct number#16) AS block_count#351L, count(distinct from_address#75) AS unique_senders_count_number#352L]
         +- Filter (date_format(cast(from_unixtime(cast(timestamp#32 as bigint), yyyy-MM-dd HH:mm:ss, Some(GMT)) as timestamp), yyyy-MM, Some(GMT)) = 2015-09)
            +- Join Inner, (block_hash#72 = hash#17)
               :- Relation[hash#70,nonce#71,block_hash#72,block_number#73,transaction_index#74,from_address#75,to_address#76,value#77,gas#78,gas_price#79L,input#80,block_timestamp#81,max_fee_per_gas#82,max_priority_fee_per_gas#83,transaction_type#84] csv
               +- Project [number#16, hash#17, parent_hash#18, nonce#19, sha3_uncles#20, logs_bloom#21, transactions_root#22, state_root#23, receipts_root#24, miner#25, difficulty#26L, total_difficulty#27, size#28, extra_data#29, gas_limit#30, gas_used#31, timestamp#32, transaction_count#33, base_fee_per_gas#34, date_format(cast(from_unixtime(cast(timestamp#32 as bigint), yyyy-MM-dd HH:mm:ss, Some(GMT)) as timestamp), yyyy-MM-dd, Some(GMT)) AS formatted_date#136]
                  +- Relation[number#16,hash#17,parent_hash#18,nonce#19,sha3_uncles#20,logs_bloom#21,transactions_root#22,state_root#23,receipts_root#24,miner#25,difficulty#26L,total_difficulty#27,size#28,extra_data#29,gas_limit#30,gas_used#31,timestamp#32,transaction_count#33,base_fee_per_gas#34] csv

== Analyzed Logical Plan ==

InsertIntoHadoopFsRelationCommand s3a://object-bucket-ec22981-9bc23785-4078-4ea5-b872-e6c98a05d411/04-12-2024_20:22:49, false, CSV, Map(header -> true, path -> s3a://object-bucket-ec22981-9bc23785-4078-4ea5-b872-e6c98a05d411/04-12-2024_20:22:49/), ErrorIfExists, [formatted_date, block_count, unique_senders_count_number]
+- Repartition 1, false
   +- Sort [formatted_date#136 ASC NULLS FIRST], true
      +- Aggregate [formatted_date#136], [formatted_date#136, count(distinct number#16) AS block_count#351L, count(distinct from_address#75) AS unique_senders_count_number#352L]
         +- Filter (date_format(cast(from_unixtime(cast(timestamp#32 as bigint), yyyy-MM-dd HH:mm:ss, Some(GMT)) as timestamp), yyyy-MM, Some(GMT)) = 2015-09)
            +- Join Inner, (block_hash#72 = hash#17)
               :- Relation[hash#70,nonce#71,block_hash#72,block_number#73,transaction_index#74,from_address#75,to_address#76,value#77,gas#78,gas_price#79L,input#80,block_timestamp#81,max_fee_per_gas#82,max_priority_fee_per_gas#83,transaction_type#84] csv
               +- Project [number#16, hash#17, parent_hash#18, nonce#19, sha3_uncles#20, logs_bloom#21, transactions_root#22, state_root#23, receipts_root#24, miner#25, difficulty#26L, total_difficulty#27, size#28, extra_data#29, gas_limit#30, gas_used#31, timestamp#32, transaction_count#33, base_fee_per_gas#34, date_format(cast(from_unixtime(cast(timestamp#32 as bigint), yyyy-MM-dd HH:mm:ss, Some(GMT)) as timestamp), yyyy-MM-dd, Some(GMT)) AS formatted_date#136]
                  +- Relation[number#16,hash#17,parent_hash#18,nonce#19,sha3_uncles#20,logs_bloom#21,transactions_root#22,state_root#23,receipts_root#24,miner#25,difficulty#26L,total_difficulty#27,size#28,extra_data#29,gas_limit#30,gas_used#31,timestamp#32,transaction_count#33,base_fee_per_gas#34] csv

== Optimized Logical Plan ==
InsertIntoHadoopFsRelationCommand s3a://object-bucket-ec22981-9bc23785-4078-4ea5-b872-e6c98a05d411/04-12-2024_20:22:49, false, CSV, Map(header -> true, path -> s3a://object-bucket-ec22981-9bc23785-4078-4ea5-b872-e6c98a05d411/04-12-2024_20:22:49/), ErrorIfExists, [formatted_date, block_count, unique_senders_count_number]
+- Repartition 1, false
   +- Sort [formatted_date#136 ASC NULLS FIRST], true
      +- Aggregate [formatted_date#136], [formatted_date#136, count(if ((gid#386 = 1)) `number`#387 else null) AS block_count#351L, count(if ((gid#386 = 2)) `from_address`#388 else null) AS unique_senders_count_number#352L]
         +- Aggregate [formatted_date#136, `number`#387, `from_address`#388, gid#386], [formatted_date#136, `number`#387, `from_address`#388, gid#386]
            +- Expand [ArrayBuffer(formatted_date#136, number#16, null, 1), ArrayBuffer(formatted_date#136, null, from_address#75, 2)], [formatted_date#136, `number`#387, `from_address`#388, gid#386]
               +- Project [from_address#75, number#16, formatted_date#136]
                  +- Join Inner, (block_hash#72 = hash#17)
                     :- Project [block_hash#72, from_address#75]
                     :  +- Filter isnotnull(block_hash#72)
                     :     +- Relation[hash#70,nonce#71,block_hash#72,block_number#73,transaction_index#74,from_address#75,to_address#76,value#77,gas#78,gas_price#79L,input#80,block_timestamp#81,max_fee_per_gas#82,max_priority_fee_per_gas#83,transaction_type#84] csv
                     +- Project [number#16, hash#17, date_format(cast(from_unixtime(cast(timestamp#32 as bigint), yyyy-MM-dd HH:mm:ss, Some(GMT)) as timestamp), yyyy-MM-dd, Some(GMT)) AS formatted_date#136]
                        +- Filter ((date_format(cast(from_unixtime(cast(timestamp#32 as bigint), yyyy-MM-dd HH:mm:ss, Some(GMT)) as timestamp), yyyy-MM, Some(GMT)) = 2015-09) AND isnotnull(hash#17))
                           +- Relation[number#16,hash#17,parent_hash#18,nonce#19,sha3_uncles#20,logs_bloom#21,transactions_root#22,state_root#23,receipts_root#24,miner#25,difficulty#26L,total_difficulty#27,size#28,extra_data#29,gas_limit#30,gas_used#31,timestamp#32,transaction_count#33,base_fee_per_gas#34] csv

== Physical Plan ==
Execute InsertIntoHadoopFsRelationCommand s3a://object-bucket-ec22981-9bc23785-4078-4ea5-b872-e6c98a05d411/04-12-2024_20:22:49, false, CSV, Map(header -> true, path -> s3a://object-bucket-ec22981-9bc23785-4078-4ea5-b872-e6c98a05d411/04-12-2024_20:22:49/), ErrorIfExists, [formatted_date, block_count, unique_senders_count_number]
+- Coalesce 1
   +- *(8) Sort [formatted_date#136 ASC NULLS FIRST], true, 0
      +- Exchange rangepartitioning(formatted_date#136 ASC NULLS FIRST, 200), true, [id=#355]
         +- *(7) HashAggregate(keys=[formatted_date#136], functions=[count(if ((gid#386 = 1)) `number`#387 else null), count(if ((gid#386 = 2)) `from_address`#388 else null)], output=[formatted_date#136, block_count#351L, unique_senders_count_number#352L])
            +- Exchange hashpartitioning(formatted_date#136, 200), true, [id=#351]
               +- *(6) HashAggregate(keys=[formatted_date#136], functions=[partial_count(if ((gid#386 = 1)) `number`#387 else null), partial_count(if ((gid#386 = 2)) `from_address`#388 else null)], output=[formatted_date#136, count#391L, count#392L])
                  +- *(6) HashAggregate(keys=[formatted_date#136, `number`#387, `from_address`#388, gid#386], functions=[], output=[formatted_date#136, `number`#387, `from_address`#388, gid#386])
                     +- Exchange hashpartitioning(formatted_date#136, `number`#387, `from_address`#388, gid#386, 200), true, [id=#346]
                        +- *(5) HashAggregate(keys=[formatted_date#136, `number`#387, `from_address`#388, gid#386], functions=[], output=[formatted_date#136, `number`#387, `from_address`#388, gid#386])
                           +- *(5) Expand [ArrayBuffer(formatted_date#136, number#16, null, 1), ArrayBuffer(formatted_date#136, null, from_address#75, 2)], [formatted_date#136, `number`#387, `from_address`#388, gid#386]
                              +- *(5) Project [from_address#75, number#16, formatted_date#136]
                                 +- *(5) SortMergeJoin [block_hash#72], [hash#17], Inner
                                    :- *(2) Sort [block_hash#72 ASC NULLS FIRST], false, 0
                                    :  +- Exchange hashpartitioning(block_hash#72, 200), true, [id=#327]
                                    :     +- *(1) Project [block_hash#72, from_address#75]
                                    :        +- *(1) Filter isnotnull(block_hash#72)
                                    :           +- FileScan csv [block_hash#72,from_address#75] Batched: false, DataFilters: [isnotnull(block_hash#72)], Format: CSV, Location: InMemoryFileIndex[s3a://data-repository-bkt/ECS765/ethereum/transactions.csv], PartitionFilters: [], PushedFilters: [IsNotNull(block_hash)], ReadSchema: struct<block_hash:string,from_address:string>
                                    +- *(4) Sort [hash#17 ASC NULLS FIRST], false, 0
                                       +- Exchange hashpartitioning(hash#17, 200), true, [id=#336]
                                          +- *(3) Project [number#16, hash#17, date_format(cast(from_unixtime(cast(timestamp#32 as bigint), yyyy-MM-dd HH:mm:ss, Some(GMT)) as timestamp), yyyy-MM-dd, Some(GMT)) AS formatted_date#136]
                                             +- *(3) Filter ((date_format(cast(from_unixtime(cast(timestamp#32 as bigint), yyyy-MM-dd HH:mm:ss, Some(GMT)) as timestamp), yyyy-MM, Some(GMT)) = 2015-09) AND isnotnull(hash#17))
                                                +- FileScan csv [number#16,hash#17,timestamp#32] Batched: false, DataFilters: [(date_format(cast(from_unixtime(cast(timestamp#32 as bigint), yyyy-MM-dd HH:mm:ss, Some(GMT)) as..., Format: CSV, Location: InMemoryFileIndex[s3a://data-repository-bkt/ECS765/ethereum/blocks.csv], PartitionFilters: [], PushedFilters: [IsNotNull(hash)], ReadSchema: struct<number:int,hash:string,timestamp:int>