Project [CASE WHEN (date#94110149 = null) THEN null ELSE cast(date#94110149 as date) END AS date#94110270, CASE WHEN ((overall#94110150 = NA) OR (overall#94110150 = null)) THEN null ELSE cast(overall#94110150 as int) END AS overall#94110271, CASE WHEN ((ret#94110151 = NA) OR (ret#94110151 = null)) THEN null ELSE cast(ret#94110151 as float) END AS ret#94110272, CASE WHEN ((resret#94110152 = NA) OR (resret#94110152 = null)) THEN null ELSE cast(resret#94110152 as float) END AS resret#94110273, CASE WHEN ((retnet#94110153 = NA) OR (retnet#94110153 = null)) THEN null ELSE cast(retnet#94110153 as float) END AS retnet#94110274, CASE WHEN ((turnover#94110154 = NA) OR (turnover#94110154 = null)) THEN null ELSE cast(turnover#94110154 as float) END AS turnover#94110275, CASE WHEN ((numcos#94110155 = NA) OR (numcos#94110155 = null)) THEN null ELSE cast(numcos#94110155 as float) END AS numcos#94110276, CASE WHEN ((benchmark#94110156 = NA) OR (benchmark#94110156 = null)) THEN null ELSE cast(benchmark#94110156 as float) END AS benchmark#94110277, CASE WHEN ((excess_ret#94110157 = NA) OR (excess_ret#94110157 = null)) THEN null ELSE cast(excess_ret#94110157 as float) END AS excess_ret#94110278, CASE WHEN ((excess_resret#94110158 = NA) OR (excess_resret#94110158 = null)) THEN null ELSE cast(excess_resret#94110158 as float) END AS excess_resret#94110279, CASE WHEN ((excess_retnet#94110159 = NA) OR (excess_retnet#94110159 = null)) THEN null ELSE cast(excess_retnet#94110159 as float) END AS excess_retnet#94110292]
Filter (isnotnull(cap#94110306) AND (cast(cap#94110306 as string) = 0))
WholeStageCodegen (1)
InMemoryTableScan [cap#94110306, date#94110305, numcos#94110311], [isnotnull(cap#94110306), (cast(cap#94110306 as string) = 0)]
Project [CASE WHEN (date#94110224 = null) THEN null ELSE cast(date#94110224 as date) END AS date#94110305, CASE WHEN ((cap#94110225 = NA) OR (cap#94110225 = null)) THEN null ELSE cast(cap#94110225 as float) END AS cap#94110306, CASE WHEN ((ret#94110226 = NA) OR (ret#94110226 = null)) THEN null ELSE cast(ret#94110226 as float) END AS ret#94110307, CASE WHEN ((resret#94110227 = NA) OR (resret#94110227 = null)) THEN null ELSE cast(resret#94110227 as float) END AS resret#94110308, CASE WHEN ((retnet#94110228 = NA) OR (retnet#94110228 = null)) THEN null ELSE cast(retnet#94110228 as float) END AS retnet#94110309, CASE WHEN ((turnover#94110229 = NA) OR (turnover#94110229 = null)) THEN null ELSE cast(turnover#94110229 as float) END AS turnover#94110310, CASE WHEN ((numcos#94110230 = NA) OR (numcos#94110230 = null)) THEN null ELSE cast(numcos#94110230 as float) END AS numcos#94110311, CASE WHEN ((coverage#94110231 = NA) OR (coverage#94110231 = null)) THEN null ELSE cast(coverage#94110231 as float) END AS coverage#94110312, CASE WHEN ((benchmark#94110232 = NA) OR (benchmark#94110232 = null)) THEN null ELSE cast(benchmark#94110232 as float) END AS benchmark#94110313, CASE WHEN ((excess_ret#94110233 = NA) OR (excess_ret#94110233 = null)) THEN null ELSE cast(excess_ret#94110233 as float) END AS excess_ret#94110314, CASE WHEN ((excess_resret#94110234 = NA) OR (excess_resret#94110234 = null)) THEN null ELSE cast(excess_resret#94110234 as float) END AS excess_resret#94110315, CASE WHEN ((excess_retnet#94110235 = NA) OR (excess_retnet#94110235 = null)) THEN null ELSE cast(excess_retnet#94110235 as float) END AS excess_retnet#94110316]
== Physical Plan ==
CollectLimit (16)
+- InMemoryTableScan (1)
+- InMemoryRelation (2)
+- * Sort (15)
+- Exchange (14)
+- Union (13)
:- InMemoryTableScan (3)
: +- InMemoryRelation (4)
: +- * Project (6)
: +- Scan csv (5)
+- * Project (12)
+- * Filter (11)
+- InMemoryTableScan (7)
+- InMemoryRelation (8)
+- * Project (10)
+- Scan csv (9)
(1) InMemoryTableScan
Output [2]: [date#94110270, numcos#94110276]
Arguments: [date#94110270, numcos#94110276]
(2) InMemoryRelation
Arguments: [date#94110270, numcos#94110276], CachedRDDBuilder(org.apache.spark.sql.execution.columnar.DefaultCachedBatchSerializer@208e3fd9,StorageLevel(disk, memory, deserialized, 1 replicas),*(2) Sort [date#94110270 ASC NULLS FIRST], true, 0
+- Exchange rangepartitioning(date#94110270 ASC NULLS FIRST, 200), ENSURE_REQUIREMENTS, [id=#7514117]
+- Union
:- InMemoryTableScan [date#94110270, numcos#94110276]
: +- InMemoryRelation [date#94110270, overall#94110271, ret#94110272, resret#94110273, retnet#94110274, turnover#94110275, numcos#94110276, benchmark#94110277, excess_ret#94110278, excess_resret#94110279, excess_retnet#94110292], StorageLevel(disk, memory, deserialized, 1 replicas)
: +- *(1) Project [CASE WHEN (date#94110149 = null) THEN null ELSE cast(date#94110149 as date) END AS date#94110270, CASE WHEN ((overall#94110150 = NA) OR (overall#94110150 = null)) THEN null ELSE cast(overall#94110150 as int) END AS overall#94110271, CASE WHEN ((ret#94110151 = NA) OR (ret#94110151 = null)) THEN null ELSE cast(ret#94110151 as float) END AS ret#94110272, CASE WHEN ((resret#94110152 = NA) OR (resret#94110152 = null)) THEN null ELSE cast(resret#94110152 as float) END AS resret#94110273, CASE WHEN ((retnet#94110153 = NA) OR (retnet#94110153 = null)) THEN null ELSE cast(retnet#94110153 as float) END AS retnet#94110274, CASE WHEN ((turnover#94110154 = NA) OR (turnover#94110154 = null)) THEN null ELSE cast(turnover#94110154 as float) END AS turnover#94110275, CASE WHEN ((numcos#94110155 = NA) OR (numcos#94110155 = null)) THEN null ELSE cast(numcos#94110155 as float) END AS numcos#94110276, CASE WHEN ((benchmark#94110156 = NA) OR (benchmark#94110156 = null)) THEN null ELSE cast(benchmark#94110156 as float) END AS benchmark#94110277, CASE WHEN ((excess_ret#94110157 = NA) OR (excess_ret#94110157 = null)) THEN null ELSE cast(excess_ret#94110157 as float) END AS excess_ret#94110278, CASE WHEN ((excess_resret#94110158 = NA) OR (excess_resret#94110158 = null)) THEN null ELSE cast(excess_resret#94110158 as float) END AS excess_resret#94110279, CASE WHEN ((excess_retnet#94110159 = NA) OR (excess_retnet#94110159 = null)) THEN null ELSE cast(excess_retnet#94110159 as float) END AS excess_retnet#94110292]
: +- FileScan csv [date#94110149,overall#94110150,ret#94110151,resret#94110152,retnet#94110153,turnover#94110154,numcos#94110155,benchmark#94110156,excess_ret#94110157,excess_resret#94110158,excess_retnet#94110159] Batched: false, DataFilters: [], Format: CSV, Location: InMemoryFileIndex(1 paths)[file:/srv/plusamp/data/default/ea-market/output/tm1/eatm1_score/longsh..., PartitionFilters: [], PushedFilters: [], ReadSchema: struct<date:string,overall:string,ret:string,resret:string,retnet:string,turnover:string,numcos:s...
+- *(1) Project [date#94110305, numcos#94110311]
+- *(1) Filter (isnotnull(cap#94110306) AND (cast(cap#94110306 as string) = 0))
+- InMemoryTableScan [cap#94110306, date#94110305, numcos#94110311], [isnotnull(cap#94110306), (cast(cap#94110306 as string) = 0)]
+- InMemoryRelation [date#94110305, cap#94110306, ret#94110307, resret#94110308, retnet#94110309, turnover#94110310, numcos#94110311, coverage#94110312, benchmark#94110313, excess_ret#94110314, excess_resret#94110315, excess_retnet#94110316], StorageLevel(disk, memory, deserialized, 1 replicas)
+- *(1) Project [CASE WHEN (date#94110224 = null) THEN null ELSE cast(date#94110224 as date) END AS date#94110305, CASE WHEN ((cap#94110225 = NA) OR (cap#94110225 = null)) THEN null ELSE cast(cap#94110225 as float) END AS cap#94110306, CASE WHEN ((ret#94110226 = NA) OR (ret#94110226 = null)) THEN null ELSE cast(ret#94110226 as float) END AS ret#94110307, CASE WHEN ((resret#94110227 = NA) OR (resret#94110227 = null)) THEN null ELSE cast(resret#94110227 as float) END AS resret#94110308, CASE WHEN ((retnet#94110228 = NA) OR (retnet#94110228 = null)) THEN null ELSE cast(retnet#94110228 as float) END AS retnet#94110309, CASE WHEN ((turnover#94110229 = NA) OR (turnover#94110229 = null)) THEN null ELSE cast(turnover#94110229 as float) END AS turnover#94110310, CASE WHEN ((numcos#94110230 = NA) OR (numcos#94110230 = null)) THEN null ELSE cast(numcos#94110230 as float) END AS numcos#94110311, CASE WHEN ((coverage#94110231 = NA) OR (coverage#94110231 = null)) THEN null ELSE cast(coverage#94110231 as float) END AS coverage#94110312, CASE WHEN ((benchmark#94110232 = NA) OR (benchmark#94110232 = null)) THEN null ELSE cast(benchmark#94110232 as float) END AS benchmark#94110313, CASE WHEN ((excess_ret#94110233 = NA) OR (excess_ret#94110233 = null)) THEN null ELSE cast(excess_ret#94110233 as float) END AS excess_ret#94110314, CASE WHEN ((excess_resret#94110234 = NA) OR (excess_resret#94110234 = null)) THEN null ELSE cast(excess_resret#94110234 as float) END AS excess_resret#94110315, CASE WHEN ((excess_retnet#94110235 = NA) OR (excess_retnet#94110235 = null)) THEN null ELSE cast(excess_retnet#94110235 as float) END AS excess_retnet#94110316]
+- FileScan csv [date#94110224,cap#94110225,ret#94110226,resret#94110227,retnet#94110228,turnover#94110229,numcos#94110230,coverage#94110231,benchmark#94110232,excess_ret#94110233,excess_resret#94110234,excess_retnet#94110235] Batched: false, DataFilters: [], Format: CSV, Location: InMemoryFileIndex(1 paths)[file:/srv/plusamp/data/default/ea-market/output/tm1/eatm1_score/longsh..., PartitionFilters: [], PushedFilters: [], ReadSchema: struct<date:string,cap:string,ret:string,resret:string,retnet:string,turnover:string,numcos:strin...
,None), [date#94110270 ASC NULLS FIRST]
(3) InMemoryTableScan
Output [2]: [date#94110270, numcos#94110276]
Arguments: [date#94110270, numcos#94110276]
(4) InMemoryRelation
Arguments: [date#94110270, overall#94110271, ret#94110272, resret#94110273, retnet#94110274, turnover#94110275, numcos#94110276, benchmark#94110277, excess_ret#94110278, excess_resret#94110279, excess_retnet#94110292], CachedRDDBuilder(org.apache.spark.sql.execution.columnar.DefaultCachedBatchSerializer@208e3fd9,StorageLevel(disk, memory, deserialized, 1 replicas),*(1) Project [CASE WHEN (date#94110149 = null) THEN null ELSE cast(date#94110149 as date) END AS date#94110270, CASE WHEN ((overall#94110150 = NA) OR (overall#94110150 = null)) THEN null ELSE cast(overall#94110150 as int) END AS overall#94110271, CASE WHEN ((ret#94110151 = NA) OR (ret#94110151 = null)) THEN null ELSE cast(ret#94110151 as float) END AS ret#94110272, CASE WHEN ((resret#94110152 = NA) OR (resret#94110152 = null)) THEN null ELSE cast(resret#94110152 as float) END AS resret#94110273, CASE WHEN ((retnet#94110153 = NA) OR (retnet#94110153 = null)) THEN null ELSE cast(retnet#94110153 as float) END AS retnet#94110274, CASE WHEN ((turnover#94110154 = NA) OR (turnover#94110154 = null)) THEN null ELSE cast(turnover#94110154 as float) END AS turnover#94110275, CASE WHEN ((numcos#94110155 = NA) OR (numcos#94110155 = null)) THEN null ELSE cast(numcos#94110155 as float) END AS numcos#94110276, CASE WHEN ((benchmark#94110156 = NA) OR (benchmark#94110156 = null)) THEN null ELSE cast(benchmark#94110156 as float) END AS benchmark#94110277, CASE WHEN ((excess_ret#94110157 = NA) OR (excess_ret#94110157 = null)) THEN null ELSE cast(excess_ret#94110157 as float) END AS excess_ret#94110278, CASE WHEN ((excess_resret#94110158 = NA) OR (excess_resret#94110158 = null)) THEN null ELSE cast(excess_resret#94110158 as float) END AS excess_resret#94110279, CASE WHEN ((excess_retnet#94110159 = NA) OR (excess_retnet#94110159 = null)) THEN null ELSE cast(excess_retnet#94110159 as float) END AS excess_retnet#94110292]
+- FileScan csv [date#94110149,overall#94110150,ret#94110151,resret#94110152,retnet#94110153,turnover#94110154,numcos#94110155,benchmark#94110156,excess_ret#94110157,excess_resret#94110158,excess_retnet#94110159] Batched: false, DataFilters: [], Format: CSV, Location: InMemoryFileIndex(1 paths)[file:/srv/plusamp/data/default/ea-market/output/tm1/eatm1_score/longsh..., PartitionFilters: [], PushedFilters: [], ReadSchema: struct<date:string,overall:string,ret:string,resret:string,retnet:string,turnover:string,numcos:s...
,None)
(5) Scan csv
Output [11]: [date#94110149, overall#94110150, ret#94110151, resret#94110152, retnet#94110153, turnover#94110154, numcos#94110155, benchmark#94110156, excess_ret#94110157, excess_resret#94110158, excess_retnet#94110159]
Batched: false
Location: InMemoryFileIndex [file:/srv/plusamp/data/default/ea-market/output/tm1/eatm1_score/longshort_overall.csv]
ReadSchema: struct<date:string,overall:string,ret:string,resret:string,retnet:string,turnover:string,numcos:string,benchmark:string,excess_ret:string,excess_resret:string,excess_retnet:string>
(6) Project [codegen id : 1]
Output [11]: [CASE WHEN (date#94110149 = null) THEN null ELSE cast(date#94110149 as date) END AS date#94110270, CASE WHEN ((overall#94110150 = NA) OR (overall#94110150 = null)) THEN null ELSE cast(overall#94110150 as int) END AS overall#94110271, CASE WHEN ((ret#94110151 = NA) OR (ret#94110151 = null)) THEN null ELSE cast(ret#94110151 as float) END AS ret#94110272, CASE WHEN ((resret#94110152 = NA) OR (resret#94110152 = null)) THEN null ELSE cast(resret#94110152 as float) END AS resret#94110273, CASE WHEN ((retnet#94110153 = NA) OR (retnet#94110153 = null)) THEN null ELSE cast(retnet#94110153 as float) END AS retnet#94110274, CASE WHEN ((turnover#94110154 = NA) OR (turnover#94110154 = null)) THEN null ELSE cast(turnover#94110154 as float) END AS turnover#94110275, CASE WHEN ((numcos#94110155 = NA) OR (numcos#94110155 = null)) THEN null ELSE cast(numcos#94110155 as float) END AS numcos#94110276, CASE WHEN ((benchmark#94110156 = NA) OR (benchmark#94110156 = null)) THEN null ELSE cast(benchmark#94110156 as float) END AS benchmark#94110277, CASE WHEN ((excess_ret#94110157 = NA) OR (excess_ret#94110157 = null)) THEN null ELSE cast(excess_ret#94110157 as float) END AS excess_ret#94110278, CASE WHEN ((excess_resret#94110158 = NA) OR (excess_resret#94110158 = null)) THEN null ELSE cast(excess_resret#94110158 as float) END AS excess_resret#94110279, CASE WHEN ((excess_retnet#94110159 = NA) OR (excess_retnet#94110159 = null)) THEN null ELSE cast(excess_retnet#94110159 as float) END AS excess_retnet#94110292]
Input [11]: [date#94110149, overall#94110150, ret#94110151, resret#94110152, retnet#94110153, turnover#94110154, numcos#94110155, benchmark#94110156, excess_ret#94110157, excess_resret#94110158, excess_retnet#94110159]
(7) InMemoryTableScan
Output [3]: [cap#94110306, date#94110305, numcos#94110311]
Arguments: [cap#94110306, date#94110305, numcos#94110311], [isnotnull(cap#94110306), (cast(cap#94110306 as string) = 0)]
(8) InMemoryRelation
Arguments: [date#94110305, cap#94110306, ret#94110307, resret#94110308, retnet#94110309, turnover#94110310, numcos#94110311, coverage#94110312, benchmark#94110313, excess_ret#94110314, excess_resret#94110315, excess_retnet#94110316], CachedRDDBuilder(org.apache.spark.sql.execution.columnar.DefaultCachedBatchSerializer@208e3fd9,StorageLevel(disk, memory, deserialized, 1 replicas),*(1) Project [CASE WHEN (date#94110224 = null) THEN null ELSE cast(date#94110224 as date) END AS date#94110305, CASE WHEN ((cap#94110225 = NA) OR (cap#94110225 = null)) THEN null ELSE cast(cap#94110225 as float) END AS cap#94110306, CASE WHEN ((ret#94110226 = NA) OR (ret#94110226 = null)) THEN null ELSE cast(ret#94110226 as float) END AS ret#94110307, CASE WHEN ((resret#94110227 = NA) OR (resret#94110227 = null)) THEN null ELSE cast(resret#94110227 as float) END AS resret#94110308, CASE WHEN ((retnet#94110228 = NA) OR (retnet#94110228 = null)) THEN null ELSE cast(retnet#94110228 as float) END AS retnet#94110309, CASE WHEN ((turnover#94110229 = NA) OR (turnover#94110229 = null)) THEN null ELSE cast(turnover#94110229 as float) END AS turnover#94110310, CASE WHEN ((numcos#94110230 = NA) OR (numcos#94110230 = null)) THEN null ELSE cast(numcos#94110230 as float) END AS numcos#94110311, CASE WHEN ((coverage#94110231 = NA) OR (coverage#94110231 = null)) THEN null ELSE cast(coverage#94110231 as float) END AS coverage#94110312, CASE WHEN ((benchmark#94110232 = NA) OR (benchmark#94110232 = null)) THEN null ELSE cast(benchmark#94110232 as float) END AS benchmark#94110313, CASE WHEN ((excess_ret#94110233 = NA) OR (excess_ret#94110233 = null)) THEN null ELSE cast(excess_ret#94110233 as float) END AS excess_ret#94110314, CASE WHEN ((excess_resret#94110234 = NA) OR (excess_resret#94110234 = null)) THEN null ELSE cast(excess_resret#94110234 as float) END AS excess_resret#94110315, CASE WHEN ((excess_retnet#94110235 = NA) OR (excess_retnet#94110235 = null)) THEN null ELSE cast(excess_retnet#94110235 as float) END AS excess_retnet#94110316]
+- FileScan csv [date#94110224,cap#94110225,ret#94110226,resret#94110227,retnet#94110228,turnover#94110229,numcos#94110230,coverage#94110231,benchmark#94110232,excess_ret#94110233,excess_resret#94110234,excess_retnet#94110235] Batched: false, DataFilters: [], Format: CSV, Location: InMemoryFileIndex(1 paths)[file:/srv/plusamp/data/default/ea-market/output/tm1/eatm1_score/longsh..., PartitionFilters: [], PushedFilters: [], ReadSchema: struct<date:string,cap:string,ret:string,resret:string,retnet:string,turnover:string,numcos:strin...
,None)
(9) Scan csv
Output [12]: [date#94110224, cap#94110225, ret#94110226, resret#94110227, retnet#94110228, turnover#94110229, numcos#94110230, coverage#94110231, benchmark#94110232, excess_ret#94110233, excess_resret#94110234, excess_retnet#94110235]
Batched: false
Location: InMemoryFileIndex [file:/srv/plusamp/data/default/ea-market/output/tm1/eatm1_score/longshort_cap.csv]
ReadSchema: struct<date:string,cap:string,ret:string,resret:string,retnet:string,turnover:string,numcos:string,coverage:string,benchmark:string,excess_ret:string,excess_resret:string,excess_retnet:string>
(10) Project [codegen id : 1]
Output [12]: [CASE WHEN (date#94110224 = null) THEN null ELSE cast(date#94110224 as date) END AS date#94110305, CASE WHEN ((cap#94110225 = NA) OR (cap#94110225 = null)) THEN null ELSE cast(cap#94110225 as float) END AS cap#94110306, CASE WHEN ((ret#94110226 = NA) OR (ret#94110226 = null)) THEN null ELSE cast(ret#94110226 as float) END AS ret#94110307, CASE WHEN ((resret#94110227 = NA) OR (resret#94110227 = null)) THEN null ELSE cast(resret#94110227 as float) END AS resret#94110308, CASE WHEN ((retnet#94110228 = NA) OR (retnet#94110228 = null)) THEN null ELSE cast(retnet#94110228 as float) END AS retnet#94110309, CASE WHEN ((turnover#94110229 = NA) OR (turnover#94110229 = null)) THEN null ELSE cast(turnover#94110229 as float) END AS turnover#94110310, CASE WHEN ((numcos#94110230 = NA) OR (numcos#94110230 = null)) THEN null ELSE cast(numcos#94110230 as float) END AS numcos#94110311, CASE WHEN ((coverage#94110231 = NA) OR (coverage#94110231 = null)) THEN null ELSE cast(coverage#94110231 as float) END AS coverage#94110312, CASE WHEN ((benchmark#94110232 = NA) OR (benchmark#94110232 = null)) THEN null ELSE cast(benchmark#94110232 as float) END AS benchmark#94110313, CASE WHEN ((excess_ret#94110233 = NA) OR (excess_ret#94110233 = null)) THEN null ELSE cast(excess_ret#94110233 as float) END AS excess_ret#94110314, CASE WHEN ((excess_resret#94110234 = NA) OR (excess_resret#94110234 = null)) THEN null ELSE cast(excess_resret#94110234 as float) END AS excess_resret#94110315, CASE WHEN ((excess_retnet#94110235 = NA) OR (excess_retnet#94110235 = null)) THEN null ELSE cast(excess_retnet#94110235 as float) END AS excess_retnet#94110316]
Input [12]: [date#94110224, cap#94110225, ret#94110226, resret#94110227, retnet#94110228, turnover#94110229, numcos#94110230, coverage#94110231, benchmark#94110232, excess_ret#94110233, excess_resret#94110234, excess_retnet#94110235]
(11) Filter [codegen id : 1]
Input [3]: [cap#94110306, date#94110305, numcos#94110311]
Condition : (isnotnull(cap#94110306) AND (cast(cap#94110306 as string) = 0))
(12) Project [codegen id : 1]
Output [2]: [date#94110305, numcos#94110311]
Input [3]: [cap#94110306, date#94110305, numcos#94110311]
(13) Union
(14) Exchange
Input [2]: [date#94110270, numcos#94110276]
Arguments: rangepartitioning(date#94110270 ASC NULLS FIRST, 200), ENSURE_REQUIREMENTS, [id=#7514117]
(15) Sort [codegen id : 2]
Input [2]: [date#94110270, numcos#94110276]
Arguments: [date#94110270 ASC NULLS FIRST], true, 0
(16) CollectLimit
Input [2]: [date#94110270, numcos#94110276]
Arguments: 1000000