Project [CASE WHEN ((fractile#94119373 = NA) OR (fractile#94119373 = null)) THEN null ELSE cast(fractile#94119373 as int) END AS fractile#94119415, CASE WHEN ((overall#94119374 = NA) OR (overall#94119374 = null)) THEN null ELSE cast(overall#94119374 as int) END AS overall#94119417, CASE WHEN ((annual_ret#94119375 = NA) OR (annual_ret#94119375 = null)) THEN null ELSE cast(annual_ret#94119375 as float) END AS annual_ret#94119441, CASE WHEN ((annual_resret#94119376 = NA) OR (annual_resret#94119376 = null)) THEN null ELSE cast(annual_resret#94119376 as float) END AS annual_resret#94119526, CASE WHEN ((numcos#94119377 = NA) OR (numcos#94119377 = null)) THEN null ELSE cast(numcos#94119377 as float) END AS numcos#94119528]
Project [CASE WHEN ((fractile#94119384 = NA) OR (fractile#94119384 = null)) THEN null ELSE cast(fractile#94119384 as int) END AS fractile#94119416, CASE WHEN ((cap#94119385 = NA) OR (cap#94119385 = null)) THEN null ELSE cast(cap#94119385 as float) END AS cap#94119418, CASE WHEN ((annual_ret#94119386 = NA) OR (annual_ret#94119386 = null)) THEN null ELSE cast(annual_ret#94119386 as float) END AS annual_ret#94119442, CASE WHEN ((annual_resret#94119387 = NA) OR (annual_resret#94119387 = null)) THEN null ELSE cast(annual_resret#94119387 as float) END AS annual_resret#94119465, CASE WHEN ((numcos#94119388 = NA) OR (numcos#94119388 = null)) THEN null ELSE cast(numcos#94119388 as float) END AS numcos#94119466]
== Physical Plan ==
CollectLimit (17)
+- * ColumnarToRow (16)
+- InMemoryTableScan (1)
+- InMemoryRelation (2)
+- Union (15)
:- * ColumnarToRow (7)
: +- InMemoryTableScan (3)
: +- InMemoryRelation (4)
: +- * Project (6)
: +- Scan csv (5)
+- * Project (14)
+- * Filter (13)
+- * ColumnarToRow (12)
+- InMemoryTableScan (8)
+- InMemoryRelation (9)
+- * Project (11)
+- Scan csv (10)
(1) InMemoryTableScan
Output [4]: [fractile#94119415, annual_ret#94119441, annual_resret#94119526, numcos#94119528]
Arguments: [fractile#94119415, annual_ret#94119441, annual_resret#94119526, numcos#94119528]
(2) InMemoryRelation
Arguments: [fractile#94119415, annual_ret#94119441, annual_resret#94119526, numcos#94119528], CachedRDDBuilder(org.apache.spark.sql.execution.columnar.DefaultCachedBatchSerializer@208e3fd9,StorageLevel(disk, memory, deserialized, 1 replicas),Union
:- *(1) ColumnarToRow
: +- InMemoryTableScan [fractile#94119415, annual_ret#94119441, annual_resret#94119526, numcos#94119528]
: +- InMemoryRelation [fractile#94119415, overall#94119417, annual_ret#94119441, annual_resret#94119526, numcos#94119528], StorageLevel(disk, memory, deserialized, 1 replicas)
: +- *(1) Project [CASE WHEN ((fractile#94119373 = NA) OR (fractile#94119373 = null)) THEN null ELSE cast(fractile#94119373 as int) END AS fractile#94119415, CASE WHEN ((overall#94119374 = NA) OR (overall#94119374 = null)) THEN null ELSE cast(overall#94119374 as int) END AS overall#94119417, CASE WHEN ((annual_ret#94119375 = NA) OR (annual_ret#94119375 = null)) THEN null ELSE cast(annual_ret#94119375 as float) END AS annual_ret#94119441, CASE WHEN ((annual_resret#94119376 = NA) OR (annual_resret#94119376 = null)) THEN null ELSE cast(annual_resret#94119376 as float) END AS annual_resret#94119526, CASE WHEN ((numcos#94119377 = NA) OR (numcos#94119377 = null)) THEN null ELSE cast(numcos#94119377 as float) END AS numcos#94119528]
: +- FileScan csv [fractile#94119373,overall#94119374,annual_ret#94119375,annual_resret#94119376,numcos#94119377] Batched: false, DataFilters: [], Format: CSV, Location: InMemoryFileIndex(1 paths)[file:/srv/plusamp/data/default/ea-market/output/transcripts/transcript..., PartitionFilters: [], PushedFilters: [], ReadSchema: struct<fractile:string,overall:string,annual_ret:string,annual_resret:string,numcos:string>
+- *(2) Project [fractile#94119416, annual_ret#94119442, annual_resret#94119465, numcos#94119466]
+- *(2) Filter (isnotnull(cap#94119418) AND (cast(cap#94119418 as string) = 0))
+- *(2) ColumnarToRow
+- InMemoryTableScan [annual_resret#94119465, annual_ret#94119442, cap#94119418, fractile#94119416, numcos#94119466], [isnotnull(cap#94119418), (cast(cap#94119418 as string) = 0)]
+- InMemoryRelation [fractile#94119416, cap#94119418, annual_ret#94119442, annual_resret#94119465, numcos#94119466], StorageLevel(disk, memory, deserialized, 1 replicas)
+- *(1) Project [CASE WHEN ((fractile#94119384 = NA) OR (fractile#94119384 = null)) THEN null ELSE cast(fractile#94119384 as int) END AS fractile#94119416, CASE WHEN ((cap#94119385 = NA) OR (cap#94119385 = null)) THEN null ELSE cast(cap#94119385 as float) END AS cap#94119418, CASE WHEN ((annual_ret#94119386 = NA) OR (annual_ret#94119386 = null)) THEN null ELSE cast(annual_ret#94119386 as float) END AS annual_ret#94119442, CASE WHEN ((annual_resret#94119387 = NA) OR (annual_resret#94119387 = null)) THEN null ELSE cast(annual_resret#94119387 as float) END AS annual_resret#94119465, CASE WHEN ((numcos#94119388 = NA) OR (numcos#94119388 = null)) THEN null ELSE cast(numcos#94119388 as float) END AS numcos#94119466]
+- FileScan csv [fractile#94119384,cap#94119385,annual_ret#94119386,annual_resret#94119387,numcos#94119388] Batched: false, DataFilters: [], Format: CSV, Location: InMemoryFileIndex(1 paths)[file:/srv/plusamp/data/default/ea-market/output/transcripts/transcript..., PartitionFilters: [], PushedFilters: [], ReadSchema: struct<fractile:string,cap:string,annual_ret:string,annual_resret:string,numcos:string>
,None)
(3) InMemoryTableScan
Output [4]: [fractile#94119415, annual_ret#94119441, annual_resret#94119526, numcos#94119528]
Arguments: [fractile#94119415, annual_ret#94119441, annual_resret#94119526, numcos#94119528]
(4) InMemoryRelation
Arguments: [fractile#94119415, overall#94119417, annual_ret#94119441, annual_resret#94119526, numcos#94119528], CachedRDDBuilder(org.apache.spark.sql.execution.columnar.DefaultCachedBatchSerializer@208e3fd9,StorageLevel(disk, memory, deserialized, 1 replicas),*(1) Project [CASE WHEN ((fractile#94119373 = NA) OR (fractile#94119373 = null)) THEN null ELSE cast(fractile#94119373 as int) END AS fractile#94119415, CASE WHEN ((overall#94119374 = NA) OR (overall#94119374 = null)) THEN null ELSE cast(overall#94119374 as int) END AS overall#94119417, CASE WHEN ((annual_ret#94119375 = NA) OR (annual_ret#94119375 = null)) THEN null ELSE cast(annual_ret#94119375 as float) END AS annual_ret#94119441, CASE WHEN ((annual_resret#94119376 = NA) OR (annual_resret#94119376 = null)) THEN null ELSE cast(annual_resret#94119376 as float) END AS annual_resret#94119526, CASE WHEN ((numcos#94119377 = NA) OR (numcos#94119377 = null)) THEN null ELSE cast(numcos#94119377 as float) END AS numcos#94119528]
+- FileScan csv [fractile#94119373,overall#94119374,annual_ret#94119375,annual_resret#94119376,numcos#94119377] Batched: false, DataFilters: [], Format: CSV, Location: InMemoryFileIndex(1 paths)[file:/srv/plusamp/data/default/ea-market/output/transcripts/transcript..., PartitionFilters: [], PushedFilters: [], ReadSchema: struct<fractile:string,overall:string,annual_ret:string,annual_resret:string,numcos:string>
,None)
(5) Scan csv
Output [5]: [fractile#94119373, overall#94119374, annual_ret#94119375, annual_resret#94119376, numcos#94119377]
Batched: false
Location: InMemoryFileIndex [file:/srv/plusamp/data/default/ea-market/output/transcripts/transcript_model_residualized/fractiles_individually_overall.csv]
ReadSchema: struct<fractile:string,overall:string,annual_ret:string,annual_resret:string,numcos:string>
(6) Project [codegen id : 1]
Output [5]: [CASE WHEN ((fractile#94119373 = NA) OR (fractile#94119373 = null)) THEN null ELSE cast(fractile#94119373 as int) END AS fractile#94119415, CASE WHEN ((overall#94119374 = NA) OR (overall#94119374 = null)) THEN null ELSE cast(overall#94119374 as int) END AS overall#94119417, CASE WHEN ((annual_ret#94119375 = NA) OR (annual_ret#94119375 = null)) THEN null ELSE cast(annual_ret#94119375 as float) END AS annual_ret#94119441, CASE WHEN ((annual_resret#94119376 = NA) OR (annual_resret#94119376 = null)) THEN null ELSE cast(annual_resret#94119376 as float) END AS annual_resret#94119526, CASE WHEN ((numcos#94119377 = NA) OR (numcos#94119377 = null)) THEN null ELSE cast(numcos#94119377 as float) END AS numcos#94119528]
Input [5]: [fractile#94119373, overall#94119374, annual_ret#94119375, annual_resret#94119376, numcos#94119377]
(7) ColumnarToRow [codegen id : 1]
Input [4]: [fractile#94119415, annual_ret#94119441, annual_resret#94119526, numcos#94119528]
(8) InMemoryTableScan
Output [5]: [annual_resret#94119465, annual_ret#94119442, cap#94119418, fractile#94119416, numcos#94119466]
Arguments: [annual_resret#94119465, annual_ret#94119442, cap#94119418, fractile#94119416, numcos#94119466], [isnotnull(cap#94119418), (cast(cap#94119418 as string) = 0)]
(9) InMemoryRelation
Arguments: [fractile#94119416, cap#94119418, annual_ret#94119442, annual_resret#94119465, numcos#94119466], CachedRDDBuilder(org.apache.spark.sql.execution.columnar.DefaultCachedBatchSerializer@208e3fd9,StorageLevel(disk, memory, deserialized, 1 replicas),*(1) Project [CASE WHEN ((fractile#94119384 = NA) OR (fractile#94119384 = null)) THEN null ELSE cast(fractile#94119384 as int) END AS fractile#94119416, CASE WHEN ((cap#94119385 = NA) OR (cap#94119385 = null)) THEN null ELSE cast(cap#94119385 as float) END AS cap#94119418, CASE WHEN ((annual_ret#94119386 = NA) OR (annual_ret#94119386 = null)) THEN null ELSE cast(annual_ret#94119386 as float) END AS annual_ret#94119442, CASE WHEN ((annual_resret#94119387 = NA) OR (annual_resret#94119387 = null)) THEN null ELSE cast(annual_resret#94119387 as float) END AS annual_resret#94119465, CASE WHEN ((numcos#94119388 = NA) OR (numcos#94119388 = null)) THEN null ELSE cast(numcos#94119388 as float) END AS numcos#94119466]
+- FileScan csv [fractile#94119384,cap#94119385,annual_ret#94119386,annual_resret#94119387,numcos#94119388] Batched: false, DataFilters: [], Format: CSV, Location: InMemoryFileIndex(1 paths)[file:/srv/plusamp/data/default/ea-market/output/transcripts/transcript..., PartitionFilters: [], PushedFilters: [], ReadSchema: struct<fractile:string,cap:string,annual_ret:string,annual_resret:string,numcos:string>
,None)
(10) Scan csv
Output [5]: [fractile#94119384, cap#94119385, annual_ret#94119386, annual_resret#94119387, numcos#94119388]
Batched: false
Location: InMemoryFileIndex [file:/srv/plusamp/data/default/ea-market/output/transcripts/transcript_model_residualized/fractiles_individually_cap.csv]
ReadSchema: struct<fractile:string,cap:string,annual_ret:string,annual_resret:string,numcos:string>
(11) Project [codegen id : 1]
Output [5]: [CASE WHEN ((fractile#94119384 = NA) OR (fractile#94119384 = null)) THEN null ELSE cast(fractile#94119384 as int) END AS fractile#94119416, CASE WHEN ((cap#94119385 = NA) OR (cap#94119385 = null)) THEN null ELSE cast(cap#94119385 as float) END AS cap#94119418, CASE WHEN ((annual_ret#94119386 = NA) OR (annual_ret#94119386 = null)) THEN null ELSE cast(annual_ret#94119386 as float) END AS annual_ret#94119442, CASE WHEN ((annual_resret#94119387 = NA) OR (annual_resret#94119387 = null)) THEN null ELSE cast(annual_resret#94119387 as float) END AS annual_resret#94119465, CASE WHEN ((numcos#94119388 = NA) OR (numcos#94119388 = null)) THEN null ELSE cast(numcos#94119388 as float) END AS numcos#94119466]
Input [5]: [fractile#94119384, cap#94119385, annual_ret#94119386, annual_resret#94119387, numcos#94119388]
(12) ColumnarToRow [codegen id : 2]
Input [5]: [annual_resret#94119465, annual_ret#94119442, cap#94119418, fractile#94119416, numcos#94119466]
(13) Filter [codegen id : 2]
Input [5]: [annual_resret#94119465, annual_ret#94119442, cap#94119418, fractile#94119416, numcos#94119466]
Condition : (isnotnull(cap#94119418) AND (cast(cap#94119418 as string) = 0))
(14) Project [codegen id : 2]
Output [4]: [fractile#94119416, annual_ret#94119442, annual_resret#94119465, numcos#94119466]
Input [5]: [annual_resret#94119465, annual_ret#94119442, cap#94119418, fractile#94119416, numcos#94119466]
(15) Union
(16) ColumnarToRow [codegen id : 1]
Input [4]: [fractile#94119415, annual_ret#94119441, annual_resret#94119526, numcos#94119528]
(17) CollectLimit
Input [4]: [fractile#94119415, annual_ret#94119441, annual_resret#94119526, numcos#94119528]
Arguments: 1000000