Sparklyr: how to center a column based spark table?

Question

I have a Spark table:

simx
x0: num 1.00 2.00 3.00 ...
x1: num 2.00 3.00 4.00 ...
...
x788: num 2.00 3.00 4.00 ...

and a handle with a name simX_tblin the R environment that is connected to this table simx.

I want to do the centering for this table, which subtracts each column with the means of the column. For example, calculation x0 - mean(x0), etc.

So far my best efforts:

meanX <- simX_tbl %>% summarise_all(funs("mean")) %>% collect()

x_centered <-  simX_tbl

for(i in 1:789) {
  colName <- paste0("x", i-1)
  colName2 <- lazyeval::interp(~ a - b, a = as.name(colName), b = as.double(meanX[i]))
  x_centered <- x_centered %>% mutate_(.dots = setNames( list(colName2) , colName) )
}

This really works when I limit the loop forfor several iterations ( 1:5), the result is x_centered %>% headcorrect. But when I do this for 789 iterations, this error occurs when I try headthis:

Error: C stack usage  7969412 is too close to the limit

The following are the output methods that I have already tried that show the error of using the C stack:

x_centered %>% head #show first 6 rows

x_centered %>% select_("x0") #select first column only

x_centered %>% sdf_register("x_centered") #register as table

x_centered %>% spark_dataframe() %>% tbl(sc, "x_centered") #also register as table

spark_write_csv(x_centered, path = "hdfs/path/here") #write as csv

, , .

/? Cstack, , , , . - 40 +, , , - (789 10000 ).

1.6.0

EDIT: ,

Answer 1

mutate_each/muate_all

library(dplyr)

df <- data.frame(x=c(1, 2, 3), y = c(-4, 5, 6), z = c(42, 42, 42))
sdf <- copy_to(sc, df, overwrite=TRUE)

mutate_all(sdf, funs(. - mean(.)))

Source:   query [3 x 3]
Database: spark connection master=local[*] app=sparklyr local=TRUE

      x         y     z
  <dbl>     <dbl> <dbl>
1    -1 -6.333333     0
2     0  2.666667     0
3     1  3.666667     0

, ( ) . :

avgs <- summarize_all(sdf, funs(mean)) %>% as.data.frame()

exprs <- as.list(paste(colnames(sdf),"-", avgs))

sdf %>%  
  spark_dataframe() %>% 
  invoke("selectExpr", exprs) %>% 
  invoke("toDF", as.list(colnames(sdf))) %>% 
  invoke("registerTempTable", "centered")

tbl(sc, "centered")

Source:   query [3 x 3]
Database: spark connection master=local[*] app=sparklyr local=TRUE

      x         y     z
  <dbl>     <dbl> <dbl>
1    -1 -6.333333     0
2     0  2.666667     0
3     1  3.666667     0

, dplyr .

, invokes dplyr :

transmute_(sdf, .dots = setNames(exprs, colnames(sdf)))

Source:   query [3 x 3]
Database: spark connection master=local[*] app=sparklyr local=TRUE

      x         y     z
  <dbl>     <dbl> <dbl>
1    -1 -6.333333     0
2     0  2.666667     0
3     1  3.666667     0

:

(. dbplyr::remote_query ):

optimizedPlan <- function(df) {
  df %>% 
    spark_dataframe() %>%
    invoke("queryExecution") %>%
    invoke("optimizedPlan")
}

dplyr:

mutate_all(sdf, funs(. - mean(.))) %>% optimizedPlan()

<jobj[190]>
  class org.apache.spark.sql.catalyst.plans.logical.Project
  Project [x#2877, y#2878, (z#1123 - _we0#2894) AS z#2879]
+- Window [avg(z#1123) windowspecdefinition(ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING) AS _we0#2894]
   +- Project [x#2877, (y#1122 - _we0#2892) AS y#2878, z#1123]
      +- Window [avg(y#1122) windowspecdefinition(ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING) AS _we0#2892]
         +- Project [(x#1121 - _we0#2890) AS x#2877, z#1123, y#1122]
            +- Window [avg(x#1121) windowspecdefinition(ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING) AS _we0#2890]
               +- Project [y#1122, z#1123, x#1121]
                  +- InMemoryRelation [x#1121, y#1122, z#1123], true, 10000, StorageLevel(disk, memory, deserialized, 1 replicas), 'df'
                     :  +- *Scan csv [x#1121,y#1122,z#1123] Format: CSV, InputPaths: file:/tmp/RtmpiEECCe/spark_serialize_f848ebf3e065c9a204092779c3e8f32ce6afdcb6e79bf6b9868ae9ff198a..., PartitionFilters: [], PushedFilters: [], ReadSchema: struct<x:double,y:double,z:double>

:

tbl(sc, "centered") %>% optimizedPlan()

<jobj[204]>
  class org.apache.spark.sql.catalyst.plans.logical.Project
  Project [(x#1121 - 2.0) AS x#2339, (y#1122 - 2.33333333333333) AS y#2340, (z#1123 - 42.0) AS z#2341]
+- InMemoryRelation [x#1121, y#1122, z#1123], true, 10000, StorageLevel(disk, memory, deserialized, 1 replicas), 'df'
   :  +- *Scan csv [x#1121,y#1122,z#1123] Format: CSV, InputPaths: file:/tmp/RtmpiEECCe/spark_serialize_f848ebf3e065c9a204092779c3e8f32ce6afdcb6e79bf6b9868ae9ff198a..., PartitionFilters: [], PushedFilters: [], ReadSchema: struct<x:double,y:double,z:double>

dplyr:

transmute_(sdf, .dots = setNames(exprs, colnames(sdf))) %>% optimizedPlan()

<jobj[272]>
  class org.apache.spark.sql.catalyst.plans.logical.Project
  Project [(x#1121 - 2.0) AS x#4792, (y#1122 - 2.33333333333333) AS y#4793, (z#1123 - 42.0) AS z#4794]
+- InMemoryRelation [x#1121, y#1122, z#1123], true, 10000, StorageLevel(disk, memory, deserialized, 1 replicas), 'df'
   :  +- *Scan csv [x#1121,y#1122,z#1123] Format: CSV, InputPaths: file:/tmp/RtmpiEECCe/spark_serialize_f848ebf3e065c9a204092779c3e8f32ce6afdcb6e79bf6b9868ae9ff198a..., PartitionFilters: [], PushedFilters: [], ReadSchema: struct<x:double,y:double,z:double>

:

Spark SQL . Spark Vector Column Spark , Vector .