dapply {SparkR} | R Documentation |
Apply a function to each partition of a SparkDataFrame.
Apply a function to each partition of a SparkDataFrame and collect the result back
## S4 method for signature 'SparkDataFrame,'function',structType' dapply(x, func, schema) ## S4 method for signature 'SparkDataFrame,'function'' dapplyCollect(x, func) dapply(x, func, schema) dapplyCollect(x, func)
x |
A SparkDataFrame |
func |
A function to be applied to each partition of the SparkDataFrame. func should have only one parameter, to which a data.frame corresponds to each partition will be passed. The output of func should be a data.frame. |
schema |
The schema of the resulting DataFrame after the function is applied. It must match the output of func. |
x |
A SparkDataFrame |
func |
A function to be applied to each partition of the SparkDataFrame. func should have only one parameter, to which a data.frame corresponds to each partition will be passed. The output of func should be a data.frame. |
Other SparkDataFrame functions: $
,
$<-
, select
,
select
,
select,SparkDataFrame,Column-method
,
select,SparkDataFrame,list-method
,
selectExpr
;
SparkDataFrame-class
,
dataFrame
; [
,
[[
, subset
;
agg
, agg
,
count,GroupedData-method
,
summarize
, summarize
;
arrange
, arrange
,
arrange
, orderBy
,
orderBy
, orderBy
,
orderBy
; as.data.frame
,
as.data.frame,SparkDataFrame-method
;
attach
,
attach,SparkDataFrame-method
;
cache
; collect
;
colnames
, colnames
,
colnames<-
, colnames<-
,
columns
, names
,
names<-
; coltypes
,
coltypes
, coltypes<-
,
coltypes<-
; columns
,
dtypes
, printSchema
,
schema
, schema
;
count
, nrow
;
describe
, describe
,
describe
, summary
,
summary
,
summary,AFTSurvivalRegressionModel-method
,
summary,GeneralizedLinearRegressionModel-method
,
summary,KMeansModel-method
,
summary,NaiveBayesModel-method
;
dim
; distinct
,
unique
; dropDuplicates
,
dropDuplicates
; dropna
,
dropna
, fillna
,
fillna
, na.omit
,
na.omit
; drop
,
drop
; dtypes
;
except
, except
;
explain
, explain
;
filter
, filter
,
where
, where
;
first
, first
;
groupBy
, groupBy
,
group_by
, group_by
;
head
; histogram
;
insertInto
, insertInto
;
intersect
, intersect
;
isLocal
, isLocal
;
join
; limit
,
limit
; merge
,
merge
; mutate
,
mutate
, transform
,
transform
; ncol
;
persist
; printSchema
;
rbind
, rbind
,
unionAll
, unionAll
;
registerTempTable
,
registerTempTable
; rename
,
rename
, withColumnRenamed
,
withColumnRenamed
;
repartition
; sample
,
sample
, sample_frac
,
sample_frac
;
saveAsParquetFile
,
saveAsParquetFile
,
write.parquet
, write.parquet
;
saveAsTable
, saveAsTable
;
saveDF
, saveDF
,
write.df
, write.df
,
write.df
; selectExpr
;
showDF
, showDF
;
show
, show
,
show,GroupedData-method
,
show,WindowSpec-method
; str
;
take
; unpersist
;
withColumn
, withColumn
;
write.jdbc
, write.jdbc
;
write.json
, write.json
;
write.text
, write.text
Other SparkDataFrame functions: $
,
$<-
, select
,
select
,
select,SparkDataFrame,Column-method
,
select,SparkDataFrame,list-method
,
selectExpr
;
SparkDataFrame-class
,
dataFrame
; [
,
[[
, subset
;
agg
, agg
,
count,GroupedData-method
,
summarize
, summarize
;
arrange
, arrange
,
arrange
, orderBy
,
orderBy
, orderBy
,
orderBy
; as.data.frame
,
as.data.frame,SparkDataFrame-method
;
attach
,
attach,SparkDataFrame-method
;
cache
; collect
;
colnames
, colnames
,
colnames<-
, colnames<-
,
columns
, names
,
names<-
; coltypes
,
coltypes
, coltypes<-
,
coltypes<-
; columns
,
dtypes
, printSchema
,
schema
, schema
;
count
, nrow
;
describe
, describe
,
describe
, summary
,
summary
,
summary,AFTSurvivalRegressionModel-method
,
summary,GeneralizedLinearRegressionModel-method
,
summary,KMeansModel-method
,
summary,NaiveBayesModel-method
;
dim
; distinct
,
unique
; dropDuplicates
,
dropDuplicates
; dropna
,
dropna
, fillna
,
fillna
, na.omit
,
na.omit
; drop
,
drop
; dtypes
;
except
, except
;
explain
, explain
;
filter
, filter
,
where
, where
;
first
, first
;
groupBy
, groupBy
,
group_by
, group_by
;
head
; histogram
;
insertInto
, insertInto
;
intersect
, intersect
;
isLocal
, isLocal
;
join
; limit
,
limit
; merge
,
merge
; mutate
,
mutate
, transform
,
transform
; ncol
;
persist
; printSchema
;
rbind
, rbind
,
unionAll
, unionAll
;
registerTempTable
,
registerTempTable
; rename
,
rename
, withColumnRenamed
,
withColumnRenamed
;
repartition
; sample
,
sample
, sample_frac
,
sample_frac
;
saveAsParquetFile
,
saveAsParquetFile
,
write.parquet
, write.parquet
;
saveAsTable
, saveAsTable
;
saveDF
, saveDF
,
write.df
, write.df
,
write.df
; selectExpr
;
showDF
, showDF
;
show
, show
,
show,GroupedData-method
,
show,WindowSpec-method
; str
;
take
; unpersist
;
withColumn
, withColumn
;
write.jdbc
, write.jdbc
;
write.json
, write.json
;
write.text
, write.text
## Not run: df <- createDataFrame (sqlContext, iris) df1 <- dapply(df, function(x) { x }, schema(df)) collect(df1) # filter and add a column df <- createDataFrame ( sqlContext, list(list(1L, 1, "1"), list(2L, 2, "2"), list(3L, 3, "3")), c("a", "b", "c")) schema <- structType(structField("a", "integer"), structField("b", "double"), structField("c", "string"), structField("d", "integer")) df1 <- dapply( df, function(x) { y <- x[x[1] > 1, ] y <- cbind(y, y[1] + 1L) }, schema) collect(df1) # the result # a b c d # 1 2 2 2 3 # 2 3 3 3 4 ## End(Not run) ## Not run: df <- createDataFrame (sqlContext, iris) ldf <- dapplyCollect(df, function(x) { x }) # filter and add a column df <- createDataFrame ( sqlContext, list(list(1L, 1, "1"), list(2L, 2, "2"), list(3L, 3, "3")), c("a", "b", "c")) ldf <- dapplyCollect( df, function(x) { y <- x[x[1] > 1, ] y <- cbind(y, y[1] + 1L) }) # the result # a b c d # 2 2 2 3 # 3 3 3 4 ## End(Not run)