randomSplit
randomSplit.RdReturn a list of randomly split dataframes with the provided weights.
Usage
randomSplit(x, weights, seed)
# S4 method for SparkDataFrame,numeric
randomSplit(x, weights, seed)Arguments
- x
A SparkDataFrame
- weights
A vector of weights for splits, will be normalized if they don't sum to 1
- seed
A seed to use for random split
See also
Other SparkDataFrame functions:
SparkDataFrame-class,
agg(),
alias(),
arrange(),
as.data.frame(),
attach,SparkDataFrame-method,
broadcast(),
cache(),
checkpoint(),
coalesce(),
collect(),
colnames(),
coltypes(),
createOrReplaceTempView(),
crossJoin(),
cube(),
dapplyCollect(),
dapply(),
describe(),
dim(),
distinct(),
dropDuplicates(),
dropna(),
drop(),
dtypes(),
exceptAll(),
except(),
explain(),
filter(),
first(),
gapplyCollect(),
gapply(),
getNumPartitions(),
group_by(),
head(),
hint(),
histogram(),
insertInto(),
intersectAll(),
intersect(),
isLocal(),
isStreaming(),
join(),
limit(),
localCheckpoint(),
merge(),
mutate(),
ncol(),
nrow(),
persist(),
printSchema(),
rbind(),
rename(),
repartitionByRange(),
repartition(),
rollup(),
sample(),
saveAsTable(),
schema(),
selectExpr(),
select(),
showDF(),
show(),
storageLevel(),
str(),
subset(),
summary(),
take(),
toJSON(),
unionAll(),
unionByName(),
union(),
unpersist(),
unpivot(),
withColumn(),
withWatermark(),
with(),
write.df(),
write.jdbc(),
write.json(),
write.orc(),
write.parquet(),
write.stream(),
write.text()
Examples
if (FALSE) {
sparkR.session()
df <- createDataFrame(data.frame(id = 1:1000))
df_list <- randomSplit(df, c(2, 3, 5), 0)
# df_list contains 3 SparkDataFrames with each having about 200, 300 and 500 rows respectively
sapply(df_list, count)
}