DataFrame

org.apache.spark.sql.DataFrame => com.snowflake.snowpark.DataFrame

Spark	SnowPark	Notes
agg(expr: Column, exprs: Column*): DataFrame	agg
agg(exprs: Map[String, String]): DataFrame	N/A
agg(exprs: Map[String, String]): DataFrame	N/A
agg(aggExpr: (String, String), aggExprs: (String, String)*): DataFrame	agg
apply(colName: String): Column	apply
cache(): DataFrame	cacheResult	cache is an alias for persist.
col(colName: String): Column	col
collect(): Array[T]	collect
count(): Long	count
createOrReplaceTempView(viewName: String): Unit	createOrReplaceTempView
createTempView(viewName: String): Unit	N/A
crossJoin(right: Dataset[_]): DataFrame	crossJoin
cube(col1: String, cols: String*): RelationalGroupedDataset	cube
cube(cols: Column*): RelationalGroupedDataset	cube*
distinct(): Dataset[T]	distinct
drop(col: Column): DataFrame	drop*
drop(colNames: String*): DataFrame	drop*
drop(colName: String): DataFrame	drop
dropDuplicates(col1: String, cols: String*): Dataset[T]	dropDuplicates*
dropDuplicates(): Dataset[T]	dropDuplicates
except(other: Dataset[T]): Dataset[T]	except
explain(): Unit	explain
filter(condition: Column): Dataset[T]	filter
first(): T	first
foreach(func: ForeachFunction[T]): Unit	N/A
foreach(f: (T) ⇒ Unit): Unit	N/A
groupBy(col1: String, cols: String*): RelationalGroupedDataset	groupBy
groupBy(cols: Column*): RelationalGroupedDataset	groupBy *
intersect(other: Dataset[T]): Dataset[T]	intersect
join(right: Dataset[_], joinExprs: Column, joinType: String): DataFrame	join
join(right: Dataset[_], joinExprs: Column): DataFrame	join
join(right: Dataset[_], usingColumns: Seq[String], joinType: String): DataFrame	join
join(right: Dataset[_], usingColumns: Seq[String]): DataFrame	join
join(right: Dataset[_], usingColumn: String): DataFrame	join
join(right: Dataset[_]): DataFrame	join
limit(n: Int): Dataset[T]	limit
map[U](func: MapFunction[T, U], encoder: Encoder[U]): Dataset[U]	map[U]*****
map[U](func: (T) ⇒ U)(implicit arg0: Encoder[U]): Dataset[U]	map[U]*****
na: DataFrameNaFunctions	na
persist(): DataFrame	cacheResult()
persist(newLevel: StorageLevel)	cacheResult()
randomSplit(weights: Array[Double]): Array[Dataset[T]]	randomSplit
randomSplit(weights: Array[Double], seed: Long): Array[Dataset[T]]	randomSplit*
reduce(func: ReduceFunction[T]): T	reduce*****
reduce(func: (T, T) ⇒ T): T	reduce*****
rollup(col1: String, cols: String*): RelationalGroupedDataset	rollup
rollup(cols: Column*): RelationalGroupedDataset	rollup*
repartition(cols: Column): DataFrame	N/A	Repartition is a Spark concept that is not needed in Snowpark
repartition(numPartitions: int): DataFrame	N/A	Repartition is a Spark concept that is not needed in Snowpark
repartition(numPartitions: int, cols: Column): DataFrame	N/A	Repartition is a Spark concept that is not needed in Snowpark
repartitionByRange(cols: Column): DataFrame	N/A	Repartition is a Spark concept that is not needed in Snowpark
repartitionByRange(numPartitions: int, cols: Column): DataFrame	N/A	Repartition is a Spark concept that is not needed in Snowpark
sample(withReplacement: Boolean, fraction: Double): Dataset[T]	sample*****
sample(withReplacement: Boolean, fraction: Double, seed: Long): Dataset[T]	sample*****
schema: StructType	schema
select(col: String, cols: String*): DataFrame	select
select(cols: Column*): DataFrame	select
select[U1, U2, U3, U4, U5](c1: TypedColumn[T, U1], c2: TypedColumn[T, U2], c3: TypedColumn[T, U3], c4: TypedColumn[T, U4], c5: TypedColumn[T, U5]): Dataset[(U1, U2, U3, U4, U5)]	select[U1, U2, U3, U4, U5]
select[U1, U2, U3, U4](c1: TypedColumn[T, U1], c2: TypedColumn[T, U2], c3: TypedColumn[T, U3], c4: TypedColumn[T, U4]): Dataset[(U1, U2, U3, U4)]	select[U1, U2, U3, U4]
select[U1, U2, U3](c1: TypedColumn[T, U1], c2: TypedColumn[T, U2], c3: TypedColumn[T, U3]): Dataset[(U1, U2, U3)]	select[U1, U2, U3]
select[U1, U2](c1: TypedColumn[T, U1], c2: TypedColumn[T, U2]): Dataset[(U1, U2)]	select[U1, U2]
select[U1](c1: TypedColumn[T, U1]): Dataset[U1]	select[U1]
show(numRows: Int, truncate: Int): Unit	show
show(numRows: Int, truncate: Boolean): Unit	show
show(): Unit	show
show(numRows: Int): Unit	show
sort(sortExprs: Column*): Dataset[T]	sort**
sort(sortCol: String, sortCols: String*): Dataset[T]	sort
stat: DataFrameStatFunctions	stat
toDF(colNames: String*): DataFrame	toDF*
toDF(): DataFrame	toDF
union(other: Dataset[T]): Dataset[T]	union
where(conditionExpr: String): Dataset[T]	where
where(condition: Column): Dataset[T]	where
withColumn(colName: String, col: Column): DataFrame	withColumn
write: DataFrameWriter[T]	write	Transformation could cause SPRKSCL1105, SPRKSCL1106 and SPRKSCL1107