/// <summary> /// Returns a new RDD by applying a function to each partition of this DataFrame. /// </summary> // Python API: https://github.com/apache/spark/blob/branch-1.4/python/pyspark/sql/dataframe.py // mapPartitions(self, f, preservesPartitioning=False): public RDD <U> MapPartitions <U>(Func <IEnumerable <Row>, IEnumerable <U> > f, bool preservesPartitioning = false) { return(Rdd.MapPartitions(f, preservesPartitioning)); }
/// <summary> /// Returns a new RDD by first applying a function to all rows of this DataFrame, and then flattening the results. /// </summary> // Python API: https://github.com/apache/spark/blob/branch-1.4/python/pyspark/sql/dataframe.py flatMap(self, f) public RDD <U> FlatMap <U>(Func <Row, IEnumerable <U> > f, bool preservesPartitioning = false) { return(Rdd.FlatMap(f, preservesPartitioning)); }