It gave some inspiration: this worked for me: It exposes a stupid function called "add" that adds 1 to the first column of the dataframe package example
import org.apache.spark.sql.DataFrame;
import org.apache.spark.SparkContext
import org.apache.spark.SparkContext._
import org.apache.spark.SparkConf
object Hello {
def add(df : DataFrame): DataFrame = {
val fc = df.columns(0);
var df2 = df.withColumn( fc, df.col(fc) + 1 );
return df2;
}
}
from pyspark.sql import DataFrame
df2 = DataFrame(sc._jvm.example.Hello.add(df._jdf),sqlContext)
... View more
