Spark History MCP Server

from pyspark.sql import SparkSession def main(): spark = SparkSession.builder.appName("CartesianJob").getOrCreate() # Two DataFrames df1 = spark.range(1000).toDF("id1") df2 = spark.range(1000).toDF("id2") # Cross join (Cartesian) without condition # Requires spark.sql.crossJoin.enabled=true in many versions or explicit API joined = df1.crossJoin(df2) print(f"Cartesian count: {joined.count()}") spark.stop() if __name__ == "__main__": main()