from pathlib import Path from pyspark.sql import SparkSession def load_partition(values): from sg_metrics import describe_value return [describe_value(value) for value in values] spark = SparkSession.builder.appName("sg-py-dependency-package").getOrCreate() spark.sparkContext.setLogLevel("ERROR") result = spark.sparkContext.parallelize([1, 2, 3], 2).mapPartitions(load_partition).collect() pyfiles = [Path(uri).name for uri in spark.sparkContext.listFiles if uri.endswith("sg_metrics.zip")] print("dependency_import=" + ",".join(result)) print("pyfile_added=" + ",".join(pyfiles)) spark.stop()