from pathlib import Path import shutil from pyspark.sql import SparkSession spark = ( SparkSession.builder .appName("sg-local-check") .master("local[2]") .config("spark.ui.enabled", "false") .config("spark.ui.showConsoleProgress", "false") .getOrCreate() ) spark.sparkContext.setLogLevel("ERROR") output = Path("/tmp/sg-spark-output/partition-count") shutil.rmtree(output, ignore_errors=True) df = spark.range(0, 16, 1, numPartitions=4) print(f"original partitions: {df.rdd.getNumPartitions()}")