import shutil from pyspark.sql import SparkSession base_path = "/tmp/sg-spark-package" avro_path = f"{base_path}/orders-avro" shutil.rmtree(base_path, ignore_errors=True) spark = ( SparkSession.builder.master("local[2]") .appName("sg-package-check") .getOrCreate() ) spark.sparkContext.setLogLevel("ERROR") orders = spark.createDataFrame( [ ("ORD-1001", "APAC", 3), ("ORD-1002", "EMEA", 1), ], "order_id string, region string, item_count int", ) orders.write.format("avro").mode("overwrite").save(avro_path) loaded = spark.read.format("avro").load(avro_path) print(f"avro_rows={loaded.count()}") loaded.orderBy("order_id").show(truncate=False) spark.stop() shutil.rmtree(base_path, ignore_errors=True)