首先引入所需模块
from pyspark.conf import SparkConf
from pyspark.sql import SparkSession
from pyspark.sql.functions import udf, pandas_udf, PandasUDFType
conf=SparkConf()
conf.setAppName('my-app')
conf.set('spark.executor.memory', '4g')
conf.set("spark.driver.memory","2g")
conf.set('spark.debug.maxToStringFields', '500')
spark = SparkSession.builder. \
config(conf=conf).\