大家好，又见面了，我是你们的朋友全栈君。

前言

查询的分区情况

程序

• Jupyter

# 导入信息
from pyspark.sql import SparkSession, Row
from pyspark import SQLContext
from pyspark.sql.functions import udf, col, explode, collect_set, get_json_object, concat_ws,  split
from pyspark.sql.types import StringType, IntegerType, StructType, StructField, ArrayType, MapType
# from offline_verification_func import *
spark = SparkSession \
        .builder.master("local[50]") \
        .config("spark.executor.memory", "10g")\
        .config("spark.driver.memory", "20g")\
        .config("spark.driver.maxResultSize","4g")\