问结构化流错误py4j.protocol.Py4JNetworkError: Java端的回答为空

EN

import os
import time

from pyspark.sql.types import *
from pyspark.sql.functions import from_json, col, struct, explode, get_json_object
from ast import literal_eval
from pyspark.sql import SparkSession
from pyspark.sql.functions import expr

os.environ['PYSPARK_SUBMIT_ARGS'] = '--packages org.apache.spark:spark-sql-kafka-0-10_2.11:2.3.0 pyspark-shell'

spark = SparkSession \
    .builder \
    .appName("Spark Kafka Structured Streaming") \
    .getOrCreate()

schema_impressions = StructType() \
    .add("id_req", StringType()) \
    .add("ts_imp_request", TimestampType()) \
    .add("country", StringType()) \
    .add("TS_IMPRESSION", TimestampType()) 

schema_requests = StructType() \
    .add("id_req", StringType()) \
    .add("page", StringType()) \
    .add("conntype", StringType()) \
    .add("TS_REQUEST", TimestampType()) 

impressions = spark.readStream \
  .format("kafka") \
  .option("kafka.bootstrap.servers", "ip-ec2.internal:9092") \
  .option("subscribe", "ssp.datascience_impressions") \
  .load()

requests = spark \
  .readStream \
  .format("kafka") \
  .option("kafka.bootstrap.servers", "ip-ec2.internal:9092") \
  .option("subscribe", "ssp.datascience_requests") \
  .option("startingOffsets", "latest") \
  .load()

query_requests = requests \
        .select(col("timestamp"), col("key").cast("string"), from_json(col("value").cast("string"), schema_requests).alias("parsed")) \
        .select(col("timestamp").alias("timestamp_req"), "parsed.id_req", "parsed.page", "parsed.conntype", "parsed.TS_REQUEST") \
        .withWatermark("timestamp_req", "120 seconds") 

query_impressions = impressions \
        .select(col("timestamp"), col("key").cast("string"), from_json(col("value").cast("string"), schema_impressions).alias("parsed")) \
        .select(col("timestamp").alias("timestamp_imp"), col("parsed.id_req").alias("id_imp"), "parsed.ts_imp_request", "parsed.country", "parsed.TS_IMPRESSION") \
        .withWatermark("timestamp_imp", "120 seconds") 

query_requests.printSchema()        
query_impressions.printSchema()

> root  
|-- timestamp_req: timestamp (nullable = true)  
|-- id_req: string (nullable = true)  
|-- page: string (nullable = true)  
|-- conntype: string (nullable = true)  
|-- TS_REQUEST: timestamp (nullable = true)
> 
> root  |-- timestamp_imp: timestamp (nullable = true)  
|-- id_imp: string (nullable = true)  
|-- ts_imp_request: timestamp (nullable = true)  
|-- country: string (nullable = true)  
|-- TS_IMPRESSION: timestamp (nullable = true)

rawQuery = query_requests.join(query_impressions,  expr(""" 
    (id_req = id_imp AND 
    timestamp_imp >= timestamp_req AND 
    timestamp_imp <= timestamp_req + interval 5 minutes) 
    """), 
  "leftOuter")

rawQuery = rawQuery \
        .writeStream \
        .format("parquet") \
        .option("checkpointLocation", "/home/jovyan/streaming/applicationHistory") \
        .option("path", "/home/jovyan/streaming").start()
print(rawQuery.status)

# Example:
# spark.master                     spark://master:7077
# spark.eventLog.enabled           true
# spark.eventLog.dir               hdfs://namenode:8021/directory
# spark.serializer                 org.apache.spark.serializer.KryoSerializer
spark.driver.memory             15g
# spark.executor.extraJavaOptions  -XX:+PrintGCDetails -Dkey=value -Dnumbers="one two three"