Я столкнулся с проблемой при попытке включить com.databricks: spark-xml_2.10: 0.4.1 в мой код pyspark в pycharm
import pyspark
from pyspark.shell import sc
from pyspark import SparkContext
from pyspark.sql import SQLContext
from pyspark.sql import SparkSession
from pyspark.sql.types import *
from pyspark.sql import SparkSession
import os
sc = SparkContext.getOrCreate()
sqlContext = SQLContext(sc)
os.environ["PYSPARK_SUBMIT_ARGS"] = (
"--packages com.databricks:spark-xml_2.10:0.4.1 pyspark-shell"
)
if __name__ == '__main__':
df = sqlContext.read.format('org.apache.spark.sql.xml') \
.option('rowTag', 'lei:Extension')
.load('C:\\Users\\Consultant\\Desktop\\20170501-gleif-concatenated-file'
'-lei2.xml')
df.show()
, но он возвращает
Exception in thread "main" org.apache.spark.SparkException: Cannot load main class from JAR file:/C:/spark-2.4.5-bin-hadoop2.7/python/dependency
at org.apache.spark.deploy.SparkSubmitArguments.error(SparkSubmitArguments.scala:657)
at org.apache.spark.deploy.SparkSubmitArguments.loadEnvironmentArguments(SparkSubmitArguments.scala:221)
at org.apache.spark.deploy.SparkSubmitArguments.<init>(SparkSubmitArguments.scala:116)
at org.apache.spark.deploy.SparkSubmit$$anon$2$$anon$1.<init>(SparkSubmit.scala:907)
at org.apache.spark.deploy.SparkSubmit$$anon$2.parseArguments(SparkSubmit.scala:907)
at org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:81)
at org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:920)
at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:929)
at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
Traceback (most recent call last):
File "C:/spark-2.4.5-bin-hadoop2.7/python/test.py", line 2, in <module>
from pyspark.shell import sc
File "C:\spark-2.4.5-bin-hadoop2.7\python\pyspark\shell.py", line 38, in <module>
SparkContext._ensure_initialized()
File "C:\spark-2.4.5-bin-hadoop2.7\python\pyspark\context.py", line 316, in _ensure_initialized
SparkContext._gateway = gateway or launch_gateway(conf)
File "C:\spark-2.4.5-bin-hadoop2.7\python\pyspark\java_gateway.py", line 46, in launch_gateway
return _launch_gateway(conf)
File "C:\spark-2.4.5-bin-hadoop2.7\python\pyspark\java_gateway.py", line 108, in _launch_gateway
raise Exception("Java gateway process exited before sending its port number")
Exception: Java gateway process exited before sending its port number
Я бы хотел добавить внешний баночек прямо в pycharm. Возможно ли это?
Заранее спасибо.