Я пытаюсь записать фрейм данных pyspark в Redshift, но это приводит к ошибке: -
java.util.ServiceConfigurationError: org.apache.spark.sql.sources.DataSourceRegister: поставщик org.apache.sparkНе удалось создать экземпляр .sql.avro.AvroFileFormat
Причина: java.lang.NoSuchMethodError: org.apache.spark.sql.execution.datasources.FileFormat. $ init $ (Lorg / apache / spark / sql/ execute / datasources / FileFormat;) V
Версия Spark: 2.4.1
Команда Spark-submit: spark-submit --master local [*] --jars ~ / Downloads / spark-avro_2.12-2.4.0.jar, ~ / Загрузки / AWS-Java-СДК-1.7.4.jar, ~ / Загрузки / RedshiftJDBC42-нет-awssdk-1.2.20.1043.jar, ~ / Загрузки / Hadoop-AWS-2.7.3.jar, ~ / Downloads / hadoop-common-2.7.3.jar - пакеты com.databricks: spark-redshift_2.11: 2.0.1, com.amazonaws: aws-java-sdk: 1.7.4, org.apache.hadoop: hadoop-aws: 2.7.3, org.apache.hadoop: hadoop-common: 2.7.3, org.apache.spark: spark-avro_2.12: 2.4.0 script.py
from pyspark.sql import DataFrameReader
from pyspark.context import SparkContext
from pyspark.sql.session import SparkSession
from pyspark.sql import SQLContext
from pyspark.sql.functions import pandas_udf, PandasUDFType
from pyspark.sql.types import *
import sys
import os
pe_dl_dbname = os.environ.get("REDSHIFT_DL_DBNAME")
pe_dl_host = os.environ.get("REDSHIFT_DL_HOST")
pe_dl_port = os.environ.get("REDSHIFT_DL_PORT")
pe_dl_user = os.environ.get("REDSHIFT_DL_USER")
pe_dl_password = os.environ.get("REDSHIFT_DL_PASSWORD")
s3_bucket_path = "s3-bucket-name/sub-folder/sub-sub-folder"
tempdir = "s3a://{}".format(s3_bucket_path)
driver = "com.databricks.spark.redshift"
sc = SparkContext.getOrCreate()
sqlContext = SQLContext(sc)
spark = SparkSession(sc)
spark.conf.set("spark.sql.execution.arrow.enabled", "true")
sc._jsc.hadoopConfiguration().set("fs.s3.impl","org.apache.hadoop.fs.s3native.NativeS3FileSystem")
datalake_jdbc_url = 'jdbc:redshift://{}:{}/{}?user={}&password={}'.format(pe_dl_host, pe_dl_port, pe_dl_dbname, pe_dl_user, pe_dl_password)
"""
The table is created in Redshift as follows:
create table adhoc_analytics.testing (name varchar(255), age integer);
"""
l = [('Alice', 1)]
df = spark.createDataFrame(l, ['name', 'age'])
df.show()
df.write \
.format("com.databricks.spark.redshift") \
.option("url", datalake_jdbc_url) \
.option("dbtable", "adhoc_analytics.testing") \
.option("tempdir", tempdir) \
.option("tempformat", "CSV") \
.save()