While working on nested json file using DyamicFrame for struct type of data. When i run the jobs its getting this error
Py4JJavaError: An error occurred while calling o67.getDynamicFrame. java.lang.reflect.InvocationTargetException.Let me know where i'm making mistake Any idea about this
Below is my code in GLUE JOB
import sys
from awsglue.transforms import *
from awsglue.utils import getResolvedOptions
from pyspark.context import SparkContext
from awsglue.context import GlueContext
from awsglue.dynamicframe import DynamicFrame, DynamicFrameReader,
DynamicFrameWriter, DynamicFrameCollection
from pyspark.sql.functions import lit
from awsglue.job import Job
## @params: [JOB_NAME]
args = getResolvedOptions(sys.argv, ['JOB_NAME'])
sc = SparkContext()
glueContext = GlueContext(sc)
spark = glueContext.spark_session
job = Job(glueContext)
job.init(args['JOB_NAME'], args)
## @type: DataSource
## @args: [database = "experimentdb", table_name = "experiment",
transformation_ctx = "datasource0"]
## @return: datasource0
## @inputs: []
datasource0 = glueContext.create_dynamic_frame.from_catalog(database =
"experimentdb", table_name = "experiment", transformation_ctx =
"datasource0")
## @type: ApplyMapping
## @args: [mapping = [("id", "string", "id", "string"), ("identifier",
"string", "identifier", "string"), ("session_count", "long",
"session_count", "long"), ("language", "string", "language", "string"),
("timezone", "long", "timezone", "long"), ("game_version", "string",
"game_version", "string"), ("device_os", "string", "device_os", "string"),
("device_type", "long", "device_type", "long"), ("device_model", "string",
"device_model", "string"), ("ad_id", "string", "ad_id", "string"),
("tags.phone_number", "string", "`tags.phone_number`", "string"),
("tags.real_name", "string", "`tags.real_name`", "string"), ("tags.email",
"string", "`tags.email`", "string"), ("tags.onboardingStatus", "string",
"`tags.onboardingStatus`", "string"), ("tags.dfuStatus", "string",
"`tags.dfuStatus`", "string"), ("tags.activityStatus", "string",
"`tags.activityStatus`", "string"), ("tags.lastOperationPerformed",
"string", "`tags.lastOperationPerformed`", "string"), ("last_active",
"string", "last_active", "string"), ("playtime", "long", "playtime",
"long"), ("amount_spent", "double", "amount_spent", "double"),
("created_at", "string", "created_at", "string"), ("invalid_identifier",
"string", "invalid_identifier", "string"), ("badge_count", "long",
"badge_count", "long")], transformation_ctx = "applymapping1"]
## @return: applymapping1
## @inputs: [frame = datasource0]
applymapping1 = ApplyMapping.apply(frame = datasource0, mappings = [("id",
"string", "id", "string"), ("identifier", "string", "identifier",
"string"), ("session_count", "long", "session_count", "long"), ("language",
"string", "language", "string"), ("timezone", "long", "timezone", "long"),
("game_version", "string", "game_version", "string"), ("device_os",
"string", "device_os", "string"), ("device_type", "long", "device_type",
"long"), ("device_model", "string", "device_model", "string"), ("ad_id",
"string", "ad_id", "string"), ("tags.phone_number", "string",
"`tags.phone_number`", "string"), ("tags.real_name", "string",
"`tags.real_name`", "string"), ("tags.email", "string", "`tags.email`",
"string"), ("tags.onboardingStatus", "string", "`tags.onboardingStatus`",
"string"), ("tags.dfuStatus", "string", "`tags.dfuStatus`", "string"),
("tags.activityStatus", "string", "`tags.activityStatus`", "string"),
("tags.lastOperationPerformed", "string", "`tags.lastOperationPerformed`",
"string"), ("last_active", "string", "last_active", "string"), ("playtime",
"long", "playtime", "long"), ("amount_spent", "double", "amount_spent",
"double"), ("created_at", "string", "created_at", "string"),
("invalid_identifier", "string", "invalid_identifier", "string"),
("badge_count", "long", "badge_count", "long")], transformation_ctx =
"applymapping1")
## @type: DataSink
## @args: [connection_type = "s3", connection_options = {"path":
"s3://output_data"}, format = "csv", transformation_ctx
= "datasink2"]
## @return: datasink2
## @inputs: [frame = applymapping1]
datasink2 = glueContext.write_dynamic_frame.from_options(frame =
applymapping1, connection_type = "s3", connection_options = {"path":
"s3://output_data"}, format = "csv", transformation_ctx
= "datasink2")
job.commit()
