Hi I am using AWS Glue to try and load data from a Json file in S3 into Redshift. I am using a Json crawler with path as $[*] and for some reason one of the fields (grade) is coming into the table with a Json structure:
Any ideas on how to make "grade" just display the value for the grade itself? Do I need to tweak the PySpark script for the job?
This is the script so far:
import sys
from awsglue.transforms import *
from awsglue.utils import getResolvedOptions
from pyspark.context import SparkContext
from awsglue.context import GlueContext
from awsglue.job import Job
from pyspark.sql.functions import current_date
from awsglue.dynamicframe import DynamicFrame
## @params: [TempDir, JOB_NAME]
args = getResolvedOptions(sys.argv, ['TempDir','JOB_NAME'])
sc = SparkContext()
glueContext = GlueContext(sc)
spark = glueContext.spark_session
job = Job(glueContext)
job.init(args['JOB_NAME'], args)
## @type: DataSource
## @args: [database = "linkredshift", table_name = "uni3", transformation_ctx = "datasource0"]
## @return: datasource0
## @inputs: []
datasource0 = glueContext.create_dynamic_frame.from_catalog(database = "linkredshift", table_name = "uni3", transformation_ctx = "datasource0")
df=datasource0.toDF().withColumn('data_date',current_date())
datasource0 = DynamicFrame.fromDF(df, glueContext, "datasource0")
## @type: ApplyMapping
## @args: [mapping = [("first_name", "string", "first_name", "string"), ("last_name", "string", "last_name", "string"), ("subject", "string", "subject", "string"), ("grade", "string", "grade", "string")], transformation_ctx = "applymapping1"]
## @return: applymapping1
## @inputs: [frame = datasource0]
applymapping1 = ApplyMapping.apply(frame = datasource0, mappings = [("first_name", "string", "first_name", "string"), ("last_name", "string", "last_name", "string"), ("subject", "string", "subject", "string"), ("grade", "string", "grade", "string"), ("data_date", "date", "data_date", "date")], transformation_ctx = "applymapping1")
## @type: SelectFields
## @args: [paths = ["subject", "grade", "last_name", "first_name"], transformation_ctx = "selectfields2"]
## @return: selectfields2
## @inputs: [frame = applymapping1]
selectfields2 = SelectFields.apply(frame = applymapping1, paths = ["subject", "grade", "last_name", "first_name", "data_date"], transformation_ctx = "selectfields2")
## @type: ResolveChoice
## @args: [choice = "MATCH_CATALOG", database = "linkredshift", table_name = "dev_public_students", transformation_ctx = "resolvechoice3"]
## @return: resolvechoice3
## @inputs: [frame = selectfields2]
resolvechoice3 = ResolveChoice.apply(frame = selectfields2, choice = "MATCH_CATALOG", database = "linkredshift", table_name = "dev_public_students", transformation_ctx = "resolvechoice3")
## @type: ResolveChoice
## @args: [choice = "make_cols", transformation_ctx = "resolvechoice4"]
## @return: resolvechoice4
## @inputs: [frame = resolvechoice3]
resolvechoice4 = ResolveChoice.apply(frame = resolvechoice3, choice = "make_cols", transformation_ctx = "resolvechoice4")
## @type: DataSink
## @args: [database = "linkredshift", table_name = "dev_public_students", redshift_tmp_dir = TempDir, transformation_ctx = "datasink5"]
## @return: datasink5
## @inputs: [frame = resolvechoice4]
datasink5 = glueContext.write_dynamic_frame.from_catalog(frame = resolvechoice4, database = "linkredshift", table_name = "dev_public_students", redshift_tmp_dir = args["TempDir"], transformation_ctx = "datasink5")
job.commit()