MLA-C01 Data Preparation for Machine Learning Practice Question

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

args = getResolvedOptions(sys.argv, ['JOB_NAME'])
sc = SparkContext()
glueContext = GlueContext(sc)
spark = glueContext.spark_session
job = Job(glueContext)
job.init(args['JOB_NAME'], args)

raw = glueContext.create_dynamic_frame.from_options(
    connection_type="s3",
    connection_options={"paths": ["s3://bucket/input/year=2023/month=01/"]},
    format="json")

transformed = raw.select_fields(["col1", "col2"]).rename_field("col1", "new_col")

glueContext.write_dynamic_frame.from_options(
    frame=transformed,
    connection_type="s3",
    connection_options={"path": "s3://bucket/output/transformed"},
    format="parquet")

job.commit()