glue

job.py

import sys
from awsglue.context import GlueContext
from pyspark.context import SparkContext
from awsglue.dynamicframe import DynamicFrame

# Initialize Glue context
sc = SparkContext()
glueContext = GlueContext(sc)

# Read the CSV file from S3
input_path = "s3://your-bucket/your-file.csv"
dynamic_frame = glueContext.create_dynamic_frame.from_options(
    format="csv",
    connection_type="s3",
    connection_options={"paths": [input_path]},
    format_options={"withHeader": True}
)

# Convert DynamicFrame to DataFrame for transformations
df = dynamic_frame.toDF()

# Perform your data transformation (e.g., group by 'date')
grouped_df = df.groupBy("date").agg(
    # example aggregation, replace with your actual logic
    sum("transaction_amount").alias("total_amount")
)

# Write out partitioned data
output_path = "s3://your-bucket/output/"
grouped_df.write.partitionBy("date").csv(output_path, header=True)