Amazon EMR の入門チュートリアルをやってみた

aws s3api create-bucket 
    --bucket <bucket-name>
    --region ap-east-1 
    --create-bucket-configuration LocationConstraint=ap-east-1

import argparse

from pyspark.sql import SparkSession

def calculate_red_violations(data_source, output_uri):
    """
    Processes sample food establishment inspection data and queries the data to find the top 10 establishments
    with the most Red violations from 2006 to 2020.

    :param data_source: The URI of your food establishment data CSV, such as 's3://amzn-s3-demo-bucket/food-establishment-data.csv'.
    :param output_uri: The URI where output is written, such as 's3://amzn-s3-demo-bucket/restaurant_violation_results'.
    """
    with SparkSession.builder.appName("Calculate Red Health Violations").getOrCreate() as spark:
        # Load the restaurant violation CSV data
        if data_source is not None:
            restaurants_df = spark.read.option("header", "true").csv(data_source)

        # Create an in-memory DataFrame to query
        restaurants_df.createOrReplaceTempView("restaurant_violations")

        # Create a DataFrame of the top 10 restaurants with the most Red violations
        top_red_violation_restaurants = spark.sql("""SELECT name, count(*) AS total_red_violations 
          FROM restaurant_violations 
          WHERE violation_type = 'RED' 
          GROUP BY name 
          ORDER BY total_red_violations DESC LIMIT 10""")

        # Write the results to the specified output URI
        top_red_violation_restaurants.write.option("header", "true").mode("overwrite").csv(output_uri)

if __name__ == "__main__":
    parser = argparse.ArgumentParser()
    parser.add_argument(
        '--data_source', help="The URI for you CSV restaurant data, like an S3 bucket location.")
    parser.add_argument(
        '--output_uri', help="The URI where output is saved, like an S3 bucket location.")
    args = parser.parse_args()

    calculate_red_violations(args.data_source, args.output_uri)

--data_source s3://事前準備で作成した S3 バケット/food_establishment_data.csv
--output_uri s3://事前準備で作成した S3 バケット/myOutputFolder	

name, total_red_violations
SUBWAY, 322
T-MOBILE PARK, 315
WHOLE FOODS MARKET, 299
PCC COMMUNITY MARKETS, 251
TACO TIME, 240
MCDONALD'S, 177
THAI GINGER, 153
SAFEWAY INC #1508, 143
TAQUERIA EL RINCONSITO, 134
HIMITSU TERIYAKI, 128