garystafford

# Purpose: Generate coffee shop sales data
# Author: Gary A. Stafford and GitHub Copilot
# Date: 2023-04-12
# Usage: python3 coffee_shop_data_gen.py 100
# Command-line argument(s): rec_count (number of records to generate as an integer)

# Write a program that creates synthetic sales data for a coffee shop.
# The program should accept a command line argument that specifies the number of records to generate.
# The program should write the sales data to a file called 'coffee_shop_sales_data.csv'.
# The program should contain the following functions:

garystafford

"transaction_id","date","time","product_id","product","calories","price","type","quantity","amount","payment_type"
"47a157f84e727fe3335db1519ee736a6","06/27/2022","19:59:42",22,"Quiche",456,4.99,"Food",2,9.98,"Debit"
"1bf01013e699ca0f804650ea50826c82","11/20/2022","06:21:14",22,"Quiche",456,4.99,"Food",3,14.97,"Cash"
"84f41c15749090d1e79bf9a48a58d6c3","08/18/2022","11:50:22",14,"Chai Tea",200,3.5,"Drink",2,7.0,"Apple Pay"
"ef1845b8438bf3b5b99d2f4891a48f03","11/13/2022","17:20:51",12,"Lemonade",120,3.0,"Drink",2,6.0,"Debit"
"9863de11be3099d6361392584e30e624","06/03/2022","18:27:03",18,"Muffin",426,3.99,"Food",2,7.98,"Gift card"
"f50ed8878250bc06f66b97f5cd2f6df7","02/21/2022","17:02:18",7,"Hot Chocolate",300,3.5,"Drink",2,7.0,"Credit"
"1903169473f41a0275ee702f2c6b1dd6","05/24/2022","14:58:25",10,"Smoothie",200,4.0,"Drink",3,12.0,"Venmo"
"164a9519fd3db952e721e9f55dc1be74","01/07/2022","14:19:35",14,"Chai Tea",200,3.5,"Drink",2,7.0,"Debit"
"dc85a202143de48ad4646190cdc0bf5c","01/28/2022","08:52:38",20,"Wrap",388,5

garystafford

# Purpose: Generate demographic data
# Author: Gary A. Stafford and GitHub Copilot
# Date: 2023-04-14
# Usage: python3 demographic_data_gen.py 100
# Command-line argument(s): rec_count (number of records to generate as an integer)

# Write an application that creates a file containing demographic data.
# The application should accept a command line argument that specifies the number of records to generate.
# The application should write the demographic data to a file called 'demographic_data.csv'.
# The application should contain the following functions:

garystafford

garystafford

garystafford

# Purpose: Generate coffee shop sales data
# Author: Gary A. Stafford and GitHub Copilot
# Date: 2023-04-12
# Usage: python3 coffee_shop_data_gen_final.py 100
# Command-line argument(s): rec_count (number of records to generate as an integer)

import csv
import random
from datetime import datetime, timedelta
import argparse

garystafford

# Purpose: Test coffee shop sales data generator
# Author: Gary A. Stafford and GitHub Copilot
# Date: 2023-04-13
# Usage: pytest coffee_shop_data_gen_tests.py -v

# write a python class that inherits from unittest.TestCase
# write a unit test for the get_product function
# write a unit test for the get_sales_record function
# write a unit test for the write_sales_records function

garystafford

"""
Purpose: Creates an Amazon DynamoDB table, adds an item to the table,
         gets that item from the table, and finally deletes the table
Author(s): Gary A. Stafford and GitHub Copilot
Created: 2023-03-26
Usage: python3 github_copilot_test.py table_name
       pytest github_copilot_test.py -v
"""

import boto3

garystafford

#!/bin/sh

# size of swapfile in megabytes
swapsize=512

# does the swap file already exist?
grep -q "swapfile" /etc/fstab

# if not then create it
if [ $? -ne 0 ]; then

garystafford

DATA_LAKE_BUCKET="<your_data_lake_s3_bucket>"
TARGET_TABLE="tickit.ecomm.sale"

spark-submit \
  --name %{TARGET_TABLE} \
  --jars /usr/lib/spark/jars/spark-avro.jar,/usr/lib/hudi/hudi-utilities-bundle.jar \
  --conf spark.sql.catalogImplementation=hive \
  --conf spark.yarn.submit.waitAppCompletion=false \
  --class org.apache.hudi.utilities.deltastreamer.HoodieDeltaStreamer `ls /usr/lib/hudi/hudi-utilities-bundle.jar` \
  --props file://${PWD}/${TARGET_TABLE}.properties \