Jonas Ferreira JnsFerreira

🖥️

Coding the future

Machines take me by surprise with great frequency

JnsFerreira / .py

Created July 18, 2023 17:29

athena_create_table_generator.py

	import boto3

	def get_glue_table_schema(database_name, table_name):
	client = boto3.client('glue')

	response = client.get_table(
	DatabaseName=database_name,
	Name=table_name
	)

JnsFerreira / glue_job_jdbc_to_s3.py

Created April 6, 2022 23:09

	# References:
	# https://aws.amazon.com/blogs/big-data/load-data-incrementally-and-optimized-parquet-writer-with-aws-glue/

	import sys

	from awsglue.job import Job
	from awsglue.transforms import *
	from pyspark.context import SparkContext
	from awsglue.context import GlueContext
	from awsglue.utils import getResolvedOptions

JnsFerreira / crawler.py

Last active August 3, 2021 19:06

book_crawler

	# Built-in libraries
	from time import time
	import threading
	import logging
	import requests
	import math

	# Project libraries
	from config import functions as f
	from config import selenium_functions as sf

JnsFerreira / map_example.py

Created February 1, 2021 23:52

Using map in Apache Beam

	import apache_beam as beam

	with beam.Pipeline() as pipeline:
	plants = (
	pipeline
	\| 'Gardening plants' >> beam.Create([
	' 🍓Strawberry \n',
	' 🥕Carrot \n',
	' 🍆Eggplant \n',
	' 🍅Tomato \n',