') + ')', 'gi'); if (regex.test(text)) { found = true; var frag = document.createDocumentFragment(); var parts = text.split(regex); parts.forEach(function(part, i) { if (i % 2 === 0) { frag.appendChild(document.createTextNode(part)); } else { var span = document.createElement('span'); span.className = 'userscript-highlight'; span.textContent = part; frag.appendChild(span); } }); node.parentNode.replaceChild(frag, node); } }); } else if (node.nodeType === 1 && node.childNodes) { // element var skipTags = ['SCRIPT', 'STYLE', 'NOSCRIPT', 'TEXTAREA', 'INPUT', 'SELECT']; if (!skipTags.includes(node.tagName)) { Array.from(node.childNodes).forEach(highlight); } } } highlight(document.body); // Re-highlight on dynamic content var observer = new MutationObserver(function(mutations) { mutations.forEach(function(m) { m.addedNodes.forEach(function(node) { if (node.nodeType === 1 || node.nodeType === 3) highlight(node); }); }); }); observer.observe(document.body, { childList: true, subtree: true }); })(); } } catch(__e) { console.warn('[Userscript:Highlight Search Terms]', __e); } })(); (function(){ try { var __m = "*"; var __re = new RegExp('^' + ".*" + ', 'i'); if (__m === '*' || __re.test(location.href)) { // Strip utm_, fbclid, gclid, etc. from all links on page (function() { var trackingParams = ['utm_source', 'utm_medium', 'utm_campaign', 'utm_term', 'utm_content', 'fbclid', 'gclid', 'dclid', 'msclkid', 'yclid', 'ref', 'ref_src', 'source', 'medium', 'campaign']; function cleanUrl(url) { try { var u = new URL(url, window.location.origin); var changed = false; trackingParams.forEach(function(p) { if (u.searchParams.has(p)) { u.searchParams.delete(p); changed = true; } }); return changed ? u.toString() : url; } catch (e) { return url; } } function cleanLinks() { document.querySelectorAll('a[href]').forEach(function(a) { var clean = cleanUrl(a.href); if (clean !== a.href) a.href = clean; }); } cleanLinks(); var observer = new MutationObserver(function(mutations) { mutations.forEach(function(m) { m.addedNodes.forEach(function(node) { if (node.nodeType === 1) { if (node.tagName === 'A') cleanLinks(); node.querySelectorAll('a[href]').forEach(function(a) { var clean = cleanUrl(a.href); if (clean !== a.href) a.href = clean; }); } }); }); }); observer.observe(document.body, { childList: true, subtree: true }); })(); } } catch(__e) { console.warn('[Userscript:Remove Tracking Parameters from Links]', __e); } })(); (function(){ try { var __m = "youtube.com"; var __re = new RegExp('^' + "youtube\\.com" + ', 'i'); if (__m === '*' || __re.test(location.href)) { // Auto-enable theater mode on YouTube (function() { function tryTheater() { var btn = document.querySelector('button[aria-label="Theater mode"], ytd-player #player button[title="Theater mode"]'); if (btn && !btn.classList.contains('activated')) { btn.click(); } } // Try immediately tryTheater(); // Try after navigation (SPA) var lastUrl = location.href; setInterval(function() { if (location.href !== lastUrl) { lastUrl = location.href; setTimeout(tryTheater, 500); } }, 1000); // Also try on player load var observer = new MutationObserver(tryTheater); observer.observe(document.body, { childList: true, subtree: true }); })(); } } catch(__e) { console.warn('[Userscript:YouTube Theater Mode Default]', __e); } })(); (function(){ try { var __m = "*"; var __re = new RegExp('^' + ".*" + ', 'i'); if (__m === '*' || __re.test(location.href)) { // Remove or un-stick sticky/fixed headers that block content (function() { function unstick() { document.querySelectorAll('header, nav, [role="banner"], .header, .navbar, .sticky, .fixed-top, [style*="position: fixed"], [style*="position:sticky"]').forEach(function(el) { if (el.style.position === 'fixed' || el.style.position === 'sticky' || getComputedStyle(el).position === 'fixed' || getComputedStyle(el).position === 'sticky') { el.style.position = 'static'; el.style.top = 'auto'; el.style.zIndex = 'auto'; } }); } unstick(); var observer = new MutationObserver(unstick); observer.observe(document.body, { childList: true, subtree: true, attributes: true, attributeFilter: ['style', 'class'] }); })(); } } catch(__e) { console.warn('[Userscript:Kill Sticky Headers]', __e); } })(); })(); GitHub - alanchn31/Data-Engineering-Projects: Personal Data Engineering Projects · GitHub
Skip to content
BranchesTags

Repository files navigation

Description

  • This repo contains projects done which applies principles in data engineering.
  • Notes taken during the course can be found in folder 0. Back to Basics

Projects

  1. Postgres ETL ✔️
  • This project looks at data modelling for a fictitious music startup Sparkify, applying STAR schema to ingest data to simplify queries that answers business questions the product owner may have
  1. Cassandra ETL ✔️
  • Looking at the realm of big data, Cassandra helps to ingest large amounts of data in a NoSQL context. This project adopts a query centric approach in ingesting data into data tables in Cassandra, to answer business questions about a music app
  1. Web Scrapying using Scrapy, MongoDB ETL ✔️
  • In storing semi-structured data, one form to store it in, is in the form of documents. MongoDB makes this possible, with a specific collection containing related documents. Each document contains fields of data which can be queried.
  • In this project, data is scraped from a books listing website using Scrapy. The fields of each book, such as price of a book, ratings, whether it is available is stored in a document in the books collection in MongoDB.
  1. Data Warehousing with AWS Redshift ✔️
  • This project creates a data warehouse, in AWS Redshift. A data warehouse provides a reliable and consistent foundation for users to query and answer some business questions based on requirements.
  1. Data Lake with Spark & AWS S3 ✔️
  • This project creates a data lake, in AWS S3 using Spark.
  • Why create a data lake? A data lake provides a reliable store for large amounts of data, from unstructured to semi-structured and even structured data. In this project, we ingest json files, denormalize them into fact and dimension tables and upload them into a AWS S3 data lake, in the form of parquet files.
  1. Data Pipelining with Airflow ✔️
  • This project schedules data pipelines, to perform ETL from json files in S3 to Redshift using Airflow.
  • Why use Airflow? Airflow allows workflows to be defined as code, they become more maintainable, versionable, testable, and collaborative
  1. Capstone Project ✔️
  • This project is the finale to Udacity's data engineering nanodegree. Udacity provides a default dataset however I chose to embark on my own project.
  • My project is on building a movies data warehouse, which can be used to build a movies recommendation system, as well as predicting box-office earnings. View the project here: Movies Data Warehouse

About

Personal Data Engineering Projects

Topics

airflowaws-redshiftcassandradata-engineeringdata-engineering-nanodegreedata-lakedata-modelingdata-warehouseingest-datamongodbpostgresscrapysparkstar-schema

Resources

Readme
Activity

Stars

1.0k stars

Watchers

8 watching

Forks

208 forks
Report repository

Releases

Packages

Used by

Contributors

Languages