<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/">
  <channel>
    <title>Data Engineering on Luis Núñez — Data Engineer (M.Sc.)</title>
    <link>https://luis-fer-333.github.io/categories/data-engineering/</link>
    <description>Recent content in Data Engineering on Luis Núñez — Data Engineer (M.Sc.)</description>
    <generator>Hugo -- gohugo.io</generator>
    <language>en-us</language>
    <lastBuildDate>Sun, 01 Jun 2025 00:00:00 +0000</lastBuildDate><atom:link href="https://luis-fer-333.github.io/categories/data-engineering/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Nobel Prize Data Lake — Medallion Architecture on AWS</title>
      <link>https://luis-fer-333.github.io/projects/nobel-prize-data-lake/</link>
      <pubDate>Tue, 01 Apr 2025 00:00:00 +0000</pubDate>
      <guid>https://luis-fer-333.github.io/projects/nobel-prize-data-lake/</guid>
      <description>A medallion-architecture data lake on AWS S3 with Prefect-orchestrated ETL Lambdas — raw API responses → bronze joins → silver analytics table.</description>
    </item>
    
    <item>
      <title>Movie Database ETL Pipeline — Multi-Source Ingestion to SQLite</title>
      <link>https://luis-fer-333.github.io/projects/movie-database-etl/</link>
      <pubDate>Sun, 01 Dec 2024 00:00:00 +0000</pubDate>
      <guid>https://luis-fer-333.github.io/projects/movie-database-etl/</guid>
      <description>An end-to-end ETL pipeline that ingests movie metadata from IMDb bulk files and a REST API, stages it in MongoDB, and lands it in a normalized relational schema with foreign keys.</description>
    </item>
    
    <item>
      <title>Airbnb Valencia — Cloud BI with Supabase &#43; Preset</title>
      <link>https://luis-fer-333.github.io/projects/airbnb-valencia-bi/</link>
      <pubDate>Sun, 01 Jun 2025 00:00:00 +0000</pubDate>
      <guid>https://luis-fer-333.github.io/projects/airbnb-valencia-bi/</guid>
      <description>A full BI stack analyzing 8,847 Airbnb listings — from raw CSV load through SQL modeling on Supabase to stakeholder dashboards in Preset.</description>
    </item>
    
    <item>
      <title>Movie Analytics — Deep EDA for Investment Decisions</title>
      <link>https://luis-fer-333.github.io/projects/movie-analytics-eda/</link>
      <pubDate>Fri, 01 Nov 2024 00:00:00 +0000</pubDate>
      <guid>https://luis-fer-333.github.io/projects/movie-analytics-eda/</guid>
      <description>A deep exploratory analysis across 4,000 movies to identify the factors driving box-office success — framed around a low-budget-production investment scenario.</description>
    </item>
    
    <item>
      <title>Sentiment Analysis at Scale — PySpark on AWS</title>
      <link>https://luis-fer-333.github.io/projects/spark-sentiment-pipeline/</link>
      <pubDate>Sat, 01 Mar 2025 00:00:00 +0000</pubDate>
      <guid>https://luis-fer-333.github.io/projects/spark-sentiment-pipeline/</guid>
      <description>A distributed ML pipeline processing 17M Amazon reviews with PySpark MLlib on AWS Glue — including S3 medallion storage, feature engineering, and model serialization for batch inference.</description>
    </item>
    
    <item>
      <title>Spanish Electricity Demand — Time-Series Pipeline with InfluxDB &#43; Forecasting</title>
      <link>https://luis-fer-333.github.io/projects/electricity-demand-pipeline/</link>
      <pubDate>Thu, 01 May 2025 00:00:00 +0000</pubDate>
      <guid>https://luis-fer-333.github.io/projects/electricity-demand-pipeline/</guid>
      <description>A continuous ingestion pipeline for Spanish grid demand with InfluxDB storage and Prophet-based day-ahead forecasting. Includes a dashboard for real vs forecast visualization.</description>
    </item>
    
    <item>
      <title>Formula 1 Data Analysis — Multi-Table Pandas Pipeline</title>
      <link>https://luis-fer-333.github.io/projects/formula1-data-analysis/</link>
      <pubDate>Tue, 01 Oct 2024 00:00:00 +0000</pubDate>
      <guid>https://luis-fer-333.github.io/projects/formula1-data-analysis/</guid>
      <description>A pandas-driven analysis across 13 relational CSVs (75 years of F1 history) with multi-way joins, filtering, and map-based visualization.</description>
    </item>
    
  </channel>
</rss>
