dullibri/README.md

Hi 👋, ich bin Dirk

Data Engineer mit Data Science Hintergrund aus Deutschland

🔭 Woran ich aktuell arbeite

Wartung und Erweiterung eines Snowflake-Datawarehouses mit Medallion-Architektur
Hauptwerkzeuge: dbt, Airflow und Databricks
AWS-Umgebung mit CI/CD-Framework auf Bitbucket
Lerne Flutter für Mobile App Entwicklung
Rechtliche Einordnung von Zahlungsgarantien mit AWS Bedrock und Claude (Prompt Engineering)

🌱 Was ich gerade lerne

Flutter für Cross-Platform App-Entwicklung
Fortgeschrittenes Prompt Engineering mit Large Language Models

💼 Berufserfahrung

Data Engineer mit Fokus auf Cloud-Datenarchitekturen
Hintergrund in Data Science und maschinellem Lernen

🛠 Technologien & Tools

📫 Kontakt

📊 GitHub Statistiken

Pinned Loading

pump_sensor pump_sensor Public

Predicting really rare positives - a notebook on the pump_sensor data from kaggle. Including both simple indicator based approaches as well as machine learning.

HTML 1 1
titanic titanic Public

The classical data science intro with Kaggle's titanic data set is used to illustrate a simple but entire data science life-cycle including model optimization, train-test-split, eda and cleaning.

Jupyter Notebook 2
Understanding_AfD_electoral_success Understanding_AfD_electoral_success Public

A data set and an AI analysis of the electoral success of Germany's right wing party AfD including a Random Forest based machine learning approach.

Jupyter Notebook 3 3
DaxRendite DaxRendite Public

App for illustration of yields of regular investment in German DAX

R
zeit-2 zeit-2 Public

Analysis of web-scrapped news articles of DIE ZEIT. Construction of a sentiment indicator out of the articles and employment in a state-of-the-art economic prediction set-up demonstrating its usefu…

R 1
immo_bee immo_bee Public

Scrape housing data from German housing portal Immowelt.de and retrieve as comma separted file.

Jupyter Notebook 2