ย
- โ Data Visualization/Analytics: Power BI, Looker, Tableau, Matplotlib, Seaborn, Plotly, Streamlit
- โ Data Science: PyTorch, TensorFlow, Scikit-learn, Hugging Face, Transformers, OpenCV, NLTK, SpaCy
- โ Web Scraping: BeautifulSoup, Scrapy, Selenium
- โ Maths and Statistics: Statsmodels, SciPy
- โ Domains: Regression, Classification, NLP, LLM, RAG, Computer Vision, Time Series, Neural Networks, Ensemble Methods, PCA, Clustering, Dimensionality, Reduction, Anomaly Detection
- โ Data Engineering: dbt, Terraform, SQL, PySpark
- โ MLOps: MLflow, Prefect, Mage
- โ APIs: Flask, FastAPI
- โ Cloud Platforms: GCP, AWS, Azure
ย
Currently working as Teaching Assistant for the Data Analytics and Data Science & AI Bootcamps @ Le Wagon and as AI Course Developer and Technical Editor @ Towards AI and open for further cooperation opportunities! ย
๐ CONTACT ME! ๐ Fill in this form or reach out on LinkedIn!
ย
-
๐ฑ Developed as a project leader a Computer Vision MLOps project FoodScore (summary) and its Website during the last 2 weeks of the Data Science Bootcamp of Le Wagon (March 2023)
-
๐ญ After my graduation, I worked as a volunteer in the following Data Science Projects NLP and GIS project (Website) at Omdena
-
๐ฐ My last personal Data Science/Engineering/Analysis and ML projects can be found in these repositories (feel free to click โญ if you like them ๐):
- MLOps:
- Car Price Prediction: MLOps project using MLFlow, Prefect, Flask, Docker, Grafana, Terraform, CI/CD and AWS
- Taxi Rides Prediction: MLOps project using MLFlow, Prefect, FastAPI, Docker, and GCP
- Music Clustering: MLOps project using FastAPI, Docker, CI/CD, AWS and deployment in Streamlit (see app)
- Data Analysis + Modeling:
- Cryptocurrencies Analysis: EDA and Modeling project: comparison of ARIMA, XGBoost, LSTM, and Prophet
- News Classification: EDA, Modeling and Deployment project: comparison of several Neural Networks (CNN, RNN, feedforward) and Multinomial Naive Bayes models and deployment in Streamlit (see app)
- Breast Cancer Classification: EDA and Modeling project: comparison of Random Forest using Sklearn and Spark, as part of the Advanced Data Science with IBM Specialization
- Bank Churn Classification: EDA and Modeling project including univariate/bivariate analysis, feature engineering, baseline model selection and voting classifier (LGBMClassifier, XGBoostClassifier, and CatBoostClassifier)
- Machine Learning & LLM:
- Birds Classification: Computer Vision project using Pytorch EfficientNet models and deployment in Gradio (see app)
- Q&A and Summarization: LLM project for audio and text extraction using Whisper and Langchain with app deployment using Streamlit (locally)
- RAG Llama Index: RAG (Retrieval-Augmented Generation) project for QA retrieval using Llama Index and Deep Lake
- RAG LangChain Ragas: RAG (Retrieval-Augmented Generation) project for QA retrieval using LangChain and evaluation with RAGAS
- Data Engineering:
- Hotel Reviews: Data Engineering project using Prefect, Spark, SQL, dbt, Terraform, Looker, CI/CD and GCP
- Air Quality Switzerland: Data Engineering project using Mage, dbt, Terraform, Looker, CI/CD and GCP
- MLOps:
-
๐ธ Additionally, you can find my Power BI projects:
- Personal Finance: Analysis and Comparison of Income, Bills, Profits and Available Money
- Product Sales Comparison: Product Sales Comparison using DAX functions
-
Last but not least, I also have a Tableau portfolio using groups, sets, blends, joins, table calculations, storylines, parameters, animations, and other advanced functions
ย
Cloud Storage | BigQuery | Cloud Run | VM | Vertex AI | Dataproc | Earth Engine | Container Registry |
---|
Azure Databricks | Data Lake Gen2 | Data Factory | Container Registry |
---|
S3 | EC2 | ECR | Kinesis | Lambda | RDS |
---|
ย