This repository is the data-related portfolio repository I created through self-directed learning. The repository contains Generative AI, Data Engineering, Data Analysis, Machine learning, Computer Vision, NLP, and other projects.

Blogs

• Building a RAG-Powered Cooking Assistant
• The challenges and solutions working with Amharic datasets
• Data warehouse tech stack with PostgreSQL, DBT, Airflow
• Speech-to-text data collection with Kafka, Airflow, and Spark
• Automatic Speech Recognition for African languages
• Pharmaceuticals prediction sales using machine learning

Generative AI

• A RAG-Powered Cooking Assistant

Data Engineering Projects

• Python Package for lidar data points
• A Data Pipeline for Drone Data
• A Migration Project for previous Data Pipeline

Machine Learning Projects

• live Crop Recommendation feedback with Arduino with best practices in MLOPS
• Detection of Breast Cancer using Causal Inference

Computer Vision Projects

• Ethiopian Currency Counterfeit Detection using Computer Vision
• Smart Anti Theft System using Computer Vision and Arduino
• Classification and Detection of Communicable Respiratory Disease

Natural Language Processing Projects

• Sentiment Analysis for East African langugaes
• Summarization for long texts
• Sentiment Analysis for Amazon customers

Regression: Predictive Analysis

• Pharmaceutical Sales Prediction Challenge

Data Analysis

• Telecomunication Data Analysis

Clustering Projects

• Clustering

Reinforcement Learning Projects

• 0nline_ads_recommendation system

Others

• A Python Package for Baher-hasab (Ancient Ethiopian astronomical Calculations)