spirdlytics/Data-Science-ALX

Showcasing ML pipelines and predictive algorithms built through ALX Data Science, applied directly to solving complex agricultural challenges in Africa. # ALX Data Science Portfolio **Building predictive models and ML pipelines to solve complex challenges in African agrifood systems.** Welcome to my Data Science portfolio. While my background in Agriculture (Dryland Option) grounds me in the physical realities of climate, soil, and food production, this repository serves as my technical engine. Here, I document my progression through the ALX Data Science program, showcasing how I apply machine learning, algorithmic thinking, and advanced analytics to build resilient, automated agritech solutions. --- ## Core Curriculum & Skill Progression This table outlines the foundational modules completed during the program, the technical focus of each, and the resulting capabilities. | Module | Technical Focus & Skills | Outcomes | | :--- | :--- | :--- | | **01: Python I: Foundations & Control Flow** | Master Python fundamentals (data structures, control flow, modular functions) and build a professional development workflow using Git, GitHub, and AI coding tools. | A working Python foundation and a version-controlled codebase built the way professional data teams expect. | | **02: Python II: Programming & Algorithmic Thinking** | Write scalable Python using OOP, algorithmic complexity analysis, and advanced data manipulation with NumPy and pandas. | The ability to architect clean, efficient, reusable code that data science teams can build on. | | **03: Python III: EDA, Data Visualisation & Reporting** | Transform raw data into narratives using exploratory analysis, statistical hypothesis testing, and advanced visualisations. | A published Python package and a data story demonstrating end-to-end analytical thinking. | | **04: Supervised Learning I: Regression Foundations** | Build, evaluate, and deploy predictive regression models using scikit-learn, applying regularisation techniques. | A production-ready machine learning model, saved and deployable, with rigorous evaluation metrics. | | **05: Supervised Learning II: Clas …