This repository contains a Machine Learning-driven system designed to analyze Antimicrobial Resistance (AMR) patterns and provide data-driven clinical drug recommendations. The project integrates data preprocessing pipelines, rule-based mapping engines, and predictive decision frameworks to assist in clinical decision support and AMR research.
AMR.ipynb: Exploratory Data Analysis (EDA) and initial experimentation on antimicrobial resistance datasets.Mfumo_wa_Kugundua_na_Kupendekeza_Dawa.ipynb: Core research notebook covering model training, evaluation, and recommendation logic prototyping.pipeline.py: End-to-end execution script handling data ingestion, preprocessing, and model inference workflows.decision_engine.py: Decision-making module responsible for evaluating model outputs and generating tailored treatment/drug recommendations.mapping_engine.py: Integration engine that maps pathogen profiles, resistance phenotypes, and corresponding antibiotic classifications.data.yaml: Environment configuration and dataset metadata parameter file.
- Language: Python 3.x
- Data Processing & ML:
pandas,numpy,scikit-learn - Development Environment: Jupyter Notebook, Linux / Bash Terminal
Ensure you have Python installed, then set up the required dependencies:
pip install pandas numpy scikit-learn jupyter