mohamedyaqub90-lgtm/Kenya-Hospitals-Health-Record

# Kenya Hospitals Health Record Analysis ## Project Overview This project analyzes patient health records collected from multiple hospitals in Kenya. The goal is to uncover trends in diagnoses, departmental patient loads, treatment costs, and insurance coverage gaps. The dataset spans from 2020 to 2025 and includes over 1,000 patient encounters. ## Tools used -Excel -Git -Github. ## Challenges Faced ### Data Quality Issues - Inconsistent date formats (DD/MM/YYYY vs MM/DD/YYYY) across different records. - Missing values in fields like Phone Number and Insurance Provider. - Spelling variations in diagnosis names (e.g., Malaria vs Maleria if present). - Duplicate patient records that needed identification and removal. ### Technical Challenges - Navigating Git Bash and understanding file paths, especially moving files from Downloads to the project folder. - Learning the difference between > (overwrite) and >> (append) when editing files via the terminal. - Handling spaces and special characters in file and folder names while using the command line. - Setting up the correct folder structure before committing to Git. ### Data Processing Challenges - Converting the Excel file (.xlsx) into a format suitable for Python analysis (CSV). - Handling large text fields and cleaning free-text doctor and department names. - Standardizing currency values (KES) for proper numerical analysis. - Dealing with outliers in bill amounts that could skew statistical summaries. ### Organizational Challenges - Keeping the project folder structured and organized from the start. - Writing clear and comprehensive documentation in the README. - Ensuring all team members (or future collaborators) understand the data schema.