Skip to content
View portia-da-analyst's full-sized avatar

Block or report portia-da-analyst

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
portia-da-analyst/README.md

Typing SVG


β™₯ ECG β€” LEAD II 72 BPM βœ“ Healthcare Data Analytics Β· Portia Tjempe


πŸ‘€ About Me

I'm Portia Tjempe, a Healthcare Data Analyst and BSc Data Science student based in South Africa πŸ‡ΏπŸ‡¦, with hands-on clinical experience from Emergency Medical Services combined with a growing data science skillset.

My work sits at the intersection of clinical operations, health informatics, and machine learning β€” I build predictive models, public health dashboards, and workflow automation tools that support evidence-based decision-making in healthcare.

πŸ“ South Africa Β |Β  πŸ₯ Former Medical Ambulance Assistant Β |Β  πŸŽ“ BSc Data Science β€” 2nd Year Β |Β  πŸ“§ pmammule@gmail.com


🧬 Tech Stack & Skills

πŸ’Š Programming & Analytics

Python SQL R MATLAB SAS

πŸ“Š Data & Reporting

Power BI Tableau Excel Pandas Scikit-learn NumPy Matplotlib

πŸ₯ Healthcare & Compliance

EHR/EMR HIPAA POPIA Health Informatics Medical Coding

πŸ—„οΈ Databases & Cloud

MySQL PostgreSQL SQL Server BigQuery

πŸ› οΈ Tools

Git Jupyter Google Workspace SPSS


πŸ”¬ Featured Projects


πŸ«€ Healthcare Patient Readmission Predictor

Python Β· Scikit-learn Β· Pandas Β· Logistic Regression Β· SMOTE

ECG monitors and patient data in a hospital setting

Predictive ML model identifying high-risk hospital readmission patients to support clinical decision-making.

  • 🧹 Cleaned and processed 10,000+ patient records β€” handled missing data and class imbalance using SMOTE
  • 🎯 Achieved 82% model accuracy β€” key predictors: diagnosis codes, length of stay, prior visit history
  • πŸ“Š Visualised risk stratification outputs in Matplotlib for clinical team review and patient intervention planning

View on GitHub


πŸ›οΈ Mall Customer Segmentation Analysis

Python Β· Power BI Β· K-Means Clustering Β· Data Visualisation

Data analytics dashboard with charts and segmentation visuals

Customer segmentation using unsupervised machine learning to identify distinct behavioural clusters.

  • πŸ—‚οΈ Aggregated and cleaned multi-source datasets β€” applied K-Means clustering for demographic and spending profiles
  • πŸ“ˆ Built dynamic Power BI dashboard communicating segment insights to non-technical stakeholders
  • πŸ’‘ Delivered actionable recommendations for targeted engagement strategies

View on GitHub


βš™οΈ Virtual Healthcare Innovation Initiative

Google Workspace Β· Automation Β· Documentation Β· SOPs

Healthcare coordination and scheduling workflow

Streamlined patient scheduling and follow-up processes during a virtual healthcare internship programme.

  • πŸ“§ Designed automated email follow-up templates β€” reduced manual coordination time by ~30%
  • πŸ“‹ Created standardised onboarding documentation and SOP guides for virtual care teams
  • 🀝 Supported cross-functional coordination between clinical supervisors and remote interns

View Document


🩻 Work Experience

Role Organisation Period
πŸš‘ Medical Ambulance Assistant Emergency Medical Services Β· South Africa 2018 – 2020
πŸ—‚οΈ Data Capturing Clerk & Office Admin Keith Ho Β· On-Site 2022 – 2023
πŸ’» Virtual Assistant Trainee ALX Programme Β· Remote 2024 – 2025
πŸ₯ Healthcare Internship Coordinator YUVA β€” Henry Harvin Education Β· Remote 2025
🌍 Data Admin & QA Specialist (Volunteer) Idealist Β· Remote 2025 – Present

πŸ… Certifications & Simulations

🏒 Organisation πŸ“œ Programme
Tata Consultancy Services Data Visualisation & Insights
Deloitte Data Analytics Job Simulation
Citi Data Analytics & Quantitative Finance
BCG Data Science & Advanced Analytics

πŸŽ“ Education

BSc Data Science 2nd Year South Africa

Relevant coursework: Statistical Modelling Β· Machine Learning Β· Database Systems Β· Health Informatics


πŸ“‘ Connect With Me

LinkedIn GitHub Email


"Data is the stethoscope of the 21st century β€” it lets us listen to systems at scale."


snake gif


Profile Views

Pinned Loading

  1. Mall-Customer-Segmentation-Analysis Mall-Customer-Segmentation-Analysis Public

    Customer segmentation analysis using K-Means clustering in Python, including full EDA, bug fixes, and business insights.

    Jupyter Notebook 2

  2. BCG-X-Customer-Churn-Prediction-Strategic-Insights BCG-X-Customer-Churn-Prediction-Strategic-Insights Public

    Jupyter Notebook

  3. Hospital-Patient-Re-Admission-Analysis-Prediction-Model- Hospital-Patient-Re-Admission-Analysis-Prediction-Model- Public

    The analysis was conducted using a structured Python-based data science workflow applied to a labelled hospital readmission dataset. Two ensemble machine learning models β€” a Random Forest Classifie…

    Jupyter Notebook