Kelvin Shilisia

Kelvin Shilisia

@Kelvin-Shilisia
Kenya
7
Followers
9
Following
350
Public Repos
0
Private Repos

Language Breakdown

Lines of code distribution across 9 owned repositories

3.2M Total LOC
Jupyter Notebook
3,222,819 lines
100.0%
N/A
I

I-Shaped Developer

I-shaped

Specialist — deep expertise in Jupyter Notebook

Jupyter Notebook

Collaboration Network

Global Impact visualization

LIVE
Kelvin Shilisia
0 active collaborators

Repos

353

PRs

0

Growth

+18%

Top Collaborators

No collaborator data yet.

Coding Streak

Contribution activity over the past year

1 day
161
Contributions
59
Commits
0
Pull Requests
Jun Jul Aug Sep Oct Nov Dec Jan Feb Mar Apr May Jun
Mo
We
Fr
Based on GitHub activity
Less
More

Top Repositories

Diabetes-Readmission-Prediction

This project directly addresses the challenge of preventable hospital readmissions, a massive cost and patient safety issue. By identifying high-risk patients before discharge, hospitals can move from reactive treatment to proactive intervention.

1 0
Jupyter Notebook
retrieval-augmented-generation-project1

I’m excited to share progress on my latest Generative AI project—an end-to-end Retrieval-Augmented Generation (RAG) pipeline designed to extract insights from complex PDF documents and deliver context-aware answers. This work bridges real-world information retrieval and modern generative AI capabilities.

1 0
Jupyter Notebook
Image-Classification-Model-using-the-MNIST-dataset

Using Artificial Neural Networks and TensorFlow/Keras to build, train, evaluate, and document an image classification model using the MNIST dataset.

1 0
Jupyter Notebook
Digital-Vigilance-System-DVS-for-Social-Media-Threat-Detection

To design, develop, and deploy a machine learning system capable of continuously monitoring public social media data (within legal parameters) to identify, score, and prioritize posts related to immediate criminal threats, large-scale criminal conspiracy, and tracking known gang activities.

1 0
Jupyter Notebook
California-Housing

Predicting house prices using California Housing. I have build an end-to-end machine learning workflow to predict housing prices using the California Housing dataset. The focus is on applying key concepts like: preprocessing, cross-validation, hyperparameter tuning, pipeline construction, and model deployment.

1 0
Jupyter Notebook
breast-cancer-prediction-streamlit-app

A Machine Learning web application built with **Streamlit** that predicts whether a breast tumor is **Benign** or **Malignant** based on cell nuclei measurements.

1 0
Python
Phase_4_Group1_NLP_Project
1 0
Jupyter Notebook
dsc-implementing-recommender-systems
1 0
Jupyter Notebook
syriatel-churn-classifier
1 0
Jupyter Notebook
dsc-phase-2-project-PT11-Grp4
1 0
Jupyter Notebook

Open Source Impact

Contributions to external projects

0 merged PRs
Contributed to 1 repositories