Newsletter

Project and product updates. Click a title to expand or collapse.

Try Storyteller on PyPI

We are excited to announce that STORYTELLER is now available for testing on PyPI!

STORYTELLER is a Python package that makes it easier to explore and work with Demographic and Health Survey (DHS) datasets. It provides simple commands for launching a web-based data explorer, running predefined queries, and exporting cleaned datasets for further analysis.

What You Can Do

  • Start an interactive Datasette web app to browse DHS databases.
  • Run predefined queries and export datasets in ready-to-use formats.
  • Enable full-text search (FTS) on DHS variable tables.
  • Export cleaned data to CSV and reproducible metadata to JSON.

How to Install

pip install storyteller-dhs

Learn More

Check out the project on PyPI: https://pypi.org/project/storyteller-dhs/

Curious about how we are using DHS data with AI/ML? Visit our DHS AI/ML Toolkit.

We are still in the early stages of this project, and your feedback will be invaluable. Please try it out and let us know your experience!

We are excited to announce the release of our new project: DHS-To-Database-dhs2CSVTables-simplified! This open-source tool is designed to simplify the conversion of raw Demographic and Health Surveys (DHS) data into a format suitable for database storage in CSVTables format.

What is DHS-To-Database-dhs2CSVTables-simplified?

Our project serves as a convenient wrapper around the existing DHS-To-Database tool developed by Harry Gibson. While the original tool is powerful, we recognized the need for a more accessible and user-friendly way to handle DHS data conversions.

Key Features

  • User-Friendly Wrapper: Provides an easy-to-use interface for converting raw DHS data.
  • Supports Python 3.8 and Above: Ensure compatibility with modern Python environments.
  • Simplified Usage: Designed for seamless interaction with raw DHS data.
  • CSV to SQLite Conversion (New in v0.2.0): Now supports converting relational CSV tables to a SQLite database using the csvs-to-sqlite command-line tool.

For detailed documentation and to get started, please visit our GitHub repository: DHS-To-Database-dhs2CSVTables-simplified.

A special thanks to Harry Gibson for his foundational work on the DHS-To-Database tool.

Contribute

We are thrilled to announce the official launch of NIGATWA1087, a powerful web application boilerplate framework designed to accelerate your development journey.

NIGATWA1087 empowers you to:

  • Hit the ground running: Skip repetitive setup tasks with a comprehensive boilerplate structure, ready to customize
  • Build with confidence: Leverage the time-tested foundation used in our own projects like kofiyatechapps
  • Build a robust dashboard like FLOWER: Leverage NIGATWA1087's foundation to create complex and data-rich dashboards like FLOWER
  • Focus on what matters: Streamline user management with built-in user authentication, registration, and secure password recovery
  • Empower your users: Equip administrators with tools to support and manage your webapp effectively
  • Handle the unexpected: Ensure a seamless user experience with error handling for incorrect URLs
  • Deploy where you need: Choose between AWS cloud deployment with Amazon RDS database or local development environment with either SQLite or PostgreSQL database

Building on the success of KILIMA TULIP AI, we are excited to introduce our latest initiative. This project, rooted in Explainable AI (XAI), focuses on child survival risk analysis using Bayesian statistics. By employing transparent and interpretable Bayesian methods, we aim to provide not just insights but a clear understanding of the factors influencing child survival.

For those eager to explore the CIAO BAYESIAN results and insights, you can access them conveniently through our user-friendly FLOWER Dashboard.

Stay tuned as we embark on this journey at the intersection of data-driven discovery and transparent AI solutions.

Welcome to the FLOWER Dashboard, your gateway to exploring child survival risk insights powered by the KILIMA TULIP AI model. With the FLOWER Dashboard, you can customize your analysis by selecting a specific country, feature group, and risk factor.

Our AI-driven predictions provide valuable insights into child survival risk. These insights empower you to allocate resources effectively, develop targeted interventions, and contribute to research efforts.

Get started today by visiting the FLOWER Dashboard and making data-driven decisions to improve child well-being.

Welcome to KILIMA TULIP AI, a project dedicated to predicting under-five (U5) child survival risk in Africa using Deep Learning AI techniques. This project builds upon the success of our previous DEEP MINTILO AI project, where we achieved a remarkable above 90% accuracy in predicting child survival risk for under-five children in Ethiopia.

With KILIMA TULIP AI, we have achieved an even more remarkable performance of 95% accuracy in predicting child survival outcomes across five African countries: Ethiopia, Ghana, Uganda, South Africa, and Zimbabwe.

Our team at kofiyatech is thrilled to present this groundbreaking technology. Join us in our mission to make a positive impact on the well-being of under-five children.

Welcome to DEEP MINTILO AI, a project dedicated to predicting under-five (U5) child survival risk in Ethiopia using Deep Learning AI techniques. This project is an extension of our MINTILO AI initiative and aims to leverage the power of neural networks to improve child survival rates.

With DEEP MINTILO AI, we have achieved remarkable performance gains, surpassing 90% accuracy in predicting child survival outcomes.

Our team at kofiyatech is excited to offer you a demo of this cutting-edge technology. Reach out to us to learn more about the implementation and the potential impact on child well-being.

An open source project dedicated to utilizing Python and machine learning techniques to provide insights for policy makers in eradicating child mortality. By analyzing data from DHS surveys, MINTILO AI identifies risk factors associated with child survival.

This project relies on the DHS AI WebApp platform as its data source. To access and contribute to MINTILO AI, visit the GitHub repository: GitHub - MINTILO AI.

For more information and to contribute, please feel free to reach out to us.

Contribute

An open source project that utilizes classical survival analysis methods in R, including Kaplan-Meier and Cox regression techniques. Its primary objective is to enable researchers and graduate students to collaborate and identify risk factors related to child survival in children under-five years old.

This project relies on the DHS AI WebApp platform as its input source. You can access the project on GitHub: GitHub - WATOTO SURVIVAL.

For more information and to contribute, please feel free to contact us.

Contribute

The DHS AI WebApp is a user-friendly, SQLite-based database repository specifically designed for DHS survey data. It serves as a powerful resource for Data Science projects, providing researchers, data analysts, and graduate students with easy-to-use querying capabilities tailored to their specific research subjects.

Our project initiative aims to promote the use of data science and machine learning techniques with DHS survey data. It was inspired by a study published by Bitew, et al (2020) that highlighted the untapped potential of utilizing these methods.

We are committed to supporting researchers interested in machine learning and data science. Through our project, we provide valuable resources, guidance, and assistance to help researchers explore the vast opportunities offered by DHS survey data.