Climate Health Analytics Platform (CHAP)

CHAP is a platform for forecasting and for assessing forecasts of climate-sensitive health outcomes. In the early phase, the focus is on vector-borne diseases like malaria and dengue.

The platform can perform data parsing, data integration, forecasting based on any of multiple supported models, automatic brokering of compatible models for a given prediction context and robust forecast assessment and method comparison.

This documentation contains technical information about installing and using CHAP. For more general information about the project, we refer to the CHAP project wiki. The documentation here is divided into sections referring to different use-cases:

---

Full installation and integration with DHIS2

For users who want to fully install CHAP locally or on a server, e.g. to integrate with DHIS2, we recommend setting up CHAP with docker compose and using the Prediction app.

---

Integrating external or custom models with CHAP

For users who want to develop custom forecasting models and run or benchmark these through CHAP, or to simply evaluate external models on small example datasets, we recommend installing the chap-core Python package and folowing the guides on integrating external models and developing custom models.

---

Using CHAP as a library

For users who want to use CHAP as a library, we refer to the tutorials and API documentation (see the menu).

---

All pages

The following is an overview of all pages in the documentation:

Installation and getting started

• Installation and getting started
  • Requirements
  • Installation of chap-core
  • Local or server setup with docker
  • Setting up CHAP inside an LXD container
  • Development setup
• Docker Compose (CHAP Core)
  • 1. Install Docker and Docker Compose (if not installed)
  • 2. Clone CHAP Core GitHub-Repository
  • 3. Add Credentials for Google Earth Engine
  • 4. Start CHAP Core
  • 5. Stop CHAP Core

Using the Predictions App with CHAP (and integration with DHIS2)

• Prediction App
  • Requirements:
  • 1. Ways of interacting with CHAP Core
  • 2. Download Prediction App
  • 3. Starting REST-API and edit URL
  • 4 Selecting prediction data
• Solution 1: Use JSON-file from Prediction App with CHAP Core CLI
  • Get started with CHAP Cli
  • Install CHAP Core CLI
  • Credentials for Google Earth Engine
  • Convert the JSON data into a CHAP-DataSet
  • Evaluate models on the dataset
  • Predict using the best model
• Solution 2: Status for predictions and prediction import
• CHAP Core status page
• Import prediction page
  • Add data elements
  • Import prediction
  • Visualize
• Running on JSON data downloaded from the Prediction App
  • Install CHAP Core
  • Credentials for Google Earth Engine
  • Convert the JSON data into a CHAP-DataSet
  • Evaluate models on the dataset
  • Predict using the best model

Integrating external or custom models with CHAP

• Developing custom models with CHAP
  • Developing custom models in Python
• Integrating external models
  • Running an external model on the command line
  • Running an external model in Python

Using CHAP as a library

• Wrapping GluonTS models
• API documentation
  • Data Fetching