Giter Site home page Giter Site logo

ustcsteve / challenge-wildfires Goto Github PK

View Code? Open in Web Editor NEW

This project forked from h2oai/challenge-wildfires

0.0 0.0 0.0 29.43 MB

Starter kit for H2O.ai competition Challenge Wildfires.

License: Apache License 2.0

Makefile 0.01% Python 0.11% Jupyter Notebook 79.88% HTML 20.00%

challenge-wildfires's Introduction

Wildfire Challenge Starter Kit

Starter kit for H2O.ai Wildfire Challenge.

Wave App Development

Requirements

  1. Install Python 3.6+, and pip3

  2. Install H2O Wave SDK - follow instructions for your platform at https://wave.h2o.ai/docs/installation

  3. Install H2O AI Cloud CLI (v0.9.1-rc1) to debug, bundle and execute your H2O Wave app: https://h2oai-cloud-release.s3.amazonaws.com/releases/ai/h2o/h2o-cloud/v0.9.1-rc1/index.html

  4. Install tar (or an alternative, to create a compressed archive file for submission)

1. Run the H2O Wave Server

Go to your H2O Wave SDK directory and run the Wave server:

cd $HOME/wave && ./waved

INFO: On Windows, run waved.exe to start the server.

2. Clone the H2O.ai Wildfire Challenge GitHub repo

git clone https://github.com/h2oai/challenge-wildfires.git

3. Search for Datasets

4. Setup your Python environment

cd wave-app
make setup

or simply

cd wave-app
python3 -m venv venv
./venv/bin/python -m pip install --upgrade pip
./venv/bin/python -m pip install -r requirements.txt

5. Run your Wave app

This step is using installed h2o-wave package to run the application.

cd wave-app
make run

or

cd wave-app
./venv/bin/wave run src.app

Point your web browser to http://localhost:10101/ to access the app.

6. Bundle your Wave app to run on H2O AI Cloud

This step prepares the Wave app for submission.

cd wave-app
make bundle

or

cd wave-app
h2o bundle

Debug or Publish your Wave app on H2O AI Cloud

H2O.ai Wildfire & Bushfire Challenge enables participants to deploy, debug, and upload their H2O Wave apps on a managed H2O AI Cloud instance. H2O AI Cloud's Appstore operationalizes AI/ML applications built with H2O Wave. https://challenge.h2o.ai/ is a H2O AI cloud instance managed by H2O.ai and is available for use for Callenge Wildfire.

Developer Guide is available here: https://h2oai.github.io/h2o-ai-cloud/docs/userguide/developer-guide

Wildfire Challenge allows two usage modes for the participants on the cloud:

  1. publish-cloud-private: immediately run your current app source in the platform. This command will automatically package your current directory into a .wave bundle, import it into the platform, and run it privately (only visible to you). In the output you will be able to find a URL where you can reach the instance, or visit the "My Instances" in the UI.

  2. publish-cloud-public: publish an app to the platform. This command will automatically package your current directory into a .wave bundle and import it into the platform. The app will be visible and available to run for all participants. Participants will be run an instance on H2OAIC Appstore.

To get started, please follow the steps below:

1. Configure your h2o cli to run your Wave apps on H2O AI Cloud

Note: For ease of use, config setup steps have been automated for you. When you get to the token portion, you will need to visit https://challenge.h2o.ai/auth/get-token in order to obtain your token. After entering the token here, you are all set.

WARNING: please ensure that the newly generated config file, h2o_wildfire_cli_config.toml, is confidential.

cd wave-app
make generate-cloud-config

2. Deploy wave app and view privately

cd wave-app
make publish-cloud-private
git update-index --skip-worktree h2o_wildfire_cli_config.toml

3. Upload wave app and make it visible to other users

WARNING: this mode will allow all participants to view and launch an instance of your H2O Wave app on the Appstore.

cd wave-app
make publish-cloud-public

Submission

This operation is going to create a new archive file in the root directory of the repo called submission.tar. The archive follows challenge rules and contains the wave app, Python notebook, and this README.

cd wave-app
make submission

Starter kit H2O Wave app in action

starter_kit_intro.mp4

Community

There are several communities to discuss topics related to AI/ML or application development:

challenge-wildfires's People

Contributors

azim-b avatar gaborfodor avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.