Coder Social home page Coder Social logo

afg6k7h4fhy2 / forecasting-tornadoes Goto Github PK

View Code? Open in Web Editor NEW
2.0 1.0 0.0 445 KB

This repository contains up to several models aimed at forecasting US tornado counts by state, season, and month.

License: MIT License

Makefile 5.26% TeX 0.92% Python 93.82%

forecasting-tornadoes's Introduction

Forecasting-Tornadoes

This repository covers up to several models for forecasting tornadoes. The authors of these models are not experts in climate modelling or tornado dynamics.

Forecasting repositories, such as this one (usually created by @AFg6K7h4fhy2), are typically positioned as small experimental test units for tackling Metaculus questions with statistical modelling.

If you are a collaborator, make sure, upon cloning this repository

  • git clone https://github.com/AFg6K7h4fhy2/Forecasting-Tornadoes.git

that you have poetry installed.

  • pip3 install poetry

Once this is done, type poetry shell. To close the environment, type exit.

Repository Structure

tree | grep -Ev "\.png|\.pyc|\.txt|\.csv"

.
├── CONTRIBUTING.md
├── LICENSE
├── README.md
├── _typos.toml
├── assets
│   └── figures
├── data
│   ├── clean
│   └── raw
├── model_E414_01
│   ├── __init__.py
│   ├── docs
│   │   ├── Makefile
│   │   ├── output
│   │   │   └── out.pdf
│   │   └── source
│   │       ├── metadata.yml
│   │       ├── model.md
│   │       └── references.bib
│   ├── output
│   │   ├── April_2024
│   │   └── May_2024
│   ├── params.toml
│   └── src
│       ├── __init__.py
│       ├── __pycache__
│       ├── model.py
│       └── run.py
├── poetry.lock
├── pyproject.toml
└── utils
    ├── __init__.py
    ├── __pycache__
    ├── config.py
    ├── data.py
    ├── inf.py
    ├── save.py
    ├── transform.py
    └── vis.py

17 directories, 92 files

forecasting-tornadoes's People

Contributors

afg6k7h4fhy2 avatar dependabot[bot] avatar

Stargazers

Constantine Zavezeon avatar Purple Fern avatar

Watchers

 avatar

forecasting-tornadoes's Issues

Post Introductory Metaculus Comment on Question 22307

Goal

Write a Metaculus comment on question 22307 discussing the results of Model A (the first model).

Context

As of 2024-04-28, there are roughly 2 days remaining for predictors to make comments on question 22307. That there were many tornadoes recently across the US has pushed predictions close to the open upper bound on the question. Despite this, the author suspects predictors are likely still interested in learning about possible modelling techniques that can be employed here.

Tasks

  • Get stable output and code for Model A, including different combinations of the terms.
  • Draft a comment here to post on Metaculus.

Out Of Scope

  • Evaluating other sorts of models that can be used for tornado prediction.
  • Discussing the nature and dynamics of tornadoes.

Resources & Links

Code Review Of Model E414 01 On StackExchange

Goal

Receive external feedback on the process of loading data from toml file in Python, generally and as is represented in the code at present.

Context

There are likely best practices with respect to loading from toml, yaml, and json files; the coding community likely has a better sense of this than I do.

Tasks

  • Post a question on Code Review.
  • General a template for questions on Code Review.

Out Of Scope

  • A discussion on configuration files in general.

Resources & Links

Meta Considerations For Issues And Discussions

Goal

Add checklist of issues & discussions that should be created to facilitate tornado forecasting and the use of best practices in software development, statistics, and forecasting.

Context

See Goal.

Tasks

  • Mathematical Approaches For Forecasting Tornados (discussion)
  • Existing Work On Tornado Forecasting (discussion)
  • Best Practices In Repository's Software And Model Design (issue and discussion)
  • Model Diagrams Creation (issue)
  • Data Visualization Checklist (issue and discussion)
  • Samples Saving Scheme (issue and discussion)
  • Forecast Saving Scheme (issue and discussion)
  • Config Default Values (issue)
  • Model Naming And Lead Models (discussion)
  • Sensitivity Analysis (issue)
  • Model Documentation (issue)
  • Converting Forecasts To Metaculus Predictions (issue)
  • README Considerations (issue)

Out Of Scope

TBD.

Resources & Links

TBD.

Recommend Projects

  • React photo React

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

  • Vue.js photo Vue.js

    🖖 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. 📊📈🎉

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 ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.