☀️ Measuring the accuracy of BBC weather forecasts in Honolulu, USA

Overview

Accuracy of BBC Weather forecasts for Honolulu

This repository records the forecasts made by BBC Weather for the city of Honolulu, USA. Essentially, there's a GitHub Action that runs at each 30 minute mark and saves the latest forecasts. The data is stored in a separate branch called data. Therefore, the data is versioned. This allows going back into the past to see the forecasts that were made for any given hour in the (relative) future.

I made this after watching Git scraping, the five minute lightning talk by Simon Willison. It blew my mind! I agree with Simon that collecting and versioning API data via git is a powerful pattern. You could use this pattern to keep a ledger of any dynamic forecasting system, such as the predicted outcomes of football games. In these dynamical systems, the forecasts are updated when new information becomes available. Therefore, the forecasted values depend on the point in time when they were made. I think that it's super interesting to analyse how these forecasts evolve through time.

The build_database.py script iterates through all the commits in the data branch and consolidates the data into an SQLite database. You can run the script yourself by simply cloning this repository. Then, go into a terminal, navigate to the cloned repository, and install the necessary Python dependencies:

python -m venv .env
source .env/bin/activate
pip install -r requirements.txt

Then, run the consolidation script:

python build_database.py

This will create a bbc_weather.sqlite file. You can load the latter into your preferred database access tool — I have a personal preference for DataGrip — to analyse the data. At present, the database contains two tables:

forecasts

These are the predicted weather values made at one point in time for a future point in time.

issued_at at celsius feels_like_celsius wind_speed_kph
2021-03-10 09:00:00 2021-03-10 11:00:00 24 30 16
2021-03-10 09:00:00 2021-03-10 12:00:00 25 31 17
2021-03-10 09:00:00 2021-03-10 13:00:00 26 32 17
2021-03-10 09:00:00 2021-03-10 14:00:00 27 33 17
2021-03-10 09:00:00 2021-03-10 15:00:00 26 33 17

observations

These are the weather values that actually occurred — as opposed to those that were forecasted.

at celsius wind_speed_kph
2021-03-09 19:00:00 23 0
2021-03-09 20:00:00 22 8
2021-03-09 21:00:00 22 0
2021-03-09 22:00:00 21 9
2021-03-09 23:00:00 21 0

Check out measure_accuracy.sql for an example of how to evaluate the correctness of the forecasts.

Owner
Max Halford
Data wizard @alan-eu. PhD in machine learning applied to query optimization. Kaggle competitions Master when it was cool. Online machine learning nut.
Max Halford
A repo for open resources & information for people to succeed in PhD in CS & career in AI / NLP

A repo for open resources & information for people to succeed in PhD in CS & career in AI / NLP

420 Dec 28, 2022
A tool helps build a talk preview image by combining the given background image and talk event description

talk-preview-img-builder A tool helps build a talk preview image by combining the given background image and talk event description Installation and U

PyCon Taiwan 4 Aug 20, 2022
Official code for Spoken ObjectNet: A Bias-Controlled Spoken Caption Dataset

Official code for our Interspeech 2021 - Spoken ObjectNet: A Bias-Controlled Spoken Caption Dataset [1]*. Visually-grounded spoken language datasets c

Ian Palmer 3 Jan 26, 2022
:house_with_garden: Fast & easy transfer learning for NLP. Harvesting language models for the industry. Focus on Question Answering.

(Framework for Adapting Representation Models) What is it? FARM makes Transfer Learning with BERT & Co simple, fast and enterprise-ready. It's built u

deepset 1.6k Dec 27, 2022
Pipeline for fast building text classification TF-IDF + LogReg baselines.

Text Classification Baseline Pipeline for fast building text classification TF-IDF + LogReg baselines. Usage Instead of writing custom code for specif

Dani El-Ayyass 57 Dec 07, 2022
Source code for CsiNet and CRNet using Fully Connected Layer-Shared feedback architecture.

FCS-applications Source code for CsiNet and CRNet using the Fully Connected Layer-Shared feedback architecture. Introduction This repository contains

Boyuan Zhang 4 Oct 07, 2022
Optimal Transport Tools (OTT), A toolbox for all things Wasserstein.

Optimal Transport Tools (OTT), A toolbox for all things Wasserstein. See full documentation for detailed info on the toolbox. The goal of OTT is to pr

OTT-JAX 255 Dec 26, 2022
Let Xiao Ai speakers control third-party devices

A stupid way to extend miot/xiaoai. Demo for Panasonic Bath Bully FV-RB20VL1 逆向 Panasonic Smart China,获得控制浴霸的请求信息(HTTP 请求),详见 apps/panasonic.py; 2. 通过

bin 14 Jul 07, 2022
Hostapd-mac-tod-acl - Setup a hostapd AP with MAC ToD ACL

A brief explanation This script provides a quick way to setup a Time-of-day (Tod

2 Feb 03, 2022
Data and code to support "Applied Natural Language Processing" (INFO 256, Fall 2021, UC Berkeley)

anlp21 Course materials for "Applied Natural Language Processing" (INFO 256, Fall 2021, UC Berkeley) Syllabus: http://people.ischool.berkeley.edu/~dba

David Bamman 48 Dec 06, 2022
Pipeline for training LSA models using Scikit-Learn.

Latent Semantic Analysis Pipeline for training LSA models using Scikit-Learn. Usage Instead of writing custom code for latent semantic analysis, you j

Dani El-Ayyass 23 Sep 05, 2022
texlive expressions for documents

tex2nix Generate Texlive environment containing all dependencies for your document rather than downloading gigabytes of texlive packages. Installation

Jörg Thalheim 70 Dec 26, 2022
☀️ Measuring the accuracy of BBC weather forecasts in Honolulu, USA

Accuracy of BBC Weather forecasts for Honolulu This repository records the forecasts made by BBC Weather for the city of Honolulu, USA. Essentially, t

Max Halford 12 Oct 15, 2022
nlp-tutorial is a tutorial for who is studying NLP(Natural Language Processing) using Pytorch

nlp-tutorial is a tutorial for who is studying NLP(Natural Language Processing) using Pytorch. Most of the models in NLP were implemented with less than 100 lines of code.(except comments or blank li

Tae-Hwan Jung 11.9k Jan 08, 2023
A workshop with several modules to help learn Feast, an open-source feature store

Workshop: Learning Feast This workshop aims to teach users about Feast, an open-source feature store. We explain concepts & best practices by example,

Feast 52 Jan 05, 2023
Code for EmBERT, a transformer model for embodied, language-guided visual task completion.

Code for EmBERT, a transformer model for embodied, language-guided visual task completion.

41 Jan 03, 2023
SimpleChinese2 集成了许多基本的中文NLP功能,使基于 Python 的中文文字处理和信息提取变得简单方便。

SimpleChinese2 SimpleChinese2 集成了许多基本的中文NLP功能,使基于 Python 的中文文字处理和信息提取变得简单方便。 声明 本项目是为方便个人工作所创建的,仅有部分代码原创。

Ming 30 Dec 02, 2022
A paper list of pre-trained language models (PLMs).

Large-scale pre-trained language models (PLMs) such as BERT and GPT have achieved great success and become a milestone in NLP.

RUCAIBox 124 Jan 02, 2023
Open solution to the Toxic Comment Classification Challenge

Starter code: Kaggle Toxic Comment Classification Challenge More competitions 🎇 Check collection of public projects 🎁 , where you can find multiple

minerva.ml 153 Jun 22, 2022