Light

clementsicard / airquality-data-science-project Goto Github PK

Using data we measured using sensors linked to a Raspberry Pi, we derived an LSTM model to predict air quality in Zurich and compared its performance with other more basic models

License: MIT License

Python 0.04% Jupyter Notebook 99.96%

data-science

airquality-data-science-project's Introduction

Air Quality Forecast Data Challenge

airquality-data-science-project's People

Contributors

Stargazers

Watchers

airquality-data-science-project's Issues

Time series analysis to understand the trends (peak hours/non-peak hours, weekdays/weekends etc.) and the relationship between different variables and PM2.5. (20%)

Implémenter DTW entre les différentes time-series du dataset : https://github.com/ClementSicard/ConstrainedDTW-Python
Transfer entropy
Calculer la corrélation entre les différentes variables

Faire une présentation + detailed description

Mettre des plots (toutes les time series ensemble, chacune individuellement, corrélation entre elles avec le graphique comme dans le cours (le correlogram)
Expliquer le soucis avec la Raspberry
Justifier que l'on a drop les colonnes avec 80% de NaN
Être critique quant à notre analyse
Ajouter les formules mathématiques des concepts qu'on utilise

Setting up an IoT device to monitor air quality (10%)

Documenter le setup de la Raspberry, fournir le script
Préciser les soucis qui nous sont arrivés

Performing PM2.5 forecast and compare your model’s performance with other time-series forecasting models. (35%)

Implémenter LSTM
https://machinelearningmastery.com/time-series-forecasting-methods-in-python-cheat-sheet/

Analysing data for missing values and outliers and creating a model for outlier detection and gap filling. (35%)

DTW entre les différentes time-series pour voir les similitudes
DBScan pour les outliers ?
https://towardsdatascience.com/anomaly-detection-in-time-series-sensor-data-86fd52e62538
Modifier les plots pour y afficher les outliers (ou les points qui semblent en être)
Utiliser différentes techniques de data imputation et sélectionner celle avec la plus petite erreur

Recommend Projects

React

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

🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
Typescript

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

An Open Source Machine Learning Framework for Everyone
Django

The Web framework for perfectionists with deadlines.
Laravel

A PHP framework for web artisans
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.
Visualization

Some thing interesting about visualization, use data art
Game

Some thing interesting about game, make everyone happy.

Recommend Org

Facebook

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

Open source projects and samples from Microsoft.
Google

Google ❤️ Open Source for everyone.
Alibaba

Alibaba Open Source for everyone
D3

Data-Driven Documents codes.
Tencent

China tencent open source team.