Data Dojo Würzburg 22
DataDojo@Lunch - live
May 2023
- When: Wednesday, May 31st, 2023 at 11:00am until 12:30pm (90 minutes)
- Where: CCTB or online (CCTB Seminar Zoom Link)
- Info: DataDojo Website, Repo
Dataset
German Electricity Data :electric_plug:
- Data Source: SMARD Web Portal
- Task: forecasting (using the past to predict the future)
- Language: julia
First steps:
- load the data
- split the data into train/val/test sets
- plot the time series (at different temporal resolution)
- calculate the mean production per month
- is there a seasonal pattern (what kinds of seasonalities)
- make a prediction for the validation set
- evaluate the quality of the prediction
Retro on the machine learning series
In the first dojo of the series, we filtered the full set to 3 species with reasonable overlap (Fagus sylvatica, Pinus pinaster, Quercus ilex). Now we want to try different Machine Learning methods to classify tree species from traits.
In the second dojo we created our first models. A very simple “Majority Vote” model and some K-Nearest-Neighbor (KNN) models with scikit-learn.
In the third dojo we explored the effect of scaling on the performance of the KNN models.
In the fourth dojo we explored Decision Trees as models for classification
In the fifth dojo we used Support Vector Machines as models for classification
In the sixth dojo we used ensemble models, including Ada boosting and random forests.
In the seventh dojo we used imputation methods to also make predictions for cases with missing data.
In the eighth dojo we trained some neural networks.
Collaborative Tools and Workflow
For Notebooks (R, python, julia, js, …) with real time collaboration CoCalc seems to be the best option right now. It worked great the last couple of times so we’ll stick to it for now. You need to register an account there (it is free).
Future Suggestions
Add your suggestions to the list and :+1: to the end of a line you are interested in
Data Sets
- Würzburg Baumkataster, Würzburger Klimabäume
- Bee Varroa Image Classification :bee:
- German Electricity Data :electric_plug:
- Mattermost Chat History - e.g. analyze the messages and reactions from the lunch channel
- Wordbank - data of children learning to talk
- All Birds :bird:
- Results of the Bundestagswahl 2021
- Weather data throughout Germany over time (incl. temperature, precipitation, …): https://www.dwd.de/DE/leistungen/cdc_portal/cdc_portal.html
- German Mikrozensus
- Kaggle Titanic or Tabular Playground or Meta Kaggle
- World Trade Data (Open Trade Statistics)
- Open Citation Data
- Top 100 charts + Audio Features
- Emoji Usage :hugging_face::heart::laughing:
- Observable Curated Datasets
- Abgeordnetenwatch - Data on German elected officials in EU-Parlament, Bundes- and Landtag (Election History, Ausschusszugehörigkeit, Side jobs, etc)
- Button Men Game Results
Tools/Languages
Skills
- interactive maps
- dashboards
- animations
Data Sources
all data types are welcome, including tables, images, videos, sounds, DNA, …
- OpenData Bayern
- TidyTuesday
- Our World in Data (R package: owidR), Sustainable Development Goals
- Open Data Initiatives (Würzburg, Germany, Statistisches Bundesamt, Europe, APIs)
- Data is plural
- Awesome Public Datasets
- Kaggle Datasets or Competitions, e.g. SLICED
- tsibbledata: Time Series Datasets
- R-text-data: Text Datasets, ready to use in R
- data.world
- Statista - the University of Würzburg has a campus license
- Open Legal Data
- Bundestag Data (e.g. poll results, deputies, wahl-o-mat, inspirational blog post)
- Deutsche Digitale Bibliothek (API, old newspapers from Germany)
- Earth Observation: Satellite Image Time Series
- Machine Learning Datasets
- Internation (Student) Assessment Data (TIMSS, PIRLS, PISA, …)
- (Medical) Imaging Datasets, MedMNIST
- Inspirational Notebooks on Observable
- Ski resort statistics :skier: