Update README after the first tinkering club

title: "Analyse Open Data"

---

Imagine a group of experts brainstorming with AI on your own dataset.

Bring your curiosity to a group of data enthusiasts

# Upcoming meetings

Universität Hohenheim, Wollgrasweg 43, Seminarraum S 12

https://aidaho-tinkering-club.uni-hohenheim.de/

- 18.11.2026 14:15 Computer Raum 2

- 09.12.2026 14:15 Computer Raum 2

- 20.01.2027 14:15 Computer Raum 2

# Audience

This workshop is specifically welcoming both:

- September 17, 2026 12:15-13:45 S 12

- September 24, 2026 12:15-13:45 S 12

- October 1, 2026 12:15-13:45 S 12

- **curious researchers** who have no knowledge whatsoever of programming with AI.

  Their very important role will be to ask domain specific questions from the

  data.

- October 15, 2026 12:15-13:45 S 12

- October 22, 2026 12:15-13:45 S 12

- **programmers and data scientists** at different level of expertise from

  newbee to self hosted home lab geeks. Their role is to specify prompts,

  context, data structures and tools at the service of the research question.

We encourage interactions between curious researchers and expert data analysts

so that we all learn from each other through osmosis. 

# Introduction

- The 90 minutes workshop chooses and analyses one dataset in 4 phases:

    1. **Choice Phase** 5 minutes. Round of introduction 1 minute per project (with

       timer). Group decision on the most mature or desirable project among the

    1. **Choice Phase** Round of introduction 3 minutes per project (with

       timer). The research question should be in the context of one or two

       papers. It is essential that these papers are based on one or more open

       datasets. Group decision on the most desirable project among the

       submitted ones.

    2. **Specification Phase** 15 minutes. On a drawing board or sheet of paper, we

       specify what we want to achieve during the session.

    2. **Specification Phase** 15 minutes. On a **drawing board**, we specify

       what software the agents should write to help us analyse the research

       question.

    3. **Implementation Phase** 1 hour. Implementation with at least one, preferably two

       or more laptops which load the dataset, tools, and generate software with a

       coding agent. We push the code to this git repository under a new sub directory

       corresponding to the day of the event.

    3. **Implementation Phase** 1 hour. Implementation with at least one,

       preferably two or more laptops which load the dataset, tools, and

       generate software with a coding agent. We push the code to this git

       repository under a new sub directory corresponding to the day of the

       event.

    4. **Wrap-up Phase** 10 minutes. What failed, what went well, what can we improve

       next time.

    4. **Wrap-up Phase** 1 minute per participant. What failed, what went well,

       what did you learn, what can we improve next time.

- Throughout the specification and implementation phase, we can discuss about

  visualizations such as histogram, scatter plot, line chart, area chart, bar chart,

  maps, trees, networks and other graphic representations. We can elaborate a data

  processing pipeline with data structures (such as multidimensional arrays, vectors and

  tensors), input/output, file storage formats, databases, git version control and issue

  management, integration tests, CI, security aspects, workflow engines to run models in

  a dependency graph and about semantics how we name variables and functions.

- Throughout this hands on workshop we could experience some of the following:

- The groups goals could be for example:

    - visualizying the dataset of the day with histograms, scatter plots, line

      charts, area charts, bar charts, maps, trees, networks and other graphic

      representations

    - Playing with data visualisations on the dataset of the day. Spawning parallel coding

      agents with personas from different disciplines to enhance the creative process.

    - thinking about semantics i.e. how we name variables and functions

    - Translating new research questions into [back of the envelope

      calculations](https://en.wikipedia.org/wiki/Back-of-the-envelope_calculation).

      From these questions, we can brainstorm about the implication for model

      modification or model linking.

    - building a data processing pipelines with data structures (such as

      multidimensional arrays, vectors and tensors), input/output, file storage

      formats, databases, git version control and issue management, integration

      tests, CI, security aspects, workflow engines to run models in a

      dependency graph.

    - Performing literature research with LLMs that ground their answers in existing

      publications such as Perplexity. To use context engineering (uploading relevant

      papers) and prompting techniques to avoid sycophancy (such as grill-me, expert

      panel, storm review, hostile review).

    - use context engineering (uploading relevant papers) and prompting

      techniques to avoid sycophancy (such as grill-me, expert panel, storm

      review, hostile review). 

# Participate in the hands on training camp

To participate preferably come with an open dataset already shared on Zenodo or Figshare

or a similar open platform. If you cannot share your data, then find a similar dataset

from the literature on which we can work on together so that the learning can be

transferable to your own data later on.

To facilitate the specification phase, preferably come with:

a. a research question

b. a couple of scientific papers that provide context to your research

questions. 

c. one or more open datasets. 

- Submit your sample dataset in a new issue also called a work item at:

- Submit your research question with links to paper references and open

  datasets in a new issue also called a work item at:

    https://aidaho-edu.uni-hohenheim.de/gitlab/modellierung/analyse_open_data/-/work_items

    - Make sure your data file is smaller than 10Mb. If the sample data is larger than

      10Mb, please post it in a shared repository that can be accessed online, either

      publicly or through the university network, for example in an idaho repository.

      Then share that link in the issue.

    - Optionally, you can also add modelling code (in the programming language of your

      choice)

# Contribution to this repository

    - If you generate code during the meeting's implementation session you are very

If you generate code during the meeting's implementation session you are very

welcomed to make a merge request to place your generated code directly in the

`events/<current date>` directory.

If the programming language is proprietary and requires a licence, please come with your

own laptop or server access so that you can run the model in it's licensed environment.

**At the beginning of each meeting we will vote on which project will be analyzed during

that meeting.**

# See also

- Research data management at the University of Hohenheim

  https://kim.uni-hohenheim.de/en/research-data-management

**At the beginning of each meeting we will vote on which project will be analyzed during

that meeting.**