Zoekresultaten voor “Jupyter Notebooks”

Zoekresultaten (37)

HBO/WO

MBO

8 april 2026

Legal Network Analysis

How can complex legal systems, filled with interconnected cases, statutes, and actors, be understood through data? Legal Network Analysis offers law students and researchers a practical guide to mapping and interpreting relationships in legal data using the tools of network science. Building on the foundations of graph theory, this open textbook shows how relationships between cases, statutes, or states can reveal underlying structures in law that traditional methods often overlook. Whether analysing citation networks, treaties among nations, or the diffusion of legal norms, readers learn to translate legal questions into visual and quantitative insights. Developed by the Law and Tech Lab at Maastricht University, this resource combines conceptual clarity with applied learning. Each chapter blends concise explanations with interactive Jupyter notebooks, allowing readers to reproduce, modify, and experiment with examples in real time. Appendices include step-by-step guidance for data preparation, visualisation, and software setup; making the book equally accessible for newcomers and advanced students. Designed to support the Network Analysis course at Maastricht University, this textbook is also a valuable standalone introduction for anyone exploring the data-driven dimensions of law and policy.

Open (Access) Tekst Boek

Gustavo Arosemena, Gijs van Dijck, Roland Moerland

2 september 2025

Intro to Open Science

Created for the GSLS Master introduction Days 2025, Utrecht University. This lecture will introduce you to the principles and practices of Open Science, a global movement aimed at making scientific research more accessible, transparent, and collaborative. You will learn why open science matters for accelerating discoveries, improving research quality, and enhancing reproducibility. Key topics include open access publishing, open and FAIR data, preprints, open peer review, and sharing research tools and methods. The session will also cover practical tips on how you can integrate open science practices into your own research from the start of your graduate journey. By embracing open science, you contribute to a more inclusive and impactful scientific community.

Presentatie

Annetrude de Mooij-van Malsen

2 juli 2025

Intro to python programming

Learning Outcomes for Python Programming Modules 1. Develop and Document Python Code in Jupyter Notebooks Learners will create, document, and execute Python code using Jupyter Notebooks, effectively utilizing Markdown for readable and well-structured analysis. 2. Understand and Apply Python Data Types and Operations Learners will identify and manipulate core Python data types, perform data operations, and utilize comprehensions for efficient data processing. 3. Implement Program Logic and Functions Learners will control program flow using conditionals and loops, encapsulate logic within functions, and handle errors using Python’s exception mechanism. 4. Read, Write, and Process Data Files Learners will read from and write to files, apply regular expressions for text processing, and leverage core library functions for common data tasks. 5. Apply Object-Oriented Programming and Prepare for Data Analysis Learners will design and use classes, including data classes, and set up a Python environment with (Ana)conda, preparing to work with data analysis libraries such as pandas. Consists of 18 lessons (5EC).

Website

Michiel Noback

24 mei 2024

Workshop material Power of Python for GIS

This workshop introduces a set of tools for geospatial data handling and vizualization using Python. The workshop targets beginning python programmers or people with no Python experience that want to learn about all the possibilities of Python. The workshop will mostly be a demonstration of the power of Python for various tasks such as accessing and handling satellite data, processing raster/vector data and visualization. You will also be provide with python code to perform the same steps on your own laptop. The workshop is given by the Geo Data team from faculty of Geosciences and UU Research Engineering, both from Utrecht University. The material contains a Github repository with workflows, playbooks, data and notebooks, a Zenodo publication with presentation slides and sample data and a Github repository with a template for Jupyter workshops

Website

Garrett Speed, Aristotelis Kandylas, Jelle Treep

1 september 2023

Practical: Presenting statistical data

Understand and demonstrate the data representation for AI and ML modelling. Apply a range of plotting techniques to visualise data. Be able to check for fairness, handle outliers and missing data.

Document

HCAIM Consortium

23 augustus 2023

Practical: Platforms

To be able to use jupyter notebooks To be able to use basics of Python (variables, lists, strings, tuple) To be able to use basics of pandas (data loading from csv, data lookup)

Website

HCAIM Consortium

23 augustus 2023

Practical: ML-Ops Lifecycle

Understanding MLOPs end-to-end Understanding Data Ingestion Getting familiar with Algorithm Development Getting familiar with Model Development and Deployment Understanding Continuous Monitoring

Website

HCAIM Consortium

23 augustus 2023

Tutorial: Regularization

Examine Weight initializers Investigate bias Apply dropout and noise Impliment callbacks Undertsand and implement a gridsearch Apply non traditional overfitting techniques

Website

HCAIM Consortium

23 augustus 2023

Tutorial: Model Evaluation

Learners understand the concept of expected predictive performance and generalization Learners understand the concept of model complexity and its relationship with generalization performance Learners are familiar with bias and variance their relationship with underfitting and overfitting Learners have a firm grasp on evaluating binary classification models with the most widely applied metrics

Website

HCAIM Consortium

23 augustus 2023

Tutorial: CNNs and Transformers for images

Implementing and training a CNN and a Transformer for a computer vision problem from scratch Comparing the performance of the two models

Website

HCAIM Consortium