Examples for Jupyter Notebooks
A space to collect and share Jupyter notebooks.
All notebooks should ideally work without any extra files, use only standard Python libraries (pandas, scikit-learn, etc.), and gather their data from the web. An introduction into Jupyter Notebooks and Python is also available online.
Contributing to this Repository
To contribute a notebook, please
- fork this project,
- add your notebook and
- create a merge request.
If you did everything correctly, you should see your changes in the list of merge requests. After your request has been approved, your notebook will be available in this repository. Thank you for contributing!
List of Notebooks
So far, notebooks are listed by difficulty, indicated by stars (☆ = simple, ☆☆ = advanced, ☆☆☆ = sophisticated), then alphabetically:
- Classification
- basic machine learning classification example (☆)
- Exponential smoothing
- using Jupyter’s interactive widget to explore exponential smoothing (☆)
- Hamming
- a graph visualising a strange type of word similarity (☆)
- Jupyter-Demo
- demo of some Jupyter features useful for creating learning material (☆)
- analysing Twitter data (raw JSON from Twitter’s API) (☆)
- Wikipedia language editions
- plotting the depth and number of articles of different Wikipedia language editions (☆)
- Regular expressions
- simple information extraction from Wikipedia articles (☆)
- Amazon reviews
- crawling web sites with Scrapy, processing JSON data, basic statistics and visualisation (☆☆)
- Art
- Creating computer-generated art by translation, scaling and composition of functions (☆☆)
- Community detection
- applying community detection algorithms to network graphs (☆☆)
- Crawling a blog
- crawling web sites, basic text mining, basic statistics and visualisation (☆☆)
- DraCor
- retrieving data from a REST API, text transformation and classification (☆☆)
- FCA
- analysing characters in plays using Formal Concept Analysis (☆☆)
- Machine Learning
- recipes for common machine learning tasks (☆☆)
- Mondrian
- turtle graphics, recursion, art (☆☆)
- Statistics top 50 faculty
- exploratory statistical analysis of the dataset of 2200 faculty in 50 top US computer science graduate programs (☆☆)
- Distances
- comprehensive interactive simulation of recovering information from noisy data (namely, point positions given their noisy distance matrix) (☆☆☆)
- Das Haus vom Nikolaus
- graph traversal and drawing (☆☆☆)
- Scrape review blog
- Here, we use the python package scrapy to download all reviews of a literature blog (☆☆☆)
Module “Datenanalyse & -auswertung”
Exemplary (and excellent) term papers from students of our module:
- AirBnB Use in Berlin
- Untersuchung der AirBnB Nutzung in Berlin by Juliane Köhler
- Weinbewertungen Vivino
- Untersuchung von Weinbewertungen des Online-Weinmarktplatzes Vivino by Heike Wilhelm