Jupyter Graffiti

Create interactive screencasts inside Jupyter Notebook that anybody can play back.

Ever wanted to offer someone a hands-on "live" demo in Jupyter Notebook? Using Graffiti you can add floating tips along with optional recorded movies anywhere in your Notebooks. Demonstrate whatever you want, highlight what's important-- all narrated by you! Since the movie plays back in and on the Notebook, the viewer can pause any time, dive into your code and try things out exactly as you had them when you were recording, and then resume play.

Is this project up to date?

Yes, Graffiti is maintained and kept up to date by its author. Please file issues as you see them or submit PRs. It's most recently been updated for security and to eliminate lodash dependencies, on January 2, 2023.

** Update 1/11/2024: Graffiti has been upgraded to run in Jupyter Notebooks V7, but in "classic" mode. You will have to run your notebooks in Classic mode to use Graffiti until it gets completely rewritten for JupyterLab. I am not intending to make that update unless I hear back from the community that it's desired. **

Try Graffiti Out! Try These Live Demos:

• General Demo
• Udacity C++ Nanodegree Example: "For Loops"
• Udacity C++ Nanodegree Example: "Pointers"
• Udacity Data Structures and Algorithms Nanodegree Example: "Implementing a Stack using an Array"

Please wait about 30 seconds for the demonstration to spin up at mybinder.org. (Thanks to the folks at MyBinder for this awesome service).

Or, Watch Regular Recorded Video Demos:

• Gentle Introduction To Graffiti (Start here)
• How to make Graffiti movies.
• How to make a Graffiti tooltip in code
• Using Graffiti extras like in-line terminals and auto-saving code cells.
• Adding a recording to a Show/Hide solution button.
• How Graffiti in-line shells are recorded into movies.
• Accessing and using the Graffiti API

What exactly can you record in the Graffiti?

• Recorded audio (e.g. voice narration), captured with your laptop's microphone while making your recording
• Mouse movement and scrolling in the Notebook
• Selecting and editing inside code cells
• The output of any code cell executions
• Inlined terminals (shells) whose activities you can also record.
• You can also draw and highlight over sections you think are important, or create handwritten notes.
• Support for the C++ kernel and the R kernel are included in addition to the Python kernel.

But, does this extension work in Jupyter Lab?

No, it only works in Jupyter Notebook classic. It would be quite complex to port to Lab as it has an entirely different internal API. However, if anybody in the community wants to see a port and collaborate, please reach out.

Learn More On Using Graffiti:

• How to make Graffiti movies
• How to make a Graffiti tooltip in code
• Accessing and using the Graffiti API
• Using Graffiti extras like in-line terminals and auto-saving code cells
• Adding a recording to a Show/Hide solution button
• How Graffiti in-line shells are recorded into movies

You can also visit the User Manual for more detailed instructions on how to use Graffiti.

Advantages of Graffiti Over Traditional Screencasts

• You can save any number of Graffitis in a Notebook.
• You don't need any special software or hardware (other than this library and Chrome/Firefox) to create and save Graffitis.
• Viewers can pause recorded playback any time, scrub forward and backward, and interact with the Notebook during playback at any point. No need to watch a whole recorded screencast first, and then switch context to a Notebook; students can explore right along with you in the same environment you recorded in. When you pause playback, you're still in a live Notebook, so you can play around.
• Jupyter Graffiti is easy to set up: either use the Python library or build the Docker image with the included Jupyter extension. (At Udacity, Jupyter Notebook Workspaces use the extension. See below how to install it). Or, you can skip installation entirely (see below).
• All data, including audio, is stored in compressed plain text in a directory separate from your Notebook files, for easy portability and storage in any version control system e.g. git/github.
• Unlike streamed video, you don't need a video server or hosted YouTube videos, and you can watch the videos even without an internet connection or over narrow bandwidth, because the files are very small.

Using Graffiti with ZERO installation

You can skip installation entirely if you want, by using the Binder demo link above. Just upload whatever Notebook you want to add Graffiti to the demo Jupyter Notebook server, activate Graffiti (see below), make some recordings, and then download the jupytergraffiti_data folder along with your Graffiti-ized Notebook from the binder Notebook server. To make this easier, we've installed nbzip into the Binder demo server. Just go to the server's tree, visit the jupytergraffiti_data folder and click the folder download link. For more details on how this works you can refer to nbzip's documentation.

You can then commit the jupytergraffiti_data folder and your Notebook to your own github repo and set up a link to it on Binder to share your Graffiti without requiring that the recipient have Graffiti installed.

Graffiti Software Installation-- Putting Graffiti onto your own System(s)

Uploading and downloading to/from Binder isn't optimal of course; it's probably better to get Graffiti going on your own computers.

There are four ways to install Jupyter Graffiti: using pip or conda, using a Python library, using a Docker image, or installing a plugin into your Jupyter Notebook server.

Installation Option #1: Use pip or conda (Easiest Option)

Just do:

pip install jupytergraffiti

or

conda install -c willkessler jupytergraffiti

This assumes you have pip or pip3, or conda as well as Jupyter Notebook, already installed.

PLEASE NOTE: Due to changes in Jupyter, the inline terminals will not work with any version of Jupyter less than 6.1.6. Please run: conda update --prefix ~/anaconda3 anaconda and conda upgrade jupyter to ensure that you have the latest version, which at the time of the last update to this README is v6.2.0.

Installation Option #2: Run Jupyter Notebook with a Docker Image Containing Graffiti (Slightly More Complex Option)

Make sure to install Docker on your system first (unless you've already installed it).

Then enter this command in a terminal on your computer:

./jupytergraffiti/build_and_run.sh

This will build and start up a Docker container running the Jupyter Server and the Jupyter Graffiti extension, with the container's home directory being mounted where your Jupyter Notebook(s) are located, and serving Notebooks over port 8888.

The advantage of using the Docker container is that Jupyter Graffiti is always loaded automatically, so you don't have to execute import jupytergraffiti in the Notebook just to play back Graffitis (but you will need to run it to access the Graffiti API).

using the Docker container also ensures you're running a recent version of Jupyter Notebook.

Take a look at the output of the Jupyter Server running in the container. It has the secret key you need to be able to surf to the Dockerized Jupyter server. The output will look something like this (but note that the Jupyter Server login token will change every time you run build_and_run.sh):

Copy/paste this URL into your browser when you connect for the first time,
    to login with a token:
        http://(b13ba2b482e9 or 127.0.0.1):8888/?token=e58a08f167881500e207ff9be05ad57ffe00e3457e54017c

What this is telling you is to surf to http://localhost:8888?token=e58a08f167881500e207ff9be05ad57ffe00e3457e54017c to access the Jupyter Server with the Graffiti extension installed and running.

The Docker container will serve content out of port 8888. If you already have something (e.g. another Jupyter server) running on this port, pass a different port to build_and_run.sh like so:

./jupytergraffiti/build_and_run.sh 8889

Note: if you specify a different port, the Jupyter Server output containing the secret key will still show port 8888, because internally it still uses port 8888; via Docker port mappings, we have remapped 8888 to the port you specify. In the example above, therefore, you would need to access the server at: http://localhost:8889?token=e58a08f167881500e207ff9be05ad57ffe00e3457e54017c.

Note: Inline terminals do not seem to work within the Docker container setup, probably due to permission levels.

Installation Option #3: Use the Python Library (Slightly More Involved Option, but does not add code to your system)

Note: Before using this method, you may need to Trust your Notebook. This is because Jupyter Graffiti is mostly written in Javascript, and by default, if the Notebook you're adding Graffitis to was not created by you, Jupyter Notebook will not "Trust" it and will not run externally loaded javascript code, for security reasons. To Trust a Notebook, click File...Trust Notebookbefore running the import command below.

1. git clone this repo in the same directory where you keep the Notebook(s) you want to add Graffiti to.
2. Add and run the following command in a cell in the Notebook you want to start adding Graffiti to:

import jupytergraffiti

If everything works, you will see a button labelled "Activate Graffiti" in your menu bar.

If you don't see this button appearing, use Kernel... Restart and Clear Output first, then try running import jupytergraffiti again.

Once you see this message, you can "Activate Graffiti" on a Notebook to begin creating Graffiti. The User Manual has many details on how to create Graffiti.

Special Note : if you are adding Graffitis to Notebooks that do not reside in the same folder where you cloned this repo, then you must :

1. Create a jupytergraffiti_data directory in the folder where you cloned this repo (mkdir jupytergraffiti_data).
2. Create symbolic links from the directory where you Notebook resides to both the jupytergraffiti folder in this repo, and to the jupytergraffiti_data folder alongside where you cloned this repo.

Installation Option #4: Install the Graffiti Extension in Your Own Jupyter Server (Most Complex Option)

This will permanently install the extension in your computer's installation of the Jupyter Server (although you can always disable it if you want to). This means the extension will always be available whenever you start up your Jupyter server. To install the extension:

cd jupytergraffiti
jupyter nbextension install graffiti_extension --symlink --user
jupyter nbextension enable graffiti_extension/main --user
cd ..

You may need to restart your Jupyter server to get the extension to load, although usually that's not required.

Disabling the Graffiti extension in your Jupyter Server

If you need to disable the Graffiti plugin for some reason, you can easily do it.

To disable the plugin:

cd jupytergraffiti
jupyter nbextension disable graffiti_extension/main --user
cd ..

Then restart your Jupyter server.

Using the Jupyter Graffiti Python API

When you import jupytergraffiti you get immediate access to functions you can use to control Jupyter Graffiti from Python. Some of these are utility functions, and others can be used to control recordings playback. To use them, simply run the Python functions in your Notebook's cells (note: the API only works with the Python kernels at this time).

Playing Back Graffiti Recordings

You can also play any Graffiti recording back using Python code. This could be valuable, for instance, after a student has failed several times to make some code work; you could watch for this situation in your testing code, and offer to play a hint recording. Or, if a student's code passes all tests you can start up a recording prompting them to go on to the next exercise.

Current Limitations of Jupyter Graffiti

• Jupyter Graffiti can record most activities in Notebooks, but it does not record interactions with Jupyter's UX, e.g. you will not see the Jupyter menus get pulled down even if you pulled down a Jupyter menu during a recording.
• If you rearrange cells after making a recording, scrolling will try to align the cursor and the page as best it can with the cells you were mousing over and scrolling to, even if they are in a different order than when you made the original recording. However, due to complexities involving cell sizing, this process may not always be perfect.
• Copying cells does not copy their Graffiti.
• Make a Copy ... of the current Notebook will not create a copy of the recordings; in fact, it will use the same recording ID and therefore supplant recordings on the original Notebook. You can use an API call to fix this issue, however.
• Given this is the first version of this software, there may well be bugs. Feel free to report issues on Github and/or propose PR's.

Future Plans

• In the next version of Jupyter Graffiti you will be able to automatically transcribe your spoken audio into subtitles that scroll along with the movie.

• Make a Copy ... of a Notebook should copy the recordings to a new Notebook recording ID.

CREDITS

Author/Maintainer:

Will Kessler

github: willkessler twitter: @atlas3650

Advisors:

• Andy Brown (feature design)
• Tugce Akin (engineering)
• Nathan Tate (engineering).