pyjamalib 0.6.8

A library for analyze joint angles from IMU data

PyJama - Python for Joint Angle Measurement and Acquisition

---

PyJama is open access project that was developed during my master's work at Edmond and Lily Safra International Institute of Neuroscience of Santos Dumont Insitute. PyJama is a user friendly python library for analyzing human kinematics data. Aimed at analyzing data from IMU's, MIMU's, data from optical devices and in the future tracking data from deeplearning models. The PyJama library was designed based on the JAMA device.

Contents

---

• Installation
• Examples
• Contributing
• Development Team
• Publications
• Credits

Installation

---

The latest stable release is available on PyPI, and you can install it by saying

pip install pyjamalib

Anaconda users can install using conda-forge:

conda install -c conda-forge pyjamalib

To build PyJama from source, say python setup.py build. Then, to install PyJama, say python setup.py install. If all went well, you should be able to execute the demo scripts under examples (OS X users should follow the installation guide given below).

Alternatively, you can download or clone the repository and use pip to handle dependencies:

unzip pyjamalib.zip
pip install -e pyjamalib

or

git clone https://github.com/tuliofalmeida/pyjama
pip install -e pyjamalib

By calling pip list you should see pyjamalib now as an installed package:

pyjamalib (0.x.x, /path/to/pyjamalib)

Examples

---

• Example of using the library using data extracted using JAMA.
• Example of using the library using data extracted using Vicon and Xsens.

Contributing

---

For minor fixes of code and documentation, please go ahead and submit a pull request. A gentle introduction to the process can be found here.

Check out the list of issues that are easy to fix. Working on them is a great way to move the project forward.

Larger changes (rewriting parts of existing code from scratch, adding new functions to the core, adding new libraries) should generally be discussed by opening an issue first. PRs with such changes require testing and approval.

Feature branches with lots of small commits (especially titled "oops", "fix typo", "forgot to add file", etc.) should be squashed before opening a pull request. At the same time, please refrain from putting multiple unrelated changes into a single pull request.

Development Team:

---

• Tulio Almeida - GitHub - Google Scholar
• Abner Cardoso - GitHub - Google Scholar
• André Dantas - GitHub - Google Scholar

Publications

---

The publications related to this project are still in the process of being published. If you publish any paper using JAMA please contact us to update here!

Credits

---

• Daniele Comotti GitHub used as a basis for filters
• Sebastian Madgwick Reference for the manipulations of quaternions
• Center for Vision, Speech & Signal Processing - University of Surrey. For making available the Total Capture dataset used to develop the library example. Reference paper: Trumble et. al., 2017