Lesson Open Access

naturalistic-data-analysis/naturalistic_data_analysis: Version 1.0

Luke Chang; Jeremy Manning; Christopher Baldassano; Alejandro de la Vega; Gordon Fleetwood; Linda Geerligs; James Haxby; Juha Lahnakoski; Carolyn Parkinson; Heather Shappell; Won Mok Shim; Tor Wager; Tal Yarkoni; Yaara Yeshurun; Emily Finn

Version 1.0 of the Naturalistic-Data.org educational course. Naturalistic-Data.org is an open access online educational resource that provides an introduction to analyzing naturalistic functional neuroimaging datasets using Python. Naturalistic-Data.org is built using Jupyter-Book and provides interactive tutorials for introducing advanced analytic techniques . This includes functional alignment, inter-subject correlations, inter-subject representational similarity analysis, inter-subject functional connectivity, event segmentation, natural language processing, hidden semi-markov models, automated annotation extraction, and visualizing high dimensional data. The tutorials focus on practical applications using open access data, short open access video lectures, and interactive Jupyter notebooks. All of the tutorials use open source packages from the python scientific computing community (e.g., numpy, pandas, scipy, matplotlib, scikit-learn, networkx, nibabel, nilearn, brainiak, hypertoos, timecorr, pliers, statesegmentation, and nltools). The course is designed to be useful for varying levels of experience, including individuals with minimal experience with programming, Python, and statistics.

Files (190.0 MB)
Name Size
naturalistic-data-analysis/naturalistic_data_analysis-1.0.zip
md5:cb61f6aa3ec1cb112d8b1e9af344fe20
190.0 MB Download
102
8
views
downloads
All versions This version
Views 102102
Downloads 88
Data volume 1.5 GB1.5 GB
Unique views 7676
Unique downloads 88

Share

Cite as