General Analysis

• Complex systems: https://bingweb.binghamton.edu/~sayama/textbook/.

• Network science: https://bingweb.binghamton.edu/~sayama/SSIE641/.

• Optimization: https://algorithmsbook.com/optimization/.

• Statistics: https://stats.oarc.ucla.edu/other/dae/

R

• Networks:

  • Primary: https://igraph.org/r/

  • Exponential random graph models: ergm (part of statnet)

    • https://github.com/eehh-stanford/SNA-workshop

    • This book is very helpful for understanding the dependency models that are closely associated with ERGM analysis in sociology and related disciplines.

  • Network data sets: http://networkdata.schochastics.net/, http://konect.cc/, http://www.ecologia.ib.usp.br/iwdb/resources.html, https://snap.stanford.edu/data/index.html, http://www.sociopatterns.org/, https://cran.r-project.org/package=igraphdata

• Principle component analysis tools (and more): http://www.sthda.com/english/

• Regression (in addition to base R; see below):

  • Hierarchical models, clustering: nlme, lme4, coxme, sandwich

  • Zero-inflated models: pscl

  • Regression support: lmtest, AER, car, arm

• Audio analysis: tuneR, seewave

• Data visualization: base R (see below).

• Parallel processing: See this blog post for an introduction.

• Documentation for the core R packages can be found here; this is the documentation for R’s equivalent of a standard library. These packages include the “base” packages (statistics, sample data sets, graphics, language utilities, but also parallel) and the “recommended” packages (e.g., boot, nlme, and survival). The core R packages are thorough: many tasks for which there are specialized packages are already well-supported in the base and recommended packages. The primary challenge with these core packages is that the documentation can be difficult, and there can be a greater expectation for general programming knowledge. For example, anonymous functions make the apply family of functions, including lapply and tapply, very useful, but take some adjustment on the part of the user. For some good pointers, see https://jozef.io/categories/rcase4base/; the reshape function can be particularly tough, but this is a good guide.

Julia

• Manual: https://docs.julialang.org/en/v1/. Includes discussion on improving performance, multithreading, class/type management, and more.

• Numerical integration and simulations: https://diffeq.sciml.ai/dev/index.html

• Networks: https://juliagraphs.org/Graphs.jl/dev/

• Statistics: https://juliastats.org/

• Data visualization: https://docs.juliaplots.org/stable/

Python

• Networks:

  • Primary: https://networkx.org/

  • Exponential random graph models: https://nemtropy.readthedocs.io/en/master/ (this package is new to me, but I have been looking for an alternate open source ERGM implementation and this may be it)

• Analysis support:

  • Numbers, arrays, calculations, vectorizing: https://numpy.org/

  • Distributions, more calculations, curve fitting, etc.: https://scipy.org/

  • Data manipulation: https://pandas.pydata.org/

• Statistics: https://www.statsmodels.org/stable/index.html

• Data visualization: https://matplotlib.org/

Video and Audio Annotation, Support

• Video annotation (for behavioral coding, etc.): https://archive.mpi.nl/tla/elan

• Audio editing, analysis, etc.: https://www.audacityteam.org/

• File conversion, etc.: https://ffmpeg.org/

Supporting Tasks

• LaTeX:

  • Introduction and reference: https://en.wikibooks.org/wiki/LaTeX

  • For help with symbols: http://detexify.kirelabs.org/classify.html

  • For collaboration, use latexdiff for tracking changes (command line use: latexdiff originalfile.tex updatedfile.tex > diff.tex)

• PDFs:

  • Viewers: Okular, Evince

  • Manipulator: pdftk

• Emacs

  • Wiki: https://www.emacswiki.org/emacs/SiteMap

  • Org Mode (notes, task scheduler/tracker, etc.): https://orgmode.org/

  • ESS (IDE for R and Julia): https://ess.r-project.org/

  • Magit (git “porcelain”, for GitHub interaction): https://magit.vc/

  • MELPA (package manager): https://melpa.org/#/

• Visualization

  • Qualitative color palettes: R, Tableau, and Okabe-Ito

  • Color model: https://www.sessions.edu/color-calculator/

  • Palette starter: https://encycolorpedia.com/