sdfb_network ============ This repository contains code to do text processing as well as perform network estimation, and finally produces output in an appropriate manner for the web interface. The working directory for all the R code SHOULD be this base folder. (Thus, when running any R code, make sure getwd() == the base directory, not sdfb_network/code/something). If you're using RStudio (www.rstudio.com), setting this folder as the working directory of a Project would suffice. The shell scripts, on the other hand, should be run from the directory that they reside. The folder structure ==================== code/ ---------- Any written code for the project data/ ---------- Automatically generated data (by code) data_manual/ --- Data written by a human (or edited) software/ ------ Software packages needed Progress ======== For text_processing: moved all from old text_mining except the toproc ones. network_processing: nothing to do here; readme file written. network_estimation: added in all code here; obtained from old PGL folder. network_visualization: added code. Getting Started =============== The primary end-to-end flow of this code to is as follows. Further details are available in the README files for each sub-directory # ODNB #1 Prepare ODNB data (code/ODNB/text_processing) #2 Perform network estimation #3 Validate network estimation #4 Prepare network estimation