paceofchange | Code and data to support the article

paceofchange is a Python library. paceofchange has no bugs, it has no vulnerabilities, it has a Permissive License and it has low support. However paceofchange build file is not available. You can download it from GitHub.

Code, data, and metadata to support replication of the results in ["How quickly do literary standards change?"] If you have Python 3 with numpy, pandas and scikit-learn, you should be able to clone this repo and then run replicate.py. Different forms of analysis can be provided to replicate.py as command-line arguments. For instance,. Replicates the main model represented in Figure 1 of the article. Other options include quarters, halves, canon, genders, and nations. The standards we are trying to meet are pithily summarized by Jason Baldridge in ["It’s okay for academic software to suck."] We want our results to be reliable, so we’ve worked hard to ensure that the models produced by this code are cross-validated appropriately. We want the enclosed data and metadata to be reliable — which means, on this scale, a low level of evenly-distributed error. So we’ve documented our procedures and shared metadata in ["Understanding Genre in a Collection of a Million Volumes."] But this is not a project that promised to build portable tools, and you won’t find any in this repo. Our view is that the really portable tools are already encapsulated in scikit-learn.