In HSPS-DataScience/tsCogs: Time series / cognostics generation package for Henry Schein Data Science Team

knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#>"
)

This package was built to take raw data and identify entities which are at risk of negatively changing their behavior. The steps and details involved include:

• create a time-series profile from raw transactional data,
• determine "truth" via k-means clustering on the shape (normalized) of the time-series profiles,
• flexibly limit both start and end of the time-series profile for modeling purposes,
• create generic feature set related to the time-series profiles,
• apply a machine learning algorithm to model/predict risk of behavior change,
• pass along details and attributes for each entity not used in each stage list above but useful in driver analysis and other post-prediction efforts.

Time-series Profile Creation

Note the various macros within the vignette section of the metadata block above. These are required in order to instruct R how to build the vignette. Note that you should change the title field and the \VignetteIndexEntry to match the title of your vignette.

k-means Clustering

Cut-Point Algorithm

The figure sizes have been customised so that you can easily put two images side-by-side.

plot(1:10)
plot(10:1)

More Examples

You can write math expressions, e.g. $Y = X\beta + \epsilon$, footnotes^[A footnote here.], and tables, e.g. using knitr::kable().

knitr::kable(head(mtcars, 10))

Also a quote using >:

"He who gives up [code] safety for [code] speed deserves neither." (via)

HSPS-DataScience/tsCogs documentation built on May 24, 2019, 8:56 a.m.