Monitoring ML Systems: Challenges, Solutions and Metrics from a Practitioners' Perspective

This is the dataset for the paper "Monitoring ML Systems: Challenges, Solutions and Metrics from a Practitioners' Perspective". The dataset is recorded in an MS Excel file which contains the following Excel sheets, and the description of each sheet is briefly presented below.

(1) Selected Projects (GitHub) contain the 15 selected ML projects with the URL of each project.

(2) Raw Data (GitHub) contains the information about the randomly selected 600 issues, such as issue titles, issue links, issue id.

(3) Raw Data (SO) contains the information about the randomly selected 2088 SO posts (part of the 2174 SO posts), such as post titles, post link, post id, and open date.

(4) MLOps (SO) contains the information about the 86 MLOps SO posts (part of the 2174 SO posts), such as post titles, post link, post id, and open date.

(5) Identified Challenges (GitHub) contain the list of categories, subcategories, and codes of identified challenges from GitHub issues.

(6) Identified Solutions (GitHub) contain the list of categories, subcategories, and codes of identified solutions from GitHub issues.

(7) Identified Metrics (GitHub) contain the list of identified metrics from GitHub issues.

(8) Identified Challenges (SO) contain the list of categories, subcategories, and codes of identified challenges from SO posts.

(9) Identified Solutions (SO) contain the list of categories, subcategories, and codes of identified solutions from SO posts.

(10) Identified Metrics (SO) contain the lists of identified metrics from SO posts.

(11) Identified Challenges (Interview) contain the list of categories, subcategories, and codes of identified challenges from interviews.

(12) Identified Solutions (Interview) contain the list of categories, subcategories, and codes of identified solutions from interviews.

(13) Identified Metrics (Interview) contain the list of identified metrics from interviews.

(14) Identified Challenges (Final) contain the taxonomy of the final challenges identified from GitHub issues, SO posts, and interviews.

(15) Identified Solutions (Final) contain the taxonomy of the final solutions identified from GitHub issues, SO posts, and interviews.

(16) Identified Metrics (Final) contain the final list of metrics identified from GitHub issues, SO posts, and interviews.