annoviko/pyclustering

[pyclustering.utils.metric][ccore.utils.metric] V-Measure

Open

#631 opened on Aug 27, 2020

View on GitHub
 (0 comments) (0 reactions) (1 assignee)Python (263 forks)auto 404
EnhancementGood First Issue

Repository metrics

Stars
 (1,215 stars)
PR merge metrics
 (PR metrics pending)

Description

Introduction There is a discussion regarding to purity estimation - see #620 . In order to cover this proposal, V-Measure should be implemented.

References Article: V-Measure: A conditional entropy-based external cluster evaluation measure. Andrew Rosenberg and Julia Hirschberg.

Description The functionality should be implemented for Python and C++ version. The following namespaces are proposed:

  • pyclustering.utils.metric (Python).
  • pyclustering::utils::metric (C++).

The implementation should be done in line with the description.

Sub-tasks

  • Implement V-Measure for Python version of the library.
  • Implement V-Measure for C++ version of the library.
  • Implement integration of the C++ into Python.
  • Write documentation for Python version including examples.
  • Write documentation for C++ version including examples.

Contributor guide

Research direction
Study the V Measure paper and implement it in pyclustering's metric module for both Python and C++. Follow existing metric implementations in the codebase. Write tests and documentation.
Tech stack
pythoncpp
Domain
machine learning
Issue type
Feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-2 days
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Clear
Prerequisites
PythonC++
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
40