bcgov / bcgov/wps

FOP: Presentation of model features and skill

Open
#2,093 1 comment 0 reactions 0 assignees View on GitHub
Task
Dominant language
Python
Stars
65
Forks
11
Avg merge
21h 25m
Merged PRs (30d)
70

Description

**Describe the task**
Develop tools to visualize how FOP models work and perform for non-technical users.

**Acceptance Criteria**
- [ ] Ability to present what features used to train a model and explain their contribution to predictions.
- [ ] Ability to compare and quantify the accuracy and skill of different models, eg.) confusion matrix.
- [ ] Ability to show how model performance varies geographically throughout the province and for different times of year and conditions.

**Additional context**
- I do not expect a model to perform the same in each of the Fire Centres or across different seasons. We need to consider these geo-spatial factors when evaluating models.

Contributor guide

Open the contributing guide

Research direction

No files, tests, or entry points are named. Start by locating the FOP model evaluation and presentation components, then define how feature contributions, model accuracy, confusion matrices, and geographic or seasonal performance should be represented. Done requires agreed user-facing tools covering all three acceptance criteria.

Written by the indexing model from the issue text.

Assessment

Tech stack
machine-learning
Domain
data-visualization, machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.