yzhao062/pyod

LOCI too much memory and run time

Open

#106 opened on Jun 7, 2019

View on GitHub
 (3 comments) (0 reactions) (1 assignee)Python (7,762 stars) (1,308 forks)batch import
help wanted

Description

I don't know why this is happening but the training time for LOCI implementation (fit) take too much time and memory for even a10,000X30 data, please try to run it for credit card fraud detection kaggle dataset

Contributor guide

Tech stack
python
Domain
performancemachine learning
Issue type
performance
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
4
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.
stale
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
needs investigation
Prerequisites
Basic understanding of LOCI algorithmFamiliarity with Python profiling
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
25
Research direction
Investigate the LOCI implementation in pyod (likely in pyod/models/loci.py). Profile memory and time usage using Python profiling tools. Check if the algorithm can be vectorized or optimized. Review comments in the issue for maintainer suggestions (there are 3 comments and the issue is assigned).