Download presentation
Presentation is loading. Please wait.
1
Isolation Forest B 工海三 顧家琛
2
Outline Algorithm Introduction Code Review Live Demo(Using InAnalysis)
.iTree .iForest Code Review .Parameters . n_estimators . max_samples Live Demo(Using InAnalysis) Conclusion Reference
3
Algorithm Introduction
iTree .randomly selecting a feature .randomly selecting a split value
4
Algorithm Introduction
iTree Who’s abnormal?
5
Algorithm Introduction
iForest .measure of normality .高度log2(n))
6
Code Review
7
WHY? Code Review n_estimators , max_samples :
Default: n_estimators = 100 , max_samples = 256 WHY?
8
WHY? Code Review n_estimators , max_samples :
Default: n_estimators = 100 , max_samples = 256 WHY?
9
Code Review n_estimators , max_samples :
Default: n_estimators = 100 , max_samples = 256
10
Code Review n_estimators , max_samples :
Default: n_estimators = 100 , max_samples = 256
11
Live demo
12
Conclusion
13
Reference https://read01.com/xD8AEnO.html
learn.org/stable/modules/generated/sklearn.ensemble.IsolationForest.html#sklear n.ensemble.IsolationForest
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.