https://github.com/javadr/yeast-occ
One Class Classifier for detecting positive cases while just trained on negative cases.
https://github.com/javadr/yeast-occ
anomaly-detection machine-learning oneclass oneclasssvm
Last synced: 12 months ago
JSON representation
One Class Classifier for detecting positive cases while just trained on negative cases.
- Host: GitHub
- URL: https://github.com/javadr/yeast-occ
- Owner: javadr
- License: gpl-3.0
- Created: 2021-09-16T12:24:35.000Z (over 4 years ago)
- Default Branch: main
- Last Pushed: 2021-09-21T08:47:35.000Z (over 4 years ago)
- Last Synced: 2025-06-02T22:48:28.705Z (about 1 year ago)
- Topics: anomaly-detection, machine-learning, oneclass, oneclasssvm
- Language: Jupyter Notebook
- Homepage:
- Size: 453 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Yeast-OCC
One Class Classifier for detecting positive cases while just trained on negative cases.
## Dataset
The Yeast dataset is obtained from [KEEL data repository](https://sci2s.ugr.es/keel/datasets.php). his dataset contains 1004 number of instances and 8 numeric attributes. The last attribute is the class variable with two values `positive` and `negative`.
## Task
Building classifier(s) on the Yeast dataset that can identify the classes `positive` and `negative` with high performance. The training data has only “negative class”, while testing data has both the classes; `negative` and `positive`.
## Method
Three different methods have been applied on the data `One Class SVM`, `Isolation Forest`, and `Elliptic Envelope`.
## Data Attribute Plots (boxplot, heatmap, and correlation)
### Box Plot
### Heat Map
### Correlation Matrix
