Anomaly detection for one-dimensional data
Project description
xiezhi: The First One-dimensional Anomaly Detection Tool
Install
pip install xiezhi-ai
Usage
The inputs include data, beta, and alpha.
data: The current version only supports the detection of one-dimensional data, so the data should be a list.
beta and alpha are set between 0 and 1 and beta is smaller than alpha, if there are few anomalies, beta and alpha can be set close to 1; otherwize, it should be set close to 0.5. If the number of anomalies are unknown, then both of beta and alpha should be close to 0.5.
Below is the example:
import xiezhi as xz
data=[1,2,3,4,5,6,7,9,10,20] # here 20 is the anomaly
benign_data=xz(data,0.7,0.9) # xiezhi will return the benign data
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
xiezhi-ai-0.0.0.tar.gz
(2.0 kB
view hashes)
Built Distribution
Close
Hashes for xiezhi_ai-0.0.0-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | e8d091b9ecbcaed5a8816332ce6996d7952cdda9d180cdb03afeb3d0ef8751c1 |
|
MD5 | 5a21b209657e7287fec45ece5f897f90 |
|
BLAKE2b-256 | 93ba948c1f78786f63e9431ecf5339b6cac9f60fc42d8612eed9a8832ea05c12 |