Merge pull request #29675 from taosdata/doc/ana_doc

doc: update TDgpt doc
This commit is contained in:
Shengliang Guan 2025-02-05 16:39:45 +08:00 committed by GitHub
commit 609389d05c
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
4 changed files with 36 additions and 1 deletions

View File

@ -91,3 +91,18 @@ taos> select _flow, _fhigh, _frowts, forecast(i32) from foo;
## 内置预测算法
- [arima](./02-arima.md)
- [holtwinters](./03-holtwinters.md)
- CES (Complex Exponential Smoothing)
- Theta
- Prophet
- XGBoost
- LightGBM
- Multiple Seasonal-Trend decomposition using LOESS (MSTL)
- ETS (Error, Trend, Seasonal)
- Long Short-Term Memory (LSTM)
- Multilayer Perceptron (MLP)
- DeepAR
- N-BEATS
- N-HiTS
- PatchTST (Patch Time Series Transformer)
- Temporal Fusion Transformer
- TimesNet

View File

@ -50,6 +50,13 @@ FROM foo
ANOMALY_WINDOW(foo.i32, "algo=shesd,direction=both,anoms=0.05")
```
后续待添加异常检测算法
- Gaussian Process Regression
基于变点检测的异常检测算法
- CUSUM (Cumulative Sum Control Chart)
- PELT (Pruned Exact Linear Time)
### 参考文献
1. [https://en.wikipedia.org/wiki/689599.7 rule](https://en.wikipedia.org/wiki/68%E2%80%9395%E2%80%9399.7_rule)
2. https://en.wikipedia.org/wiki/Interquartile_range

View File

@ -3,7 +3,7 @@ title: "数据密度算法"
sidebar_label: "数据密度算法"
---
### 基于数据密度的检测方
### 基于数据密度/数据挖掘的检测算
LOF<sup>[1]</sup>: Local Outlier Factor(LOF),局部离群因子/局部异常因子,
是 Breunig 在 2000 年提出的一种基于密度的局部离群点检测算法,该方法适用于不同类簇密度分散情况迥异的数据。根据数据点周围的数据密集情况,首先计算每个数据点的一个局部可达密度,然后通过局部可达密度进一步计算得到每个数据点的一个离群因子,
该离群因子即标识了一个数据点的离群程度,因子值越大,表示离群程度越高,因子值越小,表示离群程度越低。最后,输出离群程度最大的 $topK$ 个点。
@ -15,6 +15,14 @@ FROM foo
ANOMALY_WINDOW(foo.i32, "algo=lof")
```
后续待添加基于数据挖掘检测算法
- DBSCAN (Density-Based Spatial Clustering of Applications with Noise)
- K-Nearest Neighbors (KNN)
- Principal Component Analysis (PCA)
第三方异常检测算法库
- PyOD
### 参考文献
1. Breunig, M. M.; Kriegel, H.-P.; Ng, R. T.; Sander, J. (2000). LOF: Identifying Density-based Local Outliers (PDF). Proceedings of the 2000 ACM SIGMOD International Conference on Management of Data. SIGMOD. pp. 93104. doi:10.1145/335191.335388. ISBN 1-58113-217-4.

View File

@ -12,6 +12,11 @@ FROM foo
ANOMALY_WINDOW(col1, 'algo=encoder, model=ad_autoencoder_foo');
```
后续添加机器(深度)学习异常检测算法
- Isolation Forest
- One-Class Support Vector Machines (SVM)
- Prophet
### 参考文献
1. https://en.wikipedia.org/wiki/Autoencoder