You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: README.md
+51-39Lines changed: 51 additions & 39 deletions
Original file line number
Diff line number
Diff line change
@@ -7,6 +7,7 @@
7
7
8
8
<!-- <div style="clear: both;"></div> -->
9
9
10
+
10
11
## About The Project
11
12
12
13
**PyIKT** (Python for Isolation Kernel Toolkit) is an intuitive Python library designed for a variety of machine learning tasks including kernel similarity calculation, anomaly detection, clustering, and change detection—all powered by the innovative **Isolation Kernel (IK)** . Isolation Kernel is a data-dependent kernel that measures similarity by isolating data points using an isolation mechanism. It uniquely adapts to the data distribution, with the property that points in sparse regions are more similar than those in dense regions. Notably, it requires no learning or closed-form expression, making it efficient and scalable.
@@ -45,8 +46,19 @@ To install the basic version of `pyikt` with core dependencies, run the followin
45
46
pip install pyikt
46
47
```
47
48
48
-
For more installation options, including dependencies and additional features, check out our [Installation Guide](./quick-start/how-to-install.html).
49
+
For more installation options, including dependencies and additional features, check out our [Installation Guide](https://isolationkernel.github.io/pyikt/quick-start/how-to-install.html).
50
+
51
+
---
52
+
53
+
## Anomaly Detection Example
49
54
55
+
```py
56
+
import numpy as np
57
+
from pyikt.anomaly import INNE
58
+
X = np.array([[-1.1, 0.2], [0.3, 0.5], [0.5, 1.1], [100, 90]])
59
+
clf = INNE(contamination=0.25).fit(X)
60
+
clf.predict([[0.1, 0.3], [0, 0.7], [90, 85]])
61
+
```
50
62
---
51
63
52
64
## Implemented Algorithms
@@ -66,88 +78,88 @@ For more installation options, including dependencies and additional features, c
|[IKGAD](https://isolationkernel.github.io/pyikt/api/group/ikgad.html)| Isolation Distributional Kernel for group anomaly detections | Group Anomaly Detection | TKDE2022 |
|[IKTOD](https://isolationkernel.github.io/pyikt/api/time_series/iktod.html)| Isolation distribution kernel for Time Series Anomaly Detection | Anomaly detection | VLDB2022 |
122
134
123
135
---
124
136
125
137
## Features
126
138
127
-
pyikt provides a set of key features designed to make time series forecasting with machine learning easy and efficient. For a detailed overview, see the [User Guides](./user_guides/table-of-contents.html).
139
+
pyikt provides a set of key features designed to make time series forecasting with machine learning easy and efficient. For a detailed overview, see the [User Guides](https://isolationkernel.github.io/pyikt/user_guides/table-of-contents.html).
128
140
129
141
---
130
142
131
143
## Examples and tutorials
132
144
133
-
Explore our extensive list of examples and tutorials (English and Spanish) to get you started with PyIKT. You can find them [here](./examples/examples_english.html).
145
+
Explore our extensive list of examples and tutorials (English and Spanish) to get you started with PyIKT. You can find them [here](https://isolationkernel.github.io/pyikt/examples/examples_english.html).
134
146
135
147
---
136
148
137
149
## How to contribute
138
150
139
151
Primarily, PyIKT development consists of adding and creating new *Forecasters*, new validation strategies, or improving the performance of the current code. However, there are many other ways to contribute:
140
152
141
-
- Submit a bug report or feature request on [GitHub Issues](https://github.com/pyikt/pyikt/issues).
142
-
- Contribute a Jupyter notebook to our [examples](./examples/examples_english.html).
153
+
- Submit a bug report or feature request on [GitHub Issues](https://github.com/IsolationKernel/pyikt/issues).
154
+
- Contribute a Jupyter notebook to our [examples](https://isolationkernel.github.io/pyikt/examples/examples_english.html).
143
155
- Write [unit or integration tests](https://docs.pytest.org/en/latest/) for our project.
144
156
- Answer questions on our issues, Stack Overflow, and elsewhere.
145
157
- Translate our documentation into another language.
146
158
- Write a blog post, tweet, or share our project with others.
147
159
148
-
For more information on how to contribute to pyikt, see our [Contribution Guide](./contributing/contribution.html).
160
+
For more information on how to contribute to pyikt, see our [Contribution Guide](https://isolationkernel.github.io/pyikt/contributing/contribution.html).
149
161
150
-
Visit our [authors section](./authors/authors.html) to meet all the contributors to pyikt.
162
+
Visit our [authors section](https://isolationkernel.github.io/pyikt/authors/authors.html) to meet all the contributors to pyikt.
0 commit comments