Light

kaslanarian / pysvm Goto Github PK

View Code? Open in Web Editor NEW

25.0 1.0 2.0 3.55 MB

PySVM : A NumPy implementation of SVM based on SMO algorithm. Numpy构建SVM分类、回归与单分类，支持缓存机制与随机傅里叶特征

License: MIT License

Python 100.00%

svm svm-classifier svm-regressor svm-kernel machine-learning one-class-svm python random-fourier-features

pysvm's Introduction

😄 Hi! Nai elen siluva lyenna.

In Quenya, "Nai elen siluva lyenna" means "May the stars shine on you".

Who am I?

Welt Xing, a 1st year graduate in the School of Artificial Intelligence, Nanjing University. In German, "welt" means the "world". My interests include:

Machine learning model and their implementation.
Deep learning method and framework.
Machine learning theory.
Graph learning.

In my blog, I record what I've learned:

My stat

Your stars, forks, and issues are most welcome and appreciated 🥳.

Some finished and updating work

libsvm-sc-reading: A Chinese version manual to explain how LIBSVM works.
PySVM: A NumPy implementation of SVM based on SMO algorithm.
PyDyNet: Deep learning framework implementation using Numpy based on Autodiff.
SAGOD: A library for anomaly detection on static attributed graph.

pysvm's People

Contributors

Stargazers

Watchers

Forkers

finite-infinity yc121725

pysvm's Issues

Numpy实现ml算法

https://numpy-ml.readthedocs.io/en/latest/

https://github.com/ddbourgin/numpy-ml

第一次issue

保存模型

使用lambda表达式进行运算不利于模型的保存的。若使用joblib等工具保存模型，需要将lambda表达式重写为类成员方法。使用dill工具保存内核状态可以解决这一问题，但这是有风险的。

Solver的working_set_select中i和j的选取

为什么Solver的working_set_select中i和j的选取都采用了1阶的方法了呢？libsvm好像都是用的1阶加2阶，也就是NuSolver的working_set_select？

对比sklearn：gamma的取值问题

在sklearn里对gamma的描述是使用X.var()

gamma : {'scale', 'auto'} or float, default='scale'
        Kernel coefficient for 'rbf', 'poly' and 'sigmoid'.

        - if ``gamma='scale'`` (default) is passed then it uses
          1 / (n_features * X.var()) as value of gamma,
        - if 'auto', uses 1 / n_features.

但目前这里用的是X.std()，

kernel_func = self.register_kernel(X.std())

导致收敛速度很慢，但确实取得了更高的准确度，这是有什么考量吗？

对比大概是
sklearn 时间0.004s 准确度0.9035
X.var()+1阶时间2.7s 准确度0.9035
X.var()+2阶时间18s 准确度0.9035
X.std()+1阶时间15s 准确度0.9649
X.std()+2阶时间25s 准确度0.9649

怎么安装rff库？

Recommend Projects

React

A declarative, efficient, and flexible JavaScript library for building user interfaces.
Vue.js

🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
Typescript

TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
TensorFlow

An Open Source Machine Learning Framework for Everyone
Django

The Web framework for perfectionists with deadlines.
Laravel

A PHP framework for web artisans
D3

Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

javascript

JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
web

Some thing interesting about web. New door for the world.
server

A server is a program made to process requests and deliver data to clients.
Machine learning

Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Visualization

Some thing interesting about visualization, use data art
Game

Some thing interesting about game, make everyone happy.

Recommend Org

Facebook

We are working to build community through open source technology. NB: members must have two-factor auth.
Microsoft

Open source projects and samples from Microsoft.
Google

Google ❤️ Open Source for everyone.
Alibaba

Alibaba Open Source for everyone
D3

Data-Driven Documents codes.
Tencent

China tencent open source team.