An easy-to-use ML framework
Project description
classicML: 简单易用的经典机器学习框架
classicML 是一个用Python和C++混编的机器学习项目,它既实现了Python的简单易用快速上手,又实现了C++的高效性能。classicML的设计目标是简单易用,快速入门,编程风格简洁。
多后端支持
classicML 本身是一个Python项目,但是机器学习中涉及到的复杂的矩阵运算对于Python有点儿捉襟见肘,因此我们提供了使用C++后端的函数的加速版本。为了保证兼容性,classicML默认使用Python后端,部分算法支持了使用C++作为后端进行加速,你需要安装标准版的classicML,然后在开头使用这条语句切换后端。
import os
os.environ['CLASSICML_ENGINE'] = 'CC'
第一个机器学习程序
使用线性判别分析进行二分类
- 下载示例数据集
wget https://github.com/sun1638650145/classicML/blob/master/datasets/西瓜数据集alpha.csv
- 运行下面的代码
import pandas as pd
import classicML as cml
DATASET_PATH = '/path/to/西瓜数据集alpha.csv'
# 读取数据
dataframe = pd.read_csv(DATASET_PATH, index_col=0, header=0)
x = dataframe.iloc[:, :2].values
y = dataframe.iloc[:, 2].values
y[y == '是'] = 1
y[y == '否'] = 0
# 生成模型
model = cml.models.LDA()
# 训练模型
model.fit(x, y)
# 可视化模型
cml.plots.plot_lda(model, x, y, '密度', '含糖率')
classicML 0.6 预览
这个发行版将以性能优化和原生支持Apple Silicon为更新目标
- 原生支持(native support) Apple M1
- 增加大量
C++
后端函数,将主要的操作全部用C++
重写,大幅提高性能- 修复BUG,提高稳定性
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
classicML-0.6b3.tar.gz
(53.9 kB
view hashes)
Built Distributions
Close
Hashes for classicML-0.6b3-cp39-cp39-manylinux2010_x86_64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | d82ae9646528cad57c71976e25975dd3c881ee1dfa618ffe61a27aa6fc1406f6 |
|
MD5 | 20d786a523b44b35d229a577eaa978ed |
|
BLAKE2b-256 | 1f6a1f26877ee6e39e6ac47180f62c176c2acd3670892d2bb9f2ce037833f7bc |
Close
Hashes for classicML-0.6b3-cp39-cp39-macosx_10_14_x86_64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 58c026cce2d74047354853dff92692eec02f5068d62f34128964b706fcff4038 |
|
MD5 | 3daf81f4cd5e7cf8c3269e75618ffa1f |
|
BLAKE2b-256 | dea4fbb174ca0cdfab766335e166e08af853e391a6ca7b1624159ec54fa10769 |
Close
Hashes for classicML-0.6b3-cp38-cp38-manylinux2010_x86_64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | da8431749f5fef4e894855bba9472bcfaa381124b8452c97781b51d0494f156b |
|
MD5 | 96baf9dd4e1c2ed0bf1f76836e0ce1ae |
|
BLAKE2b-256 | d5be2a69e26ef990875bb8532e2919234e7bbdaf9fa0190edb2380eb9db33cef |
Close
Hashes for classicML-0.6b3-cp38-cp38-macosx_11_0_arm64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | d910290477dd7607361d8e4daef157c5b8d669e9db76c1937a5fce4e8cfb8884 |
|
MD5 | d95f1a8703032e48808a49f7272d33f4 |
|
BLAKE2b-256 | 831b7f2688320b9326b2003c42d51254635a1417bb9b4e96ada110d94a6b37f1 |
Close
Hashes for classicML-0.6b3-cp38-cp38-macosx_10_14_x86_64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 6ec326a9083e26b6a29e0100e5f6896c0c63834be76c27450651bf887be5f6c6 |
|
MD5 | e1cbb316ba2880577e42ccd907f8676e |
|
BLAKE2b-256 | 9bcc3bd2f67426224e2c8717f1bf2b886116f4c78ed985c4a166e959ad7f845e |
Close
Hashes for classicML-0.6b3-cp37-cp37m-manylinux2010_x86_64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 3f190c252201a0df9b4f1181f2b3f2c9a562b800f49e1871d4d4b449e4c9f7f8 |
|
MD5 | ad735f4069d65bd99bca6c38561dd7c2 |
|
BLAKE2b-256 | 8b67855a55991405ba1bc6c9fef708586f57b18c8794d36d66649dd43612ed29 |
Close
Hashes for classicML-0.6b3-cp37-cp37m-macosx_10_14_x86_64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | d00a0a2b73730ef9d8beba3ce3f13b9b970da74f70ecf9b57ccd527c7aaf45da |
|
MD5 | 1da17a52d18f234ee6216f8ec27983a8 |
|
BLAKE2b-256 | 353d21d762c23abfc3410e2831d24914098385f7b3a43d8bdb529e8f9c1bf4bc |
Close
Hashes for classicML-0.6b3-cp36-cp36m-manylinux2010_x86_64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | b6d6046795dc8c4d0c2225870ec8f317937812230ddc03c513ef93d10695eade |
|
MD5 | 9b1d375c4455e3aa12754da80db8795f |
|
BLAKE2b-256 | cf9c5e160d1e65224487542dea6a87d4e7fe681e26073f75c08ad7175494182b |
Close
Hashes for classicML-0.6b3-cp36-cp36m-macosx_10_14_x86_64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 113f8ef1daf963c84235f9b2ef9cd76aefc2a2714b79dd50c2ae8799d8236dff |
|
MD5 | 30eacf37a1f5c692098963ee9c6ffbd9 |
|
BLAKE2b-256 | 3f64ce94e12fb180670ba7bbde07d38a08f7e11f7820f63d0195d371844e1ed6 |