Implemented some ML routines
Project description
ML-handmade
Implemented some ML routines including other ML stuff such as preprocessing, visualization and model selection.
References
-
Scikit-learn source code: https://github.com/scikit-learn/scikit-learn
-
PRML algorithms by ctgk: https://github.com/ctgk/PRML
-
Sokolov lectures on ML(RU): https://github.com/esokolov/ml-course-hse
-
ML handbook by Yandex SDA(RU): https://ml-handbook.ru/
-
MLAlgorithms by rushter: https://github.com/rushter/MLAlgorithms
-
mlxtend library by rasbt: https://github.com/rasbt/mlxtend
Algorithms implemented
-
Linear models with different optmization methods(GD, SGD, Batch-SGD, SAG)
-
KNN with three approaches(brute-force, kd-tree, ball-tree)
-
Multiclass strategies (One-vs-One, One-vs-Rest)
-
Support vector (SVC and $\epsilon$-SVR) with different kernels(Linear, RBF, Polynomial)
-
Discriminant analysis(linear & quadratic) implemented using SVD
-
Decision tree classifier and regressor
-
Random forest classifier and regressor with bootstrap
-
AdaBoost classifier and regressor
-
Other ML stuff, for instance, k-fold cross validation, quality metrics, plotting, e.t.c
Installation
It can be installed using pip
pip install mlhandmade
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
Built Distribution
Hashes for mlhandmade-0.0.15-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | be277de8ea505507cfe498d76a91b8d296bc0d63aa5773d97e913116ce1085ff |
|
MD5 | 0c6380ab22b2c7a6b3f08c5ee6e667ea |
|
BLAKE2b-256 | d4844e6598cb0eed82dedd2e1bb647b80e2751e91b36704dcb10cc02b65218c9 |