PyLearn implements machine learning features from scratch.
It supports basic features of supervised and unsupervised learning.
You can
- create neural networks with dense layers, different activation functions and loss functions,
- cluster your data without previously known classes,
- classify data
- evaluate models
- and more
Read the Documentation for more information.
Install PyLearn using pip:
pip install pylearn-mlThe source code was built with Python, mainly using NumPy and Pandas.
Requirements can be found under docs/requirements.txt.
Import the library:
import pylearn as plMost models have a fit and a predict function.
Just create a model, train it and use it for predictions.
model = pl.Model()
model.fit(x_train, y_train)
...
model.predict(y_test)For details of usage, have a look at the examples folder.
Or read the Documentation
If you have a suggestion that would make this better, please fork the repo and create a pull request. You can also simply open an issue with the tag "enhancement".
- Fork the Project
- Create your Feature Branch (
git checkout -b feature/AmazingFeature) - Commit your Changes (
git commit -m 'Add some AmazingFeature') - Push to the Branch (
git push origin feature/AmazingFeature) - Open a Pull Request
Please follow the Contributing guidelines.
Distributed under the MIT License. See LICENSE for more information.