Multilayer Feed-Forward Neural Network (MuFFNN) models with TensorFlow and scikit-learn
Project description
# Introduction
This project provides multilayer perceptron predictive models, implemented
using [TensorFlow](https://www.tensorflow.org/) and following the
[scikit-learn](http://scikit-learn.org)
[Predictor API](http://scikit-learn.org/stable/developers/contributing.html#apis-of-scikit-learn-objects).
# Installation
Installation with `pip` is recommended:
```bash
pip install muffnn
```
You can also create a `conda` environment:
```bash
conda env create -f environment.yml
source activate muffnn
pip install muffnn
```
Google provides TensorFlow pip wheels for different OSs and architectures.
See [this page](https://www.tensorflow.org/install/) for more details.
For development, a few additional dependencies are needed:
```bash
conda install flake8 pytest nose
```
# Usage
To use the code, import one of the predictor classes and use it as you would
other predictors such as `LogisticRegression`. An example:
```python
from muffnn import MLPClassifier
X, y = load_some_data()
mlp = MLPClassifier()
mlp.fit(X, y)
X_new = load_some_unlabeled_data()
y_pred = mlp.predict(X_new)
```
# Contributing
See `CONTIBUTING.md` for information about contributing to this project.
# License
BSD-3
See `LICENSE.txt` for details.
# Related Tools
* [sklearn.neural_network](http://scikit-learn.org/dev/modules/classes.html#module-sklearn.neural_network)
* [tensorflow.contrib.learn](https://github.com/tensorflow/tensorflow/tree/r0.10/tensorflow/contrib/learn/python/learn)
* [keras.wrappers.scikit_learn](https://keras.io/scikit-learn-api/)
# Contributors
* [Mike Heilman](https://github.com/mheilman/)
* [Walt Askew](https://github.com/waltaskew/)
* [Matt Becker](https://github.com/beckermr/)
* [Bill Lattner](https://github.com/wlattner/)
* [Sam Weiss](https://github.com/samcarlos)
This project provides multilayer perceptron predictive models, implemented
using [TensorFlow](https://www.tensorflow.org/) and following the
[scikit-learn](http://scikit-learn.org)
[Predictor API](http://scikit-learn.org/stable/developers/contributing.html#apis-of-scikit-learn-objects).
# Installation
Installation with `pip` is recommended:
```bash
pip install muffnn
```
You can also create a `conda` environment:
```bash
conda env create -f environment.yml
source activate muffnn
pip install muffnn
```
Google provides TensorFlow pip wheels for different OSs and architectures.
See [this page](https://www.tensorflow.org/install/) for more details.
For development, a few additional dependencies are needed:
```bash
conda install flake8 pytest nose
```
# Usage
To use the code, import one of the predictor classes and use it as you would
other predictors such as `LogisticRegression`. An example:
```python
from muffnn import MLPClassifier
X, y = load_some_data()
mlp = MLPClassifier()
mlp.fit(X, y)
X_new = load_some_unlabeled_data()
y_pred = mlp.predict(X_new)
```
# Contributing
See `CONTIBUTING.md` for information about contributing to this project.
# License
BSD-3
See `LICENSE.txt` for details.
# Related Tools
* [sklearn.neural_network](http://scikit-learn.org/dev/modules/classes.html#module-sklearn.neural_network)
* [tensorflow.contrib.learn](https://github.com/tensorflow/tensorflow/tree/r0.10/tensorflow/contrib/learn/python/learn)
* [keras.wrappers.scikit_learn](https://keras.io/scikit-learn-api/)
# Contributors
* [Mike Heilman](https://github.com/mheilman/)
* [Walt Askew](https://github.com/waltaskew/)
* [Matt Becker](https://github.com/beckermr/)
* [Bill Lattner](https://github.com/wlattner/)
* [Sam Weiss](https://github.com/samcarlos)
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
muffnn-1.1.2.tar.gz
(28.7 kB
view hashes)