Installation

  • Install Keras from PyPI (recommended):

The easiest way to get SeqLearner is through pip using the following command:

sudo pip install seqlearner

If you are using a virtualenv, you may want to avoid using sudo:

pip install seqlearner

This should install all the dependencies in addition to the package.

  • Alternatively: install Keras from the GitHub source:

You can also get SeqLearner from Github using the following steps: First, clone SeqLearner using git:

git clone https://github.com/EliHei/SeqLearn

Then, cd to the SeqLearner folder and run the install command:

cd SeqLearn
python setup.py install

On Windows machines you may need to download a C++ compiler if you wish to build from source yourself.

Dependencies

The requirements for SeqLearner can be found in the requirements.txt file in the repository, and include numpy, pandas, tensorflow, keras, gensim, pomegranate, and matplotlib.

  • numpy: The fundamental package for scientific computing.

  • pandas: The library which provides high-performance, easy-to-use data structures and data analysis tools for the Python.

  • tensorflow: The library for high performance numerical computation.

  • keras: Keras is a high-level neural networks API.

  • gensim: Tools for Scalable statistical semantics.

  • pomegranate: A Python package that implements fast and flexible probabilistic models.

  • matplotlib: a Python 2D plotting library which produces publication quality figures