jrbourbeau/madpy-ml-sklearn-2018

MadPy supervised machine learning talk

Supervised machine learning in Python with scikit-learn

Materials for "Supervised machine learning in Python with scikit-learn" talk at the Madison Python (MadPy) meetup. A live version of the slides can be found at https://jrbourbeau.github.io/madpy-ml-sklearn-2018/.

Installation

The dependencies for generating the slides are:

• numpy
• pandas
• jupyter
• scikit-learn
• mlxtend
• matplotlib
• graphviz

Using conda

A conda environment with these dependencies installed can be created via:

conda env create --file environment.yml
source activate madpy-ml-sklearn-2018

Using pip

Inside a virtual environment, pip install the needed packages via:

pip install -r requirements.txt

Note: to render decision tree graphs Graphviz must also be installed.

Usage

The slides for this talk can be generated via:

jupyter nbconvert machine-learning-sklearn-madpy.ipynb --to slides --post serve

To run the corresponding notebook use

jupyter notebook machine-learning-sklearn-madpy.ipynb