Statistical/ML modeling with scikit-learn
========================================================

The `sckit-learn module <http://scikit-learn.org/stable/>`_ is a full featured Python module for all kinds of data analysis and predictive modeling algorithms. In
the pcda class we did `one session at the end of the semester <http://www.sba.oakland.edu/faculty/isken/courses/pcda/modeling3_unsupervised_scikit_learn.html>`_ that just introduced this library and did some basic statistical/ML modeling. We'll pick up
where that session left off and dive a little deeper both into some advanced modeling concepts as well as some of of sklearn's features such as `preprocessors <https://scikit-learn.org/stable/modules/preprocessing.html>`_ and `pipelines <https://scikit-learn.org/stable/modules/generated/sklearn.pipeline.Pipeline.html>`_. 

Through this module you will:

* review using sklearn to train and use statistical and machine learning models,
* learn about and build ensemble models in sklearn,
* use cookiecutter templates to create project folder/file structures and learn concepts for data science project file management,
* learn about regularization methods within the context of building classifier models for the Pump it Up competition,
* build logistic and tree based classifiers in sklearn using preprocessors and pipelines.

.. toctree::
   :maxdepth: 1
   :caption: Sub-modules:
   
   Review of sklearn and ensemble models <mod2a_sklearn_review>
   Using cookiecutters to structure projects <mod2b_pumpitup_project_structure> 
   Data prep for Pump it Up project <mod2c_pumpitup_dataprep> 
   Regularization and more classifier models <mod2d_pumpitup_modeling>

* :ref:`search`