Statistics, data mining, and machine learning in astronomy

Statistics, Data Mining, and Machine Learning in Astronomy B AstroML Machine Learning for Astronomy B 1 Introduction AstroML is a Pythonmodule for machine learning and data mining built on NumPy, SciP[.]

B AstroML: Machine Learning for Astronomy

B.1 Introduction

AstroML is a Python module for machine learning and data mining built on NumPy, SciPy, Scikit-learn, and Matplotlib, and distributed under an unrestrictive license It was created to enable the creation of the figures in this text, as well as to serve as a repository for Python astronomy tools, including routines for analyzing astronomical data, loaders for several open astronomical data sets, and a large suite of examples of analyzing and visualizing astronomical data sets

In order to balance the competing desires to offer easy installation for first-time users and at the same time offer powerful routines written in compilable code, the project is split into two components The core AstroML library is written in pure Python, and is designed to be very easy to install for any user, even one who does not have a working C or Fortran compiler A companion library, astroML_addons, can be optionally installed for increased performance on certain algorithms The algorithms in astroML_addons duplicate functionality existing in AstroML, but the astroML_addons library contains faster and more efficient implementations of the routines In order to streamline this further, if astroML_addons is installed in your Python path, the core AstroML library will import and use the faster routines

by default

For access to the source code and detailed installation instructions, see http://www.astroML.org

B.2 Dependencies

There are three levels of dependencies in AstroML Core dependencies are required for the core AstroML package Add-on dependencies are required for the perfor-mance astroML_addons Optional dependencies are required to run some (but

not all) of the example scripts Individual example scripts will list their optional dependencies at the top of the file

Core dependencies

The core AstroML package requires the following:

•Python: http://python.org version 2.6.x–2.7.x

•NumPy: http://www.numpy.org/ version 1.4+

•SciPy: http://www.scipy.org/ version 0.7+

•Matplotlib: http://matplotlib.org/ version 0.99+