mca is a Multiple Correspondence Analysis (MCA) package for python, intended to be used with pandas. MCA is a feature extraction method; essentially PCA for categorical variables. You can use it, for example, to address multicollinearity or the curse of dimensionality with big categorical variables.
Please refer to the usage notes and this illustrated ipython notebook.
Michael Greenacre, Jörg Blasius (2006). Multiple Correspondence Analysis and Related Methods, CRC Press. ISBN 1584886285.