christianbauckhage
Profile  About  Not provided yet 
Affiliation  University of Bonn  
Country  Not provided yet  
Website  Not provided yet  
Interests  Not provided yet  
Meta  Permalink  http://spc.scipy.org/user/175/ 
User Id  175 

NumPy / SciPy Recipes for Data Science: Eigenvalues/Eigenvectors of Covariance Matrices
In this note, we discuss a potential pitfall in using NumPy or SciPy methods to compute eigen decompositions of covariance matrices and show how to avoid it. In short, we ...
 0
 by christianbauckhage
 on 09 November 2015

NumPy / SciPy Recipes for Data Science: Computing Nearest Neighbors
In this note, we discuss efficient NumPy recipes for Euclidean nearest neighbor and knearest neighbor searches in data sets of moderate size. Our code snippets are basically oneliners and orders ...
 0
 by christianbauckhage
 on 08 November 2015

NumPy / SciPy Recipes for Data Science: Kernel Least Squares Optimization (1)
In this note, we show that least squares optimization is amenable to the kernel trick. This provides great flexibility in model fitting and we consider examples that illustrate this. In ...
 0
 by christianbauckhage
 on 03 April 2015

NumPy / SciPy Recipes for Data Science: Squared Euclidean Distance Matrices
In this note, we explore and evaluate various ways of computing squared Euclidean distance matrices (EDMs) using NumPy or SciPy. In particular, we discuss 6 increasingly abstract code snippets where ...
 0
 by christianbauckhage
 on 22 March 2015

NumPy / SciPy Recipes for Data Science: kMedoids Clustering
In this note, we study kmedoids clustering and show how to implement the algorithm using NumPy. To illustrate potential and practical use of this lesser known clustering method, we discuss ...
 0
 by christianbauckhage
 on 22 March 2015