cwidmer

def dual_pca(X, max_num_pcs):
    """
    assuming N << D (X.shape[0] << X.shape[1]), 
    we first compute the kernel matrix K = XX^T, perform an
    eigendecomposition and subsequently reconstruct
    truncated principle components
    """
    
    
    K = X.dot(X.T)

cwidmer

"""
snippet to time different indexing strategies

based on:
http://wesmckinney.com/blog/?p=215
http://stackoverflow.com/questions/11800075/faster-numpy-fancy-indexing-and-reduction/11813040#11813040
http://stackoverflow.com/questions/14386822/fast-numpy-fancy-indexing?rq=1
"""

import numpy as np

cwidmer

"""
cache linear algebra (or any other) operations
based on hashes of input arguments
"""

import numpy.linalg as la
from sklearn.external import joblib

mem = joblib.Memory(cachedir=cachedir, verbose=True, compress=True)
#mem.clear()

cwidmer

{
 "metadata": {
  "name": ""
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {

cwidmer

import numpy as np
import time

# generate data
X = np.random.randn(1000, 10000)

t0 = time.time()
K = X.dot(X.T) + 1e-9*np.eye(X.shape[0])
tK = time.time() - t0
print "tK:", tK