Package parsimony :: Package datasets :: Package simulate :: Module l1_l2_gl
[hide private]
[frames] | no frames]

Source Code for Module parsimony.datasets.simulate.l1_l2_gl

  1  # -*- coding: utf-8 -*- 
  2  """ 
  3  Created on Mon Jan 27 16:23:54 2014 
  4   
  5  Copyright (c) 2013-2014, CEA/DSV/I2BM/Neurospin. All rights reserved. 
  6   
  7  @author:  Tommy Löfstedt 
  8  @email:   tommy.loefstedt@cea.fr 
  9  @license: BSD 3-clause. 
 10  """ 
 11  import numpy as np 
 12  from grad import grad_l1 
 13  from grad import grad_l2_squared 
 14  from grad import grad_gl 
 15  from utils import bisection_method 
 16   
 17  __all__ = ['load'] 
 18   
 19   
20 -def load(l, k, g, beta, M, e, A, snr=None, intercept=False):
21 """Returns data generated such that we know the exact solution. 22 23 The data generated by this function is fit to the Linear regression + L1 + 24 L2 + Group lasso function, i.e. to: 25 26 f(b) = (1 / 2).|Xb - y|² + l.|b|_1 + (k / 2).|b|² + g.GL(b), 27 28 where |.|_1 is the L1 norm, |.|² is the squared L2 norm and GL is the 29 group lasso penalty. 30 31 Parameters 32 ---------- 33 l : Non-negative float. The L1 regularisation parameter. 34 35 k : Non-negative float. The L2 regularisation parameter. 36 37 g : Non-negative float. The group lasso regularisation parameter. 38 39 beta : Numpy array (p-by-1). The regression vector to generate data from. 40 41 M : Numpy array (n-by-p). The matrix to use when building data. This 42 matrix carries the desired correlation structure of the generated 43 data. The generated data will be a column-scaled version of this 44 matrix. 45 46 e : Numpy array (n-by-1). The error vector e = Xb - y. This vector carries 47 the desired distribution of the residual. 48 49 A : Numpy or (usually) scipy.sparse array (K-by-p). The linear operator 50 for the Nesterov function. 51 52 snr : Positive float. Signal-to-noise ratio between model and residual. 53 54 intercept : Boolean. Whether or not to include an intercept variable. This 55 variable is not penalised. Note that if intercept is True, then e 56 will be centred. 57 58 Returns 59 ------- 60 X : Numpy array (n-by-p). The generated X matrix. 61 62 y : Numpy array (n-by-1). The generated y vector. 63 64 beta : Numpy array (p-by-1). The regression vector with the correct snr. 65 """ 66 l = float(l) 67 k = float(k) 68 g = float(g) 69 70 if intercept: 71 e = e - np.mean(e) 72 73 if snr != None: 74 def f(x): 75 X, y = _generate(l, k, g, x * beta, M, e, A, intercept) 76 77 # print "snr = %.5f = %.5f = |X.b| / |e| = %.5f / %.5f" \ 78 # % (snr, np.linalg.norm(np.dot(X, x * beta)) \ 79 # / np.linalg.norm(e), 80 # np.linalg.norm(np.dot(X, x * beta)), np.linalg.norm(e)) 81 82 return (np.linalg.norm(np.dot(X, x * beta)) / np.linalg.norm(e)) \ 83 - snr
84 85 snr = bisection_method(f, low=0.0, high=np.sqrt(snr), maxiter=30) 86 87 beta = beta * snr 88 89 X, y = _generate(l, k, g, beta, M, e, A, intercept) 90 91 return X, y, beta 92 93
94 -def _generate(l, k, g, beta, M, e, A, intercept):
95 96 p = beta.shape[0] 97 98 if intercept: 99 gradL1 = grad_l1(beta[1:, :]) 100 gradL2 = grad_l2_squared(beta[1:, :]) 101 gradGL = grad_gl(beta[1:, :], A) 102 else: 103 gradL1 = grad_l1(beta) 104 gradL2 = grad_l2_squared(beta) 105 gradGL = grad_gl(beta, A) 106 107 alpha = -(l * gradL1 + k * gradL2 + g * gradGL) 108 Mte = np.dot(M.T, e) 109 if intercept: 110 alpha = np.divide(alpha, Mte[1:, :]) 111 else: 112 alpha = np.divide(alpha, Mte) 113 114 X = np.ones(M.shape) 115 if intercept: 116 for i in xrange(p - 1): 117 X[:, i + 1] = M[:, i + 1] * alpha[i, 0] 118 else: 119 for i in xrange(p): 120 X[:, i] = M[:, i] * alpha[i, 0] 121 122 y = np.dot(X, beta) - e 123 124 return X, y
125