Add samples_generator folder for simulated data

git-svn-id: https://scikit-learn.svn.sourceforge.net/svnroot/scikit-learn/trunk@440 22fbfee3-77ab-4535-9bad-27d1bd3bc7d8

scikits/learn/bayes/bayes.py

@@ -97,11 +97,11 @@ def bayesian_ridge( X , Y, step_th=300,th_w = 1.e-6,ll_bool=True) :
 
 	### Compute the log likelihood
 	if ll_bool :
+	  residual_ = (Y - np.dot(X, w))**2
 	  ll = 0.5*X.shape[1]*np.log(alpha) + 0.5*X.shape[0]*np.log(beta)
-	  ll -= 0.5*beta*residual_.sum()+ 0.5*alpha*np.dot(w.T,w)
-	  ll -= fast_logdet(inv_sigma_) 
+	  ll -= (0.5*beta*residual_.sum()+ 0.5*alpha*np.dot(w.T,w))
+	  ll -= fast_logdet(alpha*ones + beta*gram)
 	  ll -= X.shape[0]*np.log(2*np.pi)
 	  log_likelihood.append(ll)
 
-    return w
-
+    return w,log_likelihood[1:]

scikits/learn/samples_generator/linear.py

+import numpy as np
+
+
+def sparse_uncorrelated(nb_samples=100,nb_features=10):
+    """
+    Function creating simulated data with sparse uncorrelated design.
+    (cf.Celeux et al. 2009,  Bayesian regularization in regression)
+    X = NR.normal(0,1)
+    Y = NR.normal(2+X[:,2]+2*X[:,3]-2*X[:,6]-1.5*X[:,7])
+    The number of features is at least 10.
+
+    Parameters
+    ----------
+    nb_samples : int
+                 number of samples (defaut is 100).
+    nb_features : int
+                  number of features (defaut is 10).
+    
+    Returns
+    -------
+    X : numpy array of shape (nb_samples,nb_features)
+	simulated samples.
+    Y : numpy array of shape (nb_samples)
+    """
+    X = nr.normal(loc=0,scale=1,size=(nb_samples,nb_features))
+    Y = nr.normal(loc=2+x[:,2]+2*x[:,3]-2*x[:,6]-1.5*x[:,7],
+    scale=np.ones(nb_samples))
+    return X,Y
\ No newline at end of file