w_estimado,yy3,xx3=lasso.lasso(Xtotal,Ytotal,vec,Xtotal,Ytotal,Xtotal,Ytotal,max_iter,lamb)
w0.append(w_estimado[0,0])
w1.append(w_estimado[1,0])
w2.append(w_estimado[2,0])
w3.append(w_estimado[3,0])
w4.append(w_estimado[4,0])
print w_estimado
import pylab
import matplotlib.pyplot as plt
plt.figure(1)
'''
plt.title("Comparacao entre os 3 metodos")
plt.plot(xx1,yy1,"b",xx2,yy2,"g",xx3,yy3,"r",xx1,[custo for cenas in xrange(len(xx1))],"k--")
pylab.ylim([custo-1e14,custo+4e14])
plt.show()
'''
plt.plot(xg,w0,"r",xg,w1,"k",xg,w2,"b",xg,w3,"g",xg,w4,"y")
plt.show()
'''
#pdb.set_trace()
print "X=>",X.data
print "Y=>",Y.data
print "W=>",W.data
vec=sparse.csr_matrix([1000000 for i in xrange(X.shape[1])])
vec=vec.transpose()
grad.grad(X,Y,vec)
'''
trainsize=int(Xtotal.shape[0]*0.8)
devsize=int(Xtotal.shape[0]*0.1)+trainsize
#Xtrain,Ytrain,Xtest,Ytest,Xdev,Ydev=separaXY(Xtotal,Ytotal)
#train_index=xrange(trainsize)
#dev_index=xrange(trainsize,devsize)
#test_index=xrange(devsize,Xtotal.shape[0])
Xtotal=Xtotal.tocsc()
Xtotal,indices=cria_dados.delstopword(Xtotal,indices,False)
Xtotal,indices=tira_meta(Xtotal,indices)
#Xtotal,indices=repara(Xtotal,indices)
Xtotal=Xtotal.tocsc()
Ytotal=Ytotal.tocsc()
#vec=sparse.csr_matrix([0 for i in xrange(Xtrain.shape[1])])
vec=sparse.csr_matrix([0 for i in xrange(Xtotal[:trainsize,:].shape[1])])
vec=vec.transpose()
W,lol1,lol2=Rgrad.grad(Xtotal[:trainsize,:],Ytotal[0:trainsize,0],vec,Xtotal[devsize:,:],Ytotal[devsize:,0],Xtotal[trainsize:devsize,:],Ytotal[trainsize:devsize,0],False,False)
#W=Rgrad.grad(Xtrain,Ytrain.transpose(),vec,Xdev,Ydev.transpose(),Xtest,Ytest.transpose(),False,False)
#pdb.set_trace()
#print "ERRO:",Rfechado.erro(Xtest,Ytest,W)
print "ERRO:", Rfechado.erro(Xtotal[trainsize:devsize,:],Ytotal[trainsize:devsize,:],W)
print "__________________"
print "PIORES 10"
pdb.set_trace()
for coiso in sorted(W.toarray())[:10]:
i=0
while W[i,0] != coiso:
i+=1
else:
for cenas in indices:
if indices[cenas]==i:
print cenas , coiso, "->",i