Python nimfa.mf_run函数代码示例

def run_nmf(V):
    """
    Run standard nonnegative matrix factorization.
    
    :param V: Target matrix to estimate.
    :type V: :class:`numpy.matrix`
    """
    # Euclidean
    rank = 10
    model = nimfa.mf(V, 
                  seed = "random_vcol", 
                  rank = rank, 
                  method = "nmf", 
                  max_iter = 12, 
                  initialize_only = True,
                  update = 'euclidean',
                  objective = 'fro')
    fit = nimfa.mf_run(model)
    print_info(fit)
    # divergence
    model = nimfa.mf(V, 
                  seed = "random_vcol", 
                  rank = rank, 
                  method = "nmf", 
                  max_iter = 12, 
                  initialize_only = True,
                  update = 'divergence',
                  objective = 'div')
    fit = nimfa.mf_run(model)
    print_info(fit)

    def learnModel(self, X):
        """
        Learn X using a matrix factorisation method. If self.rank is an integer 
        then we factorise with that rank. If it is an array then we compute the 
        complete regularisation path and return a list of matrices. 
        """
        if isinstance(self.rank, int): 
            model = nimfa.mf(X, method=self.method, max_iter=self.maxIter, rank=self.rank)
            fit = nimfa.mf_run(model)
            W = fit.basis()
            H = fit.coef()
            
            predX = W.dot(H)
            return predX 
        else: 
            predXList = []

            model = nimfa.mf(X, method=self.method, max_iter=self.maxIter, rank=self.rank[0])
            fit = nimfa.mf_run(model)
            W = fit.basis()
            H = fit.coef()
            predXList.append(W.dot(H))
            
            for i in range(1, self.rank.shape[0]): 
                model = nimfa.mf(X, method=self.method, max_iter=self.maxIter, rank=self.rank[i], W=W, H=H)
                fit = nimfa.mf_run(model)
                W = fit.basis()
                H = fit.coef()
                predXList.append(W.dot(H))

            return predXList

def nmf(Xtrn, Xtst):
    # Init matricies
    Xtrn_n = np.shape(Xtrn)[0]
    Xtst_n = np.shape(Xtst)[0]
    Xtrn_nmf = np.zeros((Xtrn_n, my_rank))
    Xtst_nmf = np.zeros((Xtst_n, my_rank))
    print(file_name + ': Running non-negative matrix facorization w/ rank = ' + str(my_rank))
    #Xtrn_fctr = nimfa.mf(Xtrn, method = 'nmf', seed = "fixed", max_iter = iters,
    #                     rank = my_rank, update = 'euclidean', objective = 'fro')
    print(file_name + ': \t on traning...')
    for i in xrange(Xtrn_n):
        Xtrn_fctr = nimfa.mf(Xtrn[i,:], method = 'lsnmf', max_iter = iters, rank = my_rank)
        Xtrn_res = nimfa.mf_run(Xtrn_fctr)
        Xtrn_nmf[i,:] = Xtrn_res.basis()
        if (i%10000 == 0): print(file_name + ': \t iter ' + str(i))
    print(file_name + ' \t on testing...')
    for i in xrange(Xtst_n):
        Xtst_fctr = nimfa.mf(Xtst[i,:], method = 'lsnmf', max_iter = iters, rank = my_rank)
        Xtst_res = nimfa.mf_run(Xtrn_fctr)
        Xtst_nmf[i,:] = Xtst_res.basis()
        if (i%10000 == 0): print(file_name + ': \t iter ' + str(i))
    
    """
    Xtrn_sm = Xtrn_res.summary()
    Xtst_sm = Xtst_res.summary()
    print(file_name + ': \t\t RSS \t Explained Var \t Iters')
    print(file_name + ': Xtrn: \t' + str(Xtrn_sm['rss']) + '\t' +
          str(Xtrn_sm['evar']) + '\t' + str(Xtrn_sm['n_iter']))
    print(file_name + ': Xtst: ' + str(Xtst_sm['rss']) + '\t' +
          str(Xtst_sm['evar']) + '\t' + str(Xtst_sm['n_iter']))
    """
    
    return (Xtrn_nmf, Xtst_nmf)

 def run(self, **params):
     if not self.dataConsolided:
         print "NIMFA_SNMNMF: preparing data"     
         self.consolideTheData()         
         self.dataConsolided = True
     print "NIMFA_SNMNMF: starting"     
     #        
     V  = self.miRNA.as_matrix()
     V1 = self.mRNA.as_matrix()
     A  = csr_matrix(self.gene2gene)
     B  = csr_matrix(self.miRNA2gene)
     
     fctr = nimfa.mf(target = (V, V1),
                   seed = params['seed'], # e.g., "random_c", 
                   rank = params['rank'], # e.g., 50, 
                   method = "snmnmf", 
                   max_iter = params['max_iter'], # e.g., 500, 
                   initialize_only = True,
                   A = A ,
                   B = B,               
                   n_run = 3,
                   gamma = self.g1,
                   gamma_1 = self.g2,
                   lamb = self.l1,
                   lamb_1 = self.l2)
     fctr_res = nimfa.mf_run(fctr)
     print "NIMFA_SNMNMF: done"     
     # extract the results
     self.W =  DataFrame(fctr_res.basis(), index = self.miRNA.index)        
     self.H1_miRNA = DataFrame(fctr_res.coef(0), columns = self.miRNA.columns)
     self.H2_genes = DataFrame(fctr_res.coef(1), columns = self.mRNA.columns)
     self.performance = NIMFA_SNMNMFPerformance(fctr_res)

def run_bd(V):
    """
    Run Bayesian decomposition.
    
    :param V: Target matrix to estimate.
    :type V: :class:`numpy.matrix`
    """
    rank = 10
    model = nimfa.mf(V, 
                  seed = "random_c", 
                  rank = rank, 
                  method = "bd", 
                  max_iter = 12, 
                  initialize_only = True,
                  alpha = np.mat(np.zeros((V.shape[0], rank))),
                  beta = np.mat(np.zeros((rank, V.shape[1]))),
                  theta = .0,
                  k = .0,
                  sigma = 1., 
                  skip = 100,
                  stride = 1,
                  n_w = np.mat(np.zeros((rank, 1))),
                  n_h = np.mat(np.zeros((rank, 1))),
                  n_sigma = False)
    fit = nimfa.mf_run(model)
    print_info(fit)

def factorization(V, rank=4):
    """
    use nmf to factorize V
    :rtype : (1) the projection matrix (2) the feature vector of V
    """
    fctr = nimfa.mf(
        V,
        method="nmf",
        max_iter=30,
        rank=rank,
        update="divergence",
        objective="div",
        callback_init=init_info,
        callback=init_info,
    )
    fctr_res = nimfa.mf_run(fctr)
    print "calculate generized inverse"
    projection = pinv(fctr_res.basis().todense())
    print "inverse finished"
    return {
        "projection": projection,
        "feature": (projection * V),
        "basis": fctr_res.basis(),
        "coef": fctr_res.coef().todense(),
    }

    def nmfMatrix(self, V):
        print "---"
        print "NMF"
        print "---"

        V = np.array(V)
        print "Target matrix"
        print V

        fctr = nimfa.mf(V, seed = 'random_vcol', method = 'lsnmf', rank = 40, max_iter = 10)
        fctr_res = nimfa.mf_run(fctr)


        W = fctr_res.basis()
        print "Basis matrix"
        print W
        H = fctr_res.coef()
        print "Coef"
        print H

        print "Estimate"
        print np.dot(W, H)

        print 'Rss: %5.4f' % fctr_res.fit.rss()
        print 'Evar: %5.4f' % fctr_res.fit.evar()
        print 'K-L divergence: %5.4f' % fctr_res.distance(metric = 'kl')
        print 'Sparseness, W: %5.4f, H: %5.4f' % fctr_res.fit.sparseness()

        return W, H

def factorize(V):
    """
    Perform SNMF/R factorization on the sparse MovieLens data matrix. 
    
    Return basis and mixture matrices of the fitted factorization model. 
    
    :param V: The MovieLens data matrix. 
    :type V: `scipy.sparse.csr_matrix`
    """
    model = nimfa.mf(V,
                     seed="random_vcol",
                     rank=12,
                     method="snmf",
                     max_iter=15,
                     initialize_only=True,
                     version='r',
                     eta=1.,
                     beta=1e-4,
                     i_conv=10,
                     w_min_change=0)
    print "Performing %s %s %d factorization ..." % (model, model.seed, model.rank)
    fit = nimfa.mf_run(model)
    print "... Finished"
    sparse_w, sparse_h = fit.fit.sparseness()
    print """Stats:
            - iterations: %d
            - Euclidean distance: %5.3f
            - Sparseness basis: %5.3f, mixture: %5.3f""" % (fit.fit.n_iter, fit.distance(metric='euclidean'), sparse_w, sparse_h)
    return fit.basis(), fit.coef()

def run_snmnmf(V, V1):
    """
    Run sparse network-regularized multiple NMF. 
    
    :param V: First target matrix to estimate.
    :type V: :class:`numpy.matrix`
    :param V1: Second target matrix to estimate.
    :type V1: :class:`numpy.matrix`
    """
    rank = 10
    model = nimfa.mf(target = (V, V1), 
                  seed = "random_c", 
                  rank = rank, 
                  method = "snmnmf", 
                  max_iter = 12, 
                  initialize_only = True,
                  A = abs(sp.rand(V1.shape[1], V1.shape[1], density = 0.7, format = 'csr')),
                  B = abs(sp.rand(V.shape[1], V1.shape[1], density = 0.7, format = 'csr')), 
                  gamma = 0.01,
                  gamma_1 = 0.01,
                  lamb = 0.01,
                  lamb_1 = 0.01)
    fit = nimfa.mf_run(model)
    # print all quality measures concerning first target and mixture matrix in multiple NMF
    print_info(fit, idx = 0)
    # print all quality measures concerning second target and mixture matrix in multiple NMF
    print_info(fit, idx = 1)

def factorize(V):
    """
    Perform NMF - Divergence factorization on the sparse Medlars data matrix. 
    
    Return basis and mixture matrices of the fitted factorization model. 
    
    :param V: The Medlars data matrix. 
    :type V: `scipy.sparse.csr_matrix`
    """
    model = nimfa.mf(V, 
                  seed = "random_vcol", 
                  rank = 12, 
                  method = "nmf", 
                  max_iter = 15, 
                  initialize_only = True,
                  update = 'divergence',
                  objective = 'div')
    print "Performing %s %s %d factorization ..." % (model, model.seed, model.rank) 
    fit = nimfa.mf_run(model)
    print "... Finished"
    sparse_w, sparse_h = fit.fit.sparseness()
    print """Stats:
            - iterations: %d
            - KL Divergence: %5.3f
            - Euclidean distance: %5.3f
            - Sparseness basis: %5.3f, mixture: %5.3f""" % (fit.fit.n_iter, fit.distance(), fit.distance(metric = 'euclidean'), sparse_w, sparse_h)
    return fit.basis(), fit.coef()

def factorize(V):
    """
    Perform LSNMF factorization on the ORL faces data matrix. 
    
    Return basis and mixture matrices of the fitted factorization model. 
    
    :param V: The ORL faces data matrix. 
    :type V: `numpy.matrix`
    """
    model = nimfa.mf(V, 
                  seed = "random_vcol",
                  rank = 25, 
                  method = "lsnmf", 
                  max_iter = 50,
                  initialize_only = True,
                  sub_iter = 10,
                  inner_sub_iter = 10, 
                  beta = 0.1,
                  min_residuals = 1e-8)
    print "Performing %s %s %d factorization ..." % (model, model.seed, model.rank) 
    fit = nimfa.mf_run(model)
    print "... Finished"
    print """Stats:
            - iterations: %d
            - final projected gradients norm: %5.3f
            - Euclidean distance: %5.3f""" % (fit.fit.n_iter, fit.distance(), fit.distance(metric = 'euclidean'))
    return fit.basis(), fit.coef()

    def nmfMatrix(self, V, method, rank, maxIter):
        print "---"
        print "NMF"
        print "---"

        V = np.array(V)
        print "Target matrix"
        print V.shape[0]
        print V.shape[1]
        print V
        
        
#         X = sp.rand(V.shape[0], V.shape[1], density=1).tocsr()
        # NMFの際の、基底数やイテレーションの設定
        # rank = 8 
        # maxIter = 2000 
        # method = "snmf"
        
#         init2arizer = nimfa.methods.seeding.random_vcol.Random_vcol()
        initiarizer = nimfa.methods.seeding.random.Random()
        initW, initH = initiarizer.initialize(V, rank, {})

        fctr = nimfa.mf(V, seed = 'random_vcol', method = method, rank = rank, max_iter = maxIter)
        # fctr = nimfa.mf(V, method = "lsnmf", rank = rank, max_iter = maxIter, W = initW, H = initH)
        fctr_res = nimfa.mf_run(fctr)

        W = fctr_res.basis()
        print "Basis matrix"
        print W.shape[0]
        print W.shape[1]
        print W
        H = fctr_res.coef()
        print "Coef"
        print H.shape[0]
        print H.shape[1]
        print H

        print "Estimate"
        print np.dot(W, H)

        print 'Rss: %5.4f' % fctr_res.fit.rss()
        print 'Evar: %5.4f' % fctr_res.fit.evar()
        print 'K-L divergence: %5.4f' % fctr_res.distance(metric = 'kl')
        print 'Sparseness, W: %5.4f, H: %5.4f' % fctr_res.fit.sparseness()

        sm = fctr_res.summary()
        print type(sm)
        # print "Rss: %8.3f" % sm['rss']
        # # Print explained variance.
        # print "Evar: %8.3f" % sm['evar']
        # # Print actual number of iterations performed
        # print "Iterations: %d" % sm['n_iter']

        # プロットの際に不具合が生じるため,numpy.ndarray型に変換
        NW = np.asarray(W)
        NH = np.asarray(H)
        return NW, NH, sm

    def _NIMFA_NMF(self, X, nBases):

        model = nimfa.mf(X, seed="nndsvd", rank=nBases, method="nmf", initialize_only=True)

        fit = nimfa.mf_run(model)
        W = fit.basis()
        H = fit.coef()

        self.W = W.todense()
        self.H = H.todense()
        return (self.W, self.H)

def _factorize(matrix):
    "Factorize the matrix to get pc"
    # Build the model
    model = mf(matrix,
               seed="random_vcol",
               rank=15,
               method="nmf",
               max_iter=15,
               initialize_only=True,
               update='divergence',
               objective='div')
    # Then fit it
    fit = mf_run(model)
    return fit.basis(), fit.coef()

def max_guess_select(ratings, users, rank=9, user=None):
    matrix = sp.dok_matrix((len(users), len(users)))
    for k, v in ratings.items():
        matrix[users[k[0]], users[k[1]]] = v
        matrix[users[k[1]], users[k[0]]] = v
    # Run sparse matrix factorisation
    factor = nimfa.mf(matrix, seed="random_c", rank=rank, method="snmf", max_iter=12, initialize_only=True, version='r', eta=1., beta=1e-4, i_conv=10, w_min_change=0)
    result = nimfa.mf_run(factor)
    if user is None:
        # Pick a user to expand
        user = min(users, key=lambda u: len([i for i in ratings if u in i]))
    recommendations = result.fitted()
    rval = max([i for i in users if (i, user) not in ratings and (user, i) not in ratings], key=lambda x: recommendations[users[user], users[x]])
    return user, rval