Python networkx.to_scipy_sparse_matrix函数代码示例

def eig_calc_OLD(G,normalize=None):
    import scipy as sp
    #print '\n\t~~~~~~ eig_calc ~~~~~~'; startTime = datetime.now(); sys.stdout.flush()
    startTime = datetime.now() 
    n = G.number_of_nodes()
    if n == 1:
        eigvec = np.array([1])
    elif n == 2:     # for handling ValueError: k must be less than ndim(A)-1, k=1
        return power_iteration(G,normalize=normalize)
    else:    # the graph contains more than 2 nodes
        A=nx.to_scipy_sparse_matrix(G)
        '''print '--- eig_calc: is sub graph stochastic? ' + str(gm.check_if_stochastic_matrix(nx.to_numpy_matrix(G)))#; sys.stdout.flush()
        print '--- eig_calc: is sub graph strongly connected? ' + str(nx.is_strongly_connected(G))#; sys.stdout.flush()
        print '--- eig_calc: is sub graph aperiodic? ' + str(nx.is_aperiodic(G));# sys.stdout.flush()
        print '--- eig_calc: debug step took: '+str(datetime.now()-tmpTime); tmpTime = datetime.now(); sys.stdout.flush()
        '''
        try:
            eigval,eigvec = sp.sparse.linalg.eigen.arpack.eigs(A.T, k=1, sigma=1, which='LM')
        except RuntimeError:    
            B=nx.to_scipy_sparse_matrix(add_noise(G))
            eigval,eigvec = sp.sparse.linalg.eigen.arpack.eigs(B.T, k=1, sigma=1, which='LM')
        #eigval,eigvec = sp.sparse.linalg.eigen.arpack.eigs(A.T, k=1, which='LM')
        #print '--- eig_calc: eigs took: '+str(datetime.now()-tmpTime); sys.stdout.flush()
        #print '--- eig_calc: sub graph eigval- '+str(eigval)
    eigvec = eigvec/eigvec.sum()
    if normalize:
        norm_factor = float(n)/normalize
        eigvec = eigvec*norm_factor    
    #if (eigvec.imag.sum() != 0. ):
    #    print '##### COMPLEX VECTOR!!!! returning the real part only!!! #####'; #sys.stdout.flush(
    results_dict = dict(zip(G.nodes(),map(float,eigvec.real)))
    if n > 100: print '--- eig_calc: calc of class contains '+str(n)+' nodes, ('+str(float(n)/normalize)+'% of the non-isolates nodes from the graph) took-'+str(datetime.now()-startTime); sys.stdout.flush()
    return results_dict

def gRa(g, w):
    '''w为图中的边数，表示经过减边p扰动后仍然留在数据中的边数'''
    tg = g.copy()
    Rq = nx.to_scipy_sparse_matrix(g)
    Rq = Rq.toarray()

    bw = nx.edge_betweenness_centrality(g, normalized=False)
    norm = sum(bw.values())
    e_num = len(g.edges())

    n = len(g)
    N = (n * (n - 1)) / 2
    for k, v in bw.items():
        g.add_edge(*k, weight=v)
#    print g.edges(data=True)
    R = nx.to_scipy_sparse_matrix(g, weight='weight')
    Rp = R.toarray()

    Rp = w * Rp * 2.0 / Rp.sum()

    q = float(e_num - w) / (N - e_num)

    for i, each in enumerate(Rq):
        for j, e in enumerate(each):
            if e == 0:
                Rp[i, j] = q  # 超级绕采用特别方式在Rp中加入Rq
    for i in range(n):
        Rp[i,i]=0 #去除对角线上的q
    return Rp

 def test_weight_keyword(self):
     WP4 = nx.Graph()
     WP4.add_edges_from((n, n + 1, dict(weight=0.5, other=0.3)) for n in range(3))
     P4 = path_graph(4)
     A = nx.to_scipy_sparse_matrix(P4)
     np_assert_equal(A.todense(), nx.to_scipy_sparse_matrix(WP4, weight=None).todense())
     np_assert_equal(0.5 * A.todense(), nx.to_scipy_sparse_matrix(WP4).todense())
     np_assert_equal(0.3 * A.todense(), nx.to_scipy_sparse_matrix(WP4, weight="other").todense())

def dists(G, nbunch = None):
    
    G = G.copy()
    
    if nbunch is None:
        nbunch = G.nodes()
    
    try:
        out_degree = G.out_degree(nbunch = nbunch)
        in_degree = G.in_degree(nbunch = nbunch)
        gross_out_weight = G.out_degree(weighted = True, nbunch = nbunch)
        gross_in_weight = G.in_degree(weighted = True, nbunch = nbunch)

    except TypeError:
        out_degree = G.out_degree(nbunch = nbunch)
        in_degree = G.in_degree(nbunch = nbunch)
        gross_out_weight = G.out_degree(weight = 'weight', nbunch = nbunch)
        gross_in_weight = G.in_degree(weight = 'weight', nbunch = nbunch)

        
    A = nx.to_scipy_sparse_matrix(G, nodelist = nbunch)
    i, j, grosscells = extract.find(A)

    selfloops = G.selfloop_edges(data = True)
    G.remove_edges_from(selfloops)
    
    
    try:
        net_out_weight = G.out_degree(weighted = True, nbunch = nbunch)
        net_in_weight = G.in_degree(weighted = True, nbunch = nbunch)

    except TypeError:
        net_out_weight = G.out_degree(weight = 'weight', nbunch = nbunch)
        net_in_weight = G.in_degree(weight = 'weight', nbunch = nbunch)


    A = nx.to_scipy_sparse_matrix(G, nodelist = nbunch)
    i, j, netcells = extract.find(A)

    dists = {
    'out-degree': 
    np.array([out_degree[i] for i in nbunch],dtype = np.float32), 
    'in-degree': 
    np.array([in_degree[i] for i in nbunch],dtype = np.float32), 
    'gross_out-weight': 
    np.array([gross_out_weight[i] for i in nbunch],dtype = np.float32), 
    'gross_in-weight': 
    np.array([gross_in_weight[i] for i in nbunch],dtype = np.float32),  
    'net_out-weight': 
    np.array([net_out_weight[i] for i in nbunch],dtype = np.float32), 
    'net_in-weight': 
    np.array([net_in_weight[i] for i in nbunch],dtype = np.float32),  
    'gross_cells': grosscells,
    'net_cells': netcells
    }
    
    return dists

def to_sparse( G ):
    """
    DiGraph to scipy sparse matrix.
    """
    try:
        return nx.to_scipy_sparse_matrix( G.graph, dtype=int, format='csr' )
    # in case one sends in G.graph instead.
    except AttributeError:
        return nx.to_scipy_sparse_matrix( G, dtype=int, format='csr' )        

def eig_calc(G,normalize=None,nstart_norm=None):
    '''
    Calculates the dominant eigenvector of graph (the one related to eigenvector = 1). 
    Parameters
    ----------
        G - networkx directed graph, the strongly connected component (subGraph) in our case
        normalized - int, the number of nodes in the original (entire) graph- for normlizing the resulted eigenvector as per the proportion of the component from the entire (original) graph
        nstart_norm - float, the weight [0,1] for normalizing the resulted eigenvector (for referring the risk proportion of the component from the entire (original) graph).
        *NOTE: normalize and nstart_norm cannot come together!! only one of them can be different from None!
    Returns
    -------
        results_dict - a dict of the (normalized) dominant eigenvector (the keys are G nodes names- basically integer)
    '''
    import scipy as sp
    #print '\n\t~~~~~~ eig_calc ~~~~~~'; startTime = datetime.now(); sys.stdout.flush()
    startTime = datetime.now() 
    n = G.number_of_nodes()
    if n == 1:
        eigvec = np.array([1])
    elif n == 2:     # for handling ValueError: k must be less than ndim(A)-1, k=1
        return power_iteration(G,normalize=normalize,nstart_norm=nstart_norm)
    else:    # the graph contains more than 2 nodes
        A=nx.to_scipy_sparse_matrix(G)
        '''print '--- eig_calc: is sub graph stochastic? ' + str(gm.check_if_stochastic_matrix(nx.to_numpy_matrix(G)))#; sys.stdout.flush()
        print '--- eig_calc: is sub graph strongly connected? ' + str(nx.is_strongly_connected(G))#; sys.stdout.flush()
        print '--- eig_calc: is sub graph aperiodic? ' + str(nx.is_aperiodic(G));# sys.stdout.flush()
        print '--- eig_calc: debug step took: '+str(datetime.now()-tmpTime); tmpTime = datetime.now(); sys.stdout.flush()
        '''
        try:
            eigval,eigvec = sp.sparse.linalg.eigen.arpack.eigs(A.T, k=1, sigma=1, which='LM')
        except RuntimeError:    
            B=nx.to_scipy_sparse_matrix(add_noise(G))
            eigval,eigvec = sp.sparse.linalg.eigen.arpack.eigs(B.T, k=1, sigma=1, which='LM')
        #eigval,eigvec = sp.sparse.linalg.eigen.arpack.eigs(A.T, k=1, which='LM')
        #print '--- eig_calc: eigs took: '+str(datetime.now()-tmpTime); sys.stdout.flush()
        #print '--- eig_calc: sub graph eigval- '+str(eigval)
    eigvec = eigvec/eigvec.sum()
    if normalize:
        norm_factor = float(n)/normalize
        eigvec = eigvec*norm_factor  
        
        if n > 100: print '--- eig_calc: calc of class contains ',n,' nodes, (',float(n)/normalize,'% of the non-isolates nodes from the graph) took-',datetime.now()-startTime; sys.stdout.flush()
    
    elif nstart_norm != None:
        eigvec = eigvec*nstart_norm
        
        if n > 100: print '--- eig_calc: calc of class contains ',n,' nodes, took-',datetime.now()-startTime; sys.stdout.flush()
    #if (eigvec.imag.sum() != 0. ):
    #    print '##### COMPLEX VECTOR!!!! returning the real part only!!! #####'; #sys.stdout.flush(
    results_dict = dict(zip(G.nodes(),map(float,eigvec.real)))
    
    return results_dict

def mypr(G, alpha=0.85, personalization=None,
       max_iter=100, tol=1.0e-6, weight='weight'):

    nodelist=G.nodes()
    M=nx.to_scipy_sparse_matrix(G,nodelist=nodelist,weight=weight)
    (n,m)=M.shape # should be square

    S = scipy.array(M.sum(axis=1))
    S[S>0] = 1.0 / S[S>0]
    Sm = scipy.sparse.lil_matrix((n,n))
    Sm.setdiag(S.flat)
    Sm = Sm.tocsr()
    M = Sm * M

    ## Q = scipy.sparse.spdiags(S.T, 0, *M.shape, format='csr')
    ## M = Q * M
    
    x=scipy.ones((n))/n  # initial guess
    dangle=scipy.array(scipy.where(M.sum(axis=1)==0,1.0/n,0)).flatten()
    # add "teleportation"/personalization
    v=x
    i=0
    while i <= max_iter:
        # power iteration: make up to max_iter iterations
        xlast=x
        x=alpha*(x*M+scipy.dot(dangle,xlast))+(1-alpha)*v
        x=x/x.sum()
        # check convergence, l1 norm            
        err=scipy.absolute(x-xlast).sum()
        if err < n*tol:
            r = dict(zip(nodelist,x))
            return r
        i+=1
    
    print 'Failed to converge'

def modularity_matrix(G, nodelist=None, weight=None):
    """Return the modularity matrix of G.

    The modularity matrix is the matrix B = A - <A>, where A is the adjacency
    matrix and <A> is the average adjacency matrix, assuming that the graph
    is described by the configuration model.

    More specifically, the element B_ij of B is defined as
        A_ij - k_i k_j / 2 * m
    where k_i(in) is the degree of node i, and were m is the number of edges
    in the graph. When weight is set to a name of an attribute edge, Aij, k_i, 
    k_j and m are computed using its value. 

    Parameters
    ----------
    G : Graph
       A NetworkX graph

    nodelist : list, optional
       The rows and columns are ordered according to the nodes in nodelist.
       If nodelist is None, then the ordering is produced by G.nodes().
    
    weight : string or None, optional (default=None)
       The edge attribute that holds the numerical value used for
       the edge weight.  If None then all edge weights are 1.

    Returns
    -------
    B : Numpy matrix
      The modularity matrix of G.

    Examples
    --------
    >>> import networkx as nx
    >>> k =[3, 2, 2, 1, 0]
    >>> G = nx.havel_hakimi_graph(k)
    >>> B = nx.modularity_matrix(G)


    See Also
    --------
    to_numpy_matrix
    adjacency_matrix
    laplacian_matrix
    directed_modularity_matrix

    References
    ----------
    .. [1] M. E. J. Newman, "Modularity and community structure in networks",
       Proc. Natl. Acad. Sci. USA, vol. 103, pp. 8577-8582, 2006.
    """
    if nodelist is None:
        nodelist = list(G)
    A = nx.to_scipy_sparse_matrix(G, nodelist=nodelist, weight=weight,
                                  format='csr')
    k = A.sum(axis=1)
    m = k.sum() * 0.5
    # Expected adjacency matrix
    X = k * k.transpose() / (2 * m)
    return A - X

    def compute_slice_matrices(self,G):
        #Create node and edge layers
        node_layer = defaultdict(list)
        for n in G.nodes():
            node_layer[n[0]].append(n)

        edge_layer = defaultdict(list)
        for e in G.edges(data=True):
            edge_layer[e[2]['etype']].append(e)

        ALLNTYPES = [ntype for ntype in node_layer] 
        ALLETYPES = [etype for etype in edge_layer]

        #### Transform everything into linear algebra...

        self.OrderedNodes=[]
        for ntype in ALLNTYPES:
            self.OrderedNodes = self.OrderedNodes + node_layer[ntype]
        self.NodeIndex = {}
        for idx,n in enumerate(self.OrderedNodes):
            self.NodeIndex[n]=idx

        #Construct Adjacency Matrices for various slices (single edge type)
        self.AdjMat = {}
        self.Degs = {} # Degre
        #Invdegs = {}
        for etype in ALLETYPES:
            print '--computing slice for edge type "'+etype+'"'
            H = graph_slice(G,etypes=etype)
            self.AdjMat[etype] = nx.to_scipy_sparse_matrix(H,self.OrderedNodes,format='csr')
            self.Degs[etype] = np.array([[max(1,float(H.degree(n)))] for n in self.OrderedNodes])

def compute_pagerank(network : nx.DiGraph, damping : float=0.85):
    Adj = nx.to_scipy_sparse_matrix(network, dtype='float', format='csr')
    deg = np.ravel(Adj.sum(axis=1))
    Dinv = sparse.diags(1 / deg)
    Trans = (Dinv @ Adj).T
    pr = pagerank_power(Trans, damping=damping)
    return pr

def main111():
  if 1:
    G = nx.read_edgelist(infname)
    print nx.info(G)
    # Graph adj matix
    A = nx.to_scipy_sparse_matrix(G)
    print type(A)
    from scipy import sparse, io
    io.mmwrite("Results/test.mtx", A)
    exit()
    # write to disk clustering coeffs for this graph
    snm.get_clust_coeff([G], 'orig', 'mmonth')
    # write to disk egienvalue
    snm.network_value_distribution([G], [], 'origMmonth')

  if 0:
    edgelist = np.loadtxt(infname, dtype=str, delimiter='\t')
    print edgelist[:4]
    idx = np.arange(len(edgelist))
    np.random.shuffle(idx)
    subsamp_edgelist = edgelist[idx[:100]]
    G = nx.Graph()
    G.add_edges_from([(long(x), long(y)) for x, y in subsamp_edgelist])

  # visualize this graph
  # visualize_graph(G)
  exit()

  G = nx.Graph()
  G.add_edges_from([(long(x), long(y)) for x, y in edgelist])
  print nx.info(G)
  print 'Done'

def unroll_adjacency_matrix(G):
    '''"Unrolls" the adjacency matrix of the input graph into a vector. This
    is done by extracting all off-diagonal elements of the nxn adjacency matrix
    and concatenating them into an n(n - 1)/2 dimensional array.
    Example:
    [[0, 1, 0],
     [1, 0, 1],
     [0, 1, 0]]
     gives [1, 0, 1].'''

    # Number of nodes in the graph
    n = len(G)
    # Length of the unrolled matrix
    dim = n*(n - 1)//2
    # Sparse matrix to hold the results
    result = sp.sparse.lil_matrix((1, dim))
    # Adjacency matrix for the graph
    M = nx.to_scipy_sparse_matrix(G, format = "coo")

    for i,j,v in zip(M.row, M.col, M.data):
        # Only care about northeastern corner of the matrix
        if not j > i:
            continue
        ind = i*n - (i*(i+1))//2 + j - i - 1 # Nothing to see here, move along.
        # Add the encountered element at the appropriate index of result
        result[0, ind] = v
    
    return result

def page_rank_scipy(G,alpha=0.85,max_iter=100,tol=1.0e-4,nodelist=None):
    """Return a numpy array of the PageRank of G.
    
    PageRank computes the largest eigenvector of the stochastic
    adjacency matrix of G.

    The eigenvector calculation is done by the power iteration method
    and has no guarantee of convergence.   

    A starting vector for the power iteration can be given in the
    dictionary nstart.

    This implementation requires scipy.

    """
    import scipy.sparse
    M=NX.to_scipy_sparse_matrix(G,nodelist=nodelist)
    (n,m)=M.shape # should be square
    S=scipy.array(M.sum(axis=1)).flatten()
    index=scipy.where(S<>0)[0]
    for i in index:
        M[i,:]*=1.0/S[i]
    x=scipy.ones((n))/n  # initial guess
    dangle=scipy.array(scipy.where(M.sum(axis=1)==0,1.0/n,0)).flatten()
    for i in range(max_iter):
        xlast=x
        x=alpha*(M.rmatvec(x)+scipy.dot(dangle,xlast))+(1-alpha)*xlast.sum()/n
        # check convergence, l1 norm            
        err=scipy.absolute(x-xlast).sum()
        if err < n*tol:
            return x

    raise NetworkXError("page_rank: power iteration failed to converge in %d iterations."%(i+1))

def r_perturbSa(g,p=None):
    '''固定参数的随机扰动方法，p伯努利实验成功的概率'''
    A=nx.to_scipy_sparse_matrix(g)
    B=sparse.triu(A).toarray()
    #print B
    n=len(g)
    e_num=len(g.edges())#图中存在的边数

    q = e_num * (1 - p) / ((n * (n - 1)) / 2 - e_num)
    #print q
    i = 0
    ts=0
    listp=stats.bernoulli.rvs(p,size=e_num)
    listp=listp.tolist()
    listq=stats.bernoulli.rvs(q,size=(n * (n - 1)) / 2 - e_num)
    listq=listq.tolist()

    while i<n:
        j=i+1#略过对角线上的0
        while j<n:
            if(B[i,j]==1):
                B[i,j] = listp.pop()#参数p伯努利实验成功的概率
                #ts=ts + 1
                # print "+",ts, ":", i, ",", j, ",", B[i, j]
            else:
                B[i,j] = listq.pop()#参数q伯努利实验成功的概率
                #ts=ts + 1
                # print "-",ts, ":", i, ",", j, ",", B[i, j]
            j = j + 1
        i=i+1

    return nx.from_numpy_matrix(B,create_using=nx.Graph())#重新构建了Graph类型的返回对象

def r_perturbR(g,R):
    '''可变参数的随机扰动方法'''
    A=nx.to_scipy_sparse_matrix(g)
    B=sparse.triu(A).toarray()
    #print B
    n=len(g)
    i = 0
    ts=0

    while i<n:
        j=i+1
        while j<n:
            if(B[i,j]==1):
                if R[i,j]<1:
                    B[i,j] = stats.bernoulli.rvs(R[i,j])#参数p伯努利实验成功的概率
                else:
                    B[i, j] = stats.bernoulli.rvs(1)  #其实可以去掉
                ts=ts + 1
                #print "+",ts, ":", i, ",", j, ",", B[i, j]
            else:
                if R[i,j]<1:
                    B[i,j] = stats.bernoulli.rvs(R[i,j])#参数q伯努利实验成功的概率
                else:
                    B[i, j] = stats.bernoulli.rvs(0)  #其实可以去掉
                ts=ts + 1
                #print "-",ts, ":", i, ",", j, ",", B[i, j]
            j = j + 1
        i=i+1

    return nx.from_numpy_matrix(B,create_using=nx.Graph())#重新构建了Graph类型的返回对象