GCN图卷积 utils.py脚本

GCN图卷积 utils.py脚本
把带#注释掉的部分取消,打印一些数据,就能理解GCN是怎么处理数据的,也有助于将自己的数据转变成与它类似的形式。

import numpy as np
import pickle as pkl
import networkx as nx
import scipy.sparse as sp
from scipy.sparse.linalg.eigen.arpack import eigsh
import sys


def parse_index_file(filename):
    """Parse index file."""
    index = []
    for line in open(filename):
        index.append(int(line.strip()))
    return index


def sample_mask(idx, l):
    """Create mask."""
    mask = np.zeros(l)
    mask[idx] = 1
    return np.array(mask, dtype=np.bool)


def load_data(dataset_str):
    """
    Loads input data from gcn/data directory

    ind.dataset_str.x => the feature vectors of the training instances as scipy.sparse.csr.csr_matrix object;
    ind.dataset_str.tx => the feature vectors of the test instances as scipy.sparse.csr.csr_matrix object;
    ind.dataset_str.allx => the feature vectors of both labeled and unlabeled training instances
        (a superset of ind.dataset_str.x) as scipy.sparse.csr.csr_matrix object;
    ind.dataset_str.y => the one-hot labels of the labeled training instances as numpy.ndarray object;
    ind.dataset_str.ty => the one-hot labels of the test instances as numpy.ndarray object;
    ind.dataset_str.ally => the labels for instances in ind.dataset_str.allx as numpy.ndarray object;
    ind.dataset_str.graph => a dict in the format {index: [index_of_neighbor_nodes]} as collections.defaultdict
        object;
    ind.dataset_str.test.index => the indices of test instances in graph, for the inductive setting as list object.

    All objects above must be saved using python pickle module.

    :param dataset_str: Dataset name
    :return: All data input files loaded (as well the training/test data).
    """
    names = ['x', 'y', 'tx', 'ty', 'allx', 'ally', 'graph']
    objects = []
    for i in range(len(names)):
        with open("data/ind.{}.{}".format(dataset_str, names[i]), 'rb') as f:
            if sys.version_info > (3, 0):
                data = pkl.load(f, encoding='latin1')
                # if(names[i].find('graph')==-1):
                #     print(f)
                #     print(data.shape)
                #     for j in range(data.shape[0]):
                #         print('********',names[i],j,data[j].shape,'**********')
                #         print(data[j])
                # else:
                #     print(f)
                #     print(data)
                objects.append(data)

            else:
                objects.append(pkl.load(f))

    x, y, tx, ty, allx, ally, graph = tuple(objects)

    #测试数据集
    # print(x[0][0],x.shape,type(x))  ##x是一个稀疏矩阵,记住1的位置,140个实例,每个实例的特征向量维度是1433  (140,1433)
    # print(y[0],y.shape)   ##y是标签向量,7分类,140个实例 (140,7)

    ##训练数据集
    # print(tx[0][0],tx.shape,type(tx))  ##tx是一个稀疏矩阵,1000个实例,每个实例的特征向量维度是1433  (1000,1433)
    # print(ty[0],ty.shape)   ##y是标签向量,7分类,1000个实例 (1000,7)

    ##allx,ally和上面的形式一致
    # print(allx[0][0],allx.shape,type(allx))  ##tx是一个稀疏矩阵,1708个实例,每个实例的特征向量维度是1433  (1708,1433)
    # print(ally[0],ally.shape)   ##y是标签向量,7分类,1708个实例 (1708,7)


    ##graph是一个字典,大图总共2708个节点
    # for i in graph:
    #     print(i,graph[i])


    test_idx_reorder = parse_index_file("data/ind.{}.test.index".format(dataset_str))
    test_idx_range = np.sort(test_idx_reorder)

    # print(test_idx_range)

    if dataset_str == 'citeseer':
        # Fix citeseer dataset (there are some isolated nodes in the graph)
        # Find isolated nodes, add them as zero-vecs into the right position
        test_idx_range_full = range(min(test_idx_reorder), max(test_idx_reorder)+1)
        tx_extended = sp.lil_matrix((len(test_idx_range_full), x.shape[1]))
        tx_extended[test_idx_range-min(test_idx_range), :] = tx
        tx = tx_extended
        ty_extended = np.zeros((len(test_idx_range_full), y.shape[1]))
        ty_extended[test_idx_range-min(test_idx_range), :] = ty
        ty = ty_extended

    features = sp.vstack((allx, tx)).tolil()
    features[test_idx_reorder, :] = features[test_idx_range, :]
    adj = nx.adjacency_matrix(nx.from_dict_of_lists(graph))
    # print(adj,adj.shape)

    labels = np.vstack((ally, ty))
    labels[test_idx_reorder, :] = labels[test_idx_range, :]

    idx_test = test_idx_range.tolist()
    idx_train = range(len(y))
    idx_val = range(len(y), len(y)+500)

    train_mask = sample_mask(idx_train, labels.shape[0])
    val_mask = sample_mask(idx_val, labels.shape[0])
    test_mask = sample_mask(idx_test, labels.shape[0])

    y_train = np.zeros(labels.shape)
    y_val = np.zeros(labels.shape)
    y_test = np.zeros(labels.shape)
    y_train[train_mask, :] = labels[train_mask, :]
    y_val[val_mask, :] = labels[val_mask, :]
    y_test[test_mask, :] = labels[test_mask, :]
    

    return adj, features, y_train, y_val, y_test, train_mask, val_mask, test_mask


def sparse_to_tuple(sparse_mx):
    """Convert sparse matrix to tuple representation."""
    def to_tuple(mx):
        if not sp.isspmatrix_coo(mx):
            mx = mx.tocoo()
        coords = np.vstack((mx.row, mx.col)).transpose()
        values = mx.data
        shape = mx.shape
        return coords, values, shape

    if isinstance(sparse_mx, list):
        for i in range(len(sparse_mx)):
            sparse_mx[i] = to_tuple(sparse_mx[i])
    else:
        sparse_mx = to_tuple(sparse_mx)

    return sparse_mx


def preprocess_features(features):
    """Row-normalize feature matrix and convert to tuple representation"""
    rowsum = np.array(features.sum(1))
    r_inv = np.power(rowsum, -1).flatten()
    r_inv[np.isinf(r_inv)] = 0.
    r_mat_inv = sp.diags(r_inv)
    features = r_mat_inv.dot(features)
    return sparse_to_tuple(features)


def normalize_adj(adj):
    """Symmetrically normalize adjacency matrix."""
    adj = sp.coo_matrix(adj)
    rowsum = np.array(adj.sum(1))
    d_inv_sqrt = np.power(rowsum, -0.5).flatten()
    d_inv_sqrt[np.isinf(d_inv_sqrt)] = 0.
    d_mat_inv_sqrt = sp.diags(d_inv_sqrt)
    return adj.dot(d_mat_inv_sqrt).transpose().dot(d_mat_inv_sqrt).tocoo()


def preprocess_adj(adj):
    """Preprocessing of adjacency matrix for simple GCN model and conversion to tuple representation."""
    adj_normalized = normalize_adj(adj + sp.eye(adj.shape[0]))
    return sparse_to_tuple(adj_normalized)


def construct_feed_dict(features, support, labels, labels_mask, placeholders):
    """Construct feed dictionary."""
    feed_dict = dict()
    feed_dict.update({placeholders['labels']: labels})
    feed_dict.update({placeholders['labels_mask']: labels_mask})
    feed_dict.update({placeholders['features']: features})
    feed_dict.update({placeholders['support'][i]: support[i] for i in range(len(support))})
    feed_dict.update({placeholders['num_features_nonzero']: features[1].shape})
    return feed_dict


def chebyshev_polynomials(adj, k):
    """Calculate Chebyshev polynomials up to order k. Return a list of sparse matrices (tuple representation)."""
    print("Calculating Chebyshev polynomials up to order {}...".format(k))

    adj_normalized = normalize_adj(adj)
    laplacian = sp.eye(adj.shape[0]) - adj_normalized
    largest_eigval, _ = eigsh(laplacian, 1, which='LM')
    scaled_laplacian = (2. / largest_eigval[0]) * laplacian - sp.eye(adj.shape[0])

    t_k = list()
    t_k.append(sp.eye(adj.shape[0]))
    t_k.append(scaled_laplacian)

    def chebyshev_recurrence(t_k_minus_one, t_k_minus_two, scaled_lap):
        s_lap = sp.csr_matrix(scaled_lap, copy=True)
        return 2 * s_lap.dot(t_k_minus_one) - t_k_minus_two

    for i in range(2, k+1):
        t_k.append(chebyshev_recurrence(t_k[-1], t_k[-2], scaled_laplacian))

    return sparse_to_tuple(t_k)


load_data('cora')
©著作权归作者所有,转载或内容合作请联系作者
  • 序言:七十年代末,一起剥皮案震惊了整个滨河市,随后出现的几起案子,更是在滨河造成了极大的恐慌,老刑警刘岩,带你破解...
    沈念sama阅读 214,904评论 6 497
  • 序言:滨河连续发生了三起死亡事件,死亡现场离奇诡异,居然都是意外死亡,警方通过查阅死者的电脑和手机,发现死者居然都...
    沈念sama阅读 91,581评论 3 389
  • 文/潘晓璐 我一进店门,熙熙楼的掌柜王于贵愁眉苦脸地迎上来,“玉大人,你说我怎么就摊上这事。” “怎么了?”我有些...
    开封第一讲书人阅读 160,527评论 0 350
  • 文/不坏的土叔 我叫张陵,是天一观的道长。 经常有香客问我,道长,这世上最难降的妖魔是什么? 我笑而不...
    开封第一讲书人阅读 57,463评论 1 288
  • 正文 为了忘掉前任,我火速办了婚礼,结果婚礼上,老公的妹妹穿的比我还像新娘。我一直安慰自己,他们只是感情好,可当我...
    茶点故事阅读 66,546评论 6 386
  • 文/花漫 我一把揭开白布。 她就那样静静地躺着,像睡着了一般。 火红的嫁衣衬着肌肤如雪。 梳的纹丝不乱的头发上,一...
    开封第一讲书人阅读 50,572评论 1 293
  • 那天,我揣着相机与录音,去河边找鬼。 笑死,一个胖子当着我的面吹牛,可吹牛的内容都是我干的。 我是一名探鬼主播,决...
    沈念sama阅读 39,582评论 3 414
  • 文/苍兰香墨 我猛地睁开眼,长吁一口气:“原来是场噩梦啊……” “哼!你这毒妇竟也来了?” 一声冷哼从身侧响起,我...
    开封第一讲书人阅读 38,330评论 0 270
  • 序言:老挝万荣一对情侣失踪,失踪者是张志新(化名)和其女友刘颖,没想到半个月后,有当地人在树林里发现了一具尸体,经...
    沈念sama阅读 44,776评论 1 307
  • 正文 独居荒郊野岭守林人离奇死亡,尸身上长有42处带血的脓包…… 初始之章·张勋 以下内容为张勋视角 年9月15日...
    茶点故事阅读 37,087评论 2 330
  • 正文 我和宋清朗相恋三年,在试婚纱的时候发现自己被绿了。 大学时的朋友给我发了我未婚夫和他白月光在一起吃饭的照片。...
    茶点故事阅读 39,257评论 1 344
  • 序言:一个原本活蹦乱跳的男人离奇死亡,死状恐怖,灵堂内的尸体忽然破棺而出,到底是诈尸还是另有隐情,我是刑警宁泽,带...
    沈念sama阅读 34,923评论 5 338
  • 正文 年R本政府宣布,位于F岛的核电站,受9级特大地震影响,放射性物质发生泄漏。R本人自食恶果不足惜,却给世界环境...
    茶点故事阅读 40,571评论 3 322
  • 文/蒙蒙 一、第九天 我趴在偏房一处隐蔽的房顶上张望。 院中可真热闹,春花似锦、人声如沸。这庄子的主人今日做“春日...
    开封第一讲书人阅读 31,192评论 0 21
  • 文/苍兰香墨 我抬头看了看天上的太阳。三九已至,却和暖如春,着一层夹袄步出监牢的瞬间,已是汗流浃背。 一阵脚步声响...
    开封第一讲书人阅读 32,436评论 1 268
  • 我被黑心中介骗来泰国打工, 没想到刚下飞机就差点儿被人妖公主榨干…… 1. 我叫王不留,地道东北人。 一个月前我还...
    沈念sama阅读 47,145评论 2 366
  • 正文 我出身青楼,却偏偏与公主长得像,于是被迫代替她去往敌国和亲。 传闻我的和亲对象是个残疾皇子,可洞房花烛夜当晚...
    茶点故事阅读 44,127评论 2 352

推荐阅读更多精彩内容