一：
出自：《深入浅出图神经网络》机械工业出版社，刘忠雨、李彦霖、周洋
# 加载数据，并转换为torch.Tensor
dataset = CoraData().data
node_feature = dataset.x / dataset.x.sum(1, keepdims=True) # 归一化数据，使得每一行和为1
tensor_x = tensor_from_numpy(node_feature, DEVICE)
tensor_y = tensor_from_numpy(dataset.y, DEVICE)
tensor_train_mask = tensor_from_numpy(dataset.train_mask, DEVICE)
tensor_val_mask = tensor_from_numpy(dataset.val_mask, DEVICE)
tensor_test_mask = tensor_from_numpy(dataset.test_mask, DEVICE)
normalize_adjacency = CoraData.normalization(dataset.adjacency) # 规范化邻接矩阵
num_nodes, input_dim = node_feature.shape
indices = torch.from_numpy(np.asarray(
[normalize_adjacency.row,
normalize_adjacency.col]).astype('int64')).long()
values = torch.from_numpy(normalize_adjacency.data.astype(np.float32))
tensor_adjacency = torch.sparse.FloatTensor(indices, values,
(num_nodes, num_nodes)).to(DEVICE)
out：
Process data ...
Node's feature shape: (2708, 1433)
Node's label shape: (2708,)
Adjacency's shape: (2708, 2708)
Number of training nodes: 140
Number of validation nodes: 500
Number of test nodes: 1000
Cached file: cora/processed_cora.pkl
二. gcn里的
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):
objects.append(pkl.load(f, encoding='latin1'))
else:
objects.append(pkl.load(f))
x, y, tx, ty, allx, ally, graph = tuple(objects)
test_idx_reorder = parse_index_file("data/ind.{}.test.index".format(dataset_str))
test_idx_range = np.sort(test_idx_reorder)
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))
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)
三. 百度网盘里
输入：7个文件的
import sys
import pickle as pkl
import networkx as nx
import numpy as np
import scipy.sparse as sp
def load_data(dataset_str = 'cora'):
"""Load 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):
objects.append(pkl.load(f, encoding='latin1'))
else:
objects.append(pkl.load(f))
x, y, tx, ty, allx, ally, graph = tuple(objects)
test_idx_reorder = parse_index_file("data/ind.{}.test.index".format(dataset_str))
test_idx_range = np.sort(test_idx_reorder)
features = sp.vstack((allx, tx)).tolil()
features[test_idx_reorder, :] = features[test_idx_range, :]
# normalize
features = normalize(features)
adj = nx.adjacency_matrix(nx.from_dict_of_lists(graph))
# build symmetric adjacency matrix
adj = adj + adj.T.multiply(adj.T > adj) - adj.multiply(adj.T > adj)
# network_emb = pros(adj)
# network_emb = 0
labels = np.vstack((ally, ty))
labels[test_idx_reorder, :] = labels[test_idx_range, :] # onehot
idx_train = range(len(y)) # training data index
idx_val = range(len(y), len(y)+500) # validation data index
idx_test = test_idx_range.tolist() # test data index
features = np.array(features.todense())
return adj, features, labels, idx_train, idx_val, idx_test
def parse_index_file(filename):
"""Parse index file."""
index = []
for line in open(filename):
index.append(int(line.strip()))
return index
def normalize(mx):
"""Row-normalize sparse matrix"""
rowsum = np.array(mx.sum(1))
r_inv = np.power(rowsum, -1).flatten()
r_inv[np.isinf(r_inv)] = 0.
r_mat_inv = sp.diags(r_inv)
mx = r_mat_inv.dot(mx)
return mx
if __name__ == '__main__':
adj, features, labels, idx_train, idx_val, idx_test = load_data('cora')
print('adj shape', adj.shape) # adjacency matrix with Shape(2708, 2708)
print('feature shape', features.shape) # feature matrix, Shape(2708, 1433)
print('label shape', labels.shape) #label matrix, Shape(2708, 7)
print('train/validation/test split: %s/%s/%s'%(len(idx_train), len(idx_val), len(idx_test)) )
数据集介绍
Cora数据集由许多机器学习领域的paper构成，这些paper被分为7个类别：
Case_Based
Genetic_Algorithms
Neural_Networks
Probabilistic_Methods
Reinforcement_Learning
Rule_Learning
Theory
在该数据集中，每一篇论文至少引用了该数据集里面另外一篇论文或者被另外一篇论文所引用，数据集总共有2708篇papers。
在消除停词以及除去文档频率小于10的词汇，最终词汇表中有1433个词汇。
数据集文件夹中包含两个文件：
.content文件包含对paper的内容描述，格式为
[公式]
其中,
==> <paper_id>是paper的标识符，每一篇paper对应一个标识符。
==> <word_attributes>是词汇特征，为0或1，表示对应词汇是否存在。
==> <class_label>是该文档所述的类别。
.cites文件包含数据集的引用图(citation graph)，每一行格式如下
[公式]
其中
==> 是被引用的paper标识符。
==> 是引用的paper标识符。
引用的方向是从右向左的，比如有一行为paper1 paper2，那么对应的连接关系是paper2->paper1。