utils.py

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 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 features.todense(), sparse_to_tuple(features)

def adj_to_bias(adj, sizes, nhood=1):
    nb_graphs = adj.shape[0]
    mt = np.empty(adj.shape)
    for g in range(nb_graphs):
        mt[g] = np.eye(adj.shape[1])
        for _ in range(nhood):
            mt[g] = np.matmul(mt[g], (adj[g] + np.eye(adj.shape[1])))
        for i in range(sizes[g]):
            for j in range(sizes[g]):
                if mt[g][i][j] > 0.0:
                    mt[g][i][j] = 1.0
    return -1e9 * (1.0 - mt)

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): # {'pubmed', 'citeseer', '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)

    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, :]

    #pytorch的标签不需要进行one-hot编码
    my_labels = np.where(labels==1)[1]
    idx_test = test_idx_range.tolist()
    idx_train = range(len(y))
    idx_val = range(len(y), len(y)+500)

    train_my_labels_mask = sample_mask(idx_train, my_labels.shape[0])
    val_my_labels_mask = sample_mask(idx_val, my_labels.shape[0])
    test_my_labels_mask = sample_mask(idx_test, my_labels.shape[0])
    train_my_labels = my_labels[train_my_labels_mask]
    val_my_labels = my_labels[val_my_labels_mask]
    test_my_labels = my_labels[test_my_labels_mask]

    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, :]

    print(adj.shape)
    print(features.shape)
    data_dict = {
      'adj': adj,
      'features': features,
      'y_train': y_train,
      'y_val': y_val,
      'y_test': y_test,
      'train_mask': train_mask,
      'val_mask': val_mask,
      'test_mask': test_mask,
      'train_my_labels': train_my_labels,
      'val_my_labels': val_my_labels,
      'test_my_labels': test_my_labels,
      'my_labels': my_labels
    }
    return data_dict