LMIA / node2vec / gae / input_data.py
input_data.py
Raw
import numpy as np
import pickle as pkl
import networkx as nx
import scipy.sparse as sp


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


# Documentation: https://github.com/kimiyoung/planetoid
    # x: the feature vectors of the labeled training instances
    # tx: the feature vectors of the test instances
    # allx: the feature vectors of both labeled and unlabeled training instances (a superset of x)
    # graph: a dict in the format {index: [index_of_neighbor_nodes]}
def load_data(dataset):
    # load the data: x, tx, allx, graph
    names = ['x', 'tx', 'allx', 'graph']
    objects = []
    for i in range(len(names)):
        objects.append(pkl.load(open("data/ind.{}.{}".format(dataset, names[i]))))
    x, tx, allx, graph = tuple(objects)

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

    if dataset == '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

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

    return adj, features