datasets.py

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Authors : Nairouz Mrabah (mrabah.nairouz@courrier.uqam.ca) & Mohamed Fawzi Touati (touati.mohamed_fawzi@courrier.uqam.ca)
# @Paper   : Rethinking Graph Autoencoder Models for Attributed Graph Clustering
# @License : MIT License

import numpy as np
import pickle as pkl
import networkx as nx
import scipy.sparse as sp
import torch
import sys


def parse_index_file(filename):
    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,data_path):
    # load the data: x, tx, allx, graph
    names = ['x', 'y', 'tx', 'ty', 'allx', 'ally', 'graph']
    objects = []
    for i in range(len(names)):
        '''
        fix Pickle incompatibility of numpy arrays between Python 2 and 3
        https://stackoverflow.com/questions/11305790/pickle-incompatibility-of-numpy-arrays-between-python-2-and-3
        '''
        with open(data_path+"/ind.{}.{}".format(dataset, names[i]), 'rb') as rf:
            u = pkl._Unpickler(rf)
            u.encoding = 'latin1'
            cur_data = u.load()
            objects.append(cur_data)
    x, y, tx, ty, allx, ally, graph = tuple(objects)
    test_idx_reorder = parse_index_file(data_path+"/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
        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_test, tx, ty, test_mask, np.argmax(labels,1)


def load_alldata(dataset_str):
    """Load data."""
    names = ['x', 'y', 'tx', 'ty', 'allx', 'ally', 'graph']
    objects = []
    for i in range(len(names)):
        objects.append(pkl.load(open("data/ind.{}.{}".format(dataset_str, names[i]))))

    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, np.argmax(labels, 1)
    
def sparse_to_tuple(sparse_mx):
    if not sp.isspmatrix_coo(sparse_mx):
        sparse_mx = sparse_mx.tocoo()
    coords = np.vstack((sparse_mx.row, sparse_mx.col)).transpose()
    values = sparse_mx.data
    shape = sparse_mx.shape
    return coords, values, shape


def preprocess_graph(adj):
    adj = sp.coo_matrix(adj)
    adj_ = adj + sp.eye(adj.shape[0])
    rowsum = np.array(adj_.sum(1))
    degree_mat_inv_sqrt = sp.diags(np.power(rowsum, -0.5).flatten())
    adj_normalized = adj_.dot(degree_mat_inv_sqrt).transpose().dot(degree_mat_inv_sqrt).tocoo()
    return adj_normalized


def construct_feed_dict(adj_normalized, adj, features, placeholders):
    # construct feed dictionary
    feed_dict = dict()
    feed_dict.update({placeholders['features']: features})
    feed_dict.update({placeholders['adj']: adj_normalized})
    feed_dict.update({placeholders['adj_orig']: adj})
    return feed_dict


def mask_test_edges(adj):
    # Function to build test set with 10% positive links
    # NOTE: Splits are randomized and results might slightly deviate from reported numbers in the paper.
    # TODO: Clean up.

    # Remove diagonal elements
    adj = adj - sp.dia_matrix((adj.diagonal()[np.newaxis, :], [0]), shape=adj.shape)
    adj.eliminate_zeros()
    # Check that diag is zero:
    assert np.diag(adj.todense()).sum() == 0

    adj_triu = sp.triu(adj)
    adj_tuple = sparse_to_tuple(adj_triu)
    edges = adj_tuple[0]
    edges_all = sparse_to_tuple(adj)[0]
    num_test = int(np.floor(edges.shape[0] / 10.))
    num_val = int(np.floor(edges.shape[0] / 20.))

    all_edge_idx = list(range(edges.shape[0]))
    np.random.shuffle(all_edge_idx)
    val_edge_idx = all_edge_idx[:num_val]
    test_edge_idx = all_edge_idx[num_val:(num_val + num_test)]
    test_edges = edges[test_edge_idx]
    val_edges = edges[val_edge_idx]
    train_edges = np.delete(edges, np.hstack([test_edge_idx, val_edge_idx]), axis=0)

    def ismember(a, b, tol=5):
        rows_close = np.all(np.round(a - b[:, None], tol) == 0, axis=-1)
        return (np.all(np.any(rows_close, axis=-1), axis=-1) and
                np.all(np.any(rows_close, axis=0), axis=0))

    test_edges_false = []
    while len(test_edges_false) < len(test_edges):
        idx_i = np.random.randint(0, adj.shape[0])
        idx_j = np.random.randint(0, adj.shape[0])
        if idx_i == idx_j:
            continue
        if ismember([idx_i, idx_j], edges_all):
            continue
        if test_edges_false:
            if ismember([idx_j, idx_i], np.array(test_edges_false)):
                continue
            if ismember([idx_i, idx_j], np.array(test_edges_false)):
                continue
        test_edges_false.append([idx_i, idx_j])

    val_edges_false = []
    while len(val_edges_false) < len(val_edges):
        idx_i = np.random.randint(0, adj.shape[0])
        idx_j = np.random.randint(0, adj.shape[0])
        if idx_i == idx_j:
            continue
        if ismember([idx_i, idx_j], train_edges):
            continue
        if ismember([idx_j, idx_i], train_edges):
            continue
        if ismember([idx_i, idx_j], val_edges):
            continue
        if ismember([idx_j, idx_i], val_edges):
            continue
        if val_edges_false:
            if ismember([idx_j, idx_i], np.array(val_edges_false)):
                continue
            if ismember([idx_i, idx_j], np.array(val_edges_false)):
                continue
        val_edges_false.append([idx_i, idx_j])

    assert ~ismember(test_edges_false, edges_all)
    assert ~ismember(val_edges_false, edges_all)
    assert ~ismember(val_edges, train_edges)
    assert ~ismember(test_edges, train_edges)
    assert ~ismember(val_edges, test_edges)

    data = np.ones(train_edges.shape[0])

    # Re-build adj matrix
    adj_train = sp.csr_matrix((data, (train_edges[:, 0], train_edges[:, 1])), shape=adj.shape)
    adj_train = adj_train + adj_train.T

    # NOTE: these edge lists only contain single direction of edge!
    return adj_train, train_edges, val_edges, val_edges_false, test_edges, test_edges_false
    
def format_data(data_name, data_path):
    # Load data
    adj, features, y_test, tx, ty, test_maks, true_labels = load_data(data_name, data_path)


    # Store original adjacency matrix (without diagonal entries) for later
    adj_orig = adj
    adj_orig = adj_orig - sp.dia_matrix((adj_orig.diagonal()[np.newaxis, :], [0]), shape=adj_orig.shape)
    adj_orig.eliminate_zeros()

    adj_train, train_edges, val_edges, val_edges_false, test_edges, test_edges_false = mask_test_edges(adj)
    adj = adj_train

    # Some preprocessing
    adj_norm = preprocess_graph(adj)

    num_nodes = adj.shape[0]
    
    feas = {}
    feas['features_orig'] = sparse_mx_to_torch_sparse_tensor(features)

    features = features.tocoo()
    
    pos_weight = float(adj.shape[0] * adj.shape[0] - adj.sum()) / adj.sum()
    norm = adj.shape[0] * adj.shape[0] / float((adj.shape[0] * adj.shape[0] - adj.sum()) * 2)

    adj_label = adj_train + sp.eye(adj_train.shape[0])
    adj_label = sparse_to_tuple(adj_label)
             
    feas['adj'] = sparse_mx_to_torch_sparse_tensor(adj)
    feas['num_nodes'] = num_nodes
    feas['pos_weight'] = pos_weight
    feas['norm'] = norm
    feas['adj_norm'] = sparse_mx_to_torch_sparse_tensor(adj_norm)
    feas['adj_label'] = adj_label
    feas['features'] = sparse_mx_to_torch_sparse_tensor(features)
    feas['true_labels'] = true_labels
    feas['train_edges'] = train_edges
    feas['val_edges'] = val_edges
    feas['val_edges_false'] = val_edges_false
    feas['test_edges'] = test_edges
    feas['test_edges_false'] = test_edges_false
    feas['adj_orig'] = sparse_mx_to_torch_sparse_tensor(adj_orig)
        
    return feas

def sparse_mx_to_torch_sparse_tensor(sparse_mx):
    """Convert a scipy sparse matrix to a torch sparse tensor."""
    sparse_mx = sparse_mx.tocoo().astype(np.float32)
    indices = torch.from_numpy(np.vstack((sparse_mx.row, sparse_mx.col)).astype(np.int64))
    values = torch.from_numpy(sparse_mx.data)
    shape = torch.Size(sparse_mx.shape)
    return torch.sparse.FloatTensor(indices, values, shape)