citation_networks.py

# The MIT License

# Copyright (c) 2016 Thomas Kipf

# Permission is hereby granted, free of charge, to any person obtaining a copy
# of this software and associated documentation files (the "Software"), to deal
# in the Software without restriction, including without limitation the rights
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
# copies of the Software, and to permit persons to whom the Software is
# furnished to do so, subject to the following conditions:

# The above copyright notice and this permission notice shall be included in
# all copies or substantial portions of the Software.

# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
# THE SOFTWARE.

import pickle as pkl
import sys
import warnings

import numpy as np
import scipy.sparse as sp
import torch

warnings.simplefilter("ignore")


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_citation_network(dataset_str):
    names = ['x', 'y', 'tx', 'ty', 'allx', 'ally', 'graph']
    objects = []
    for i in range(len(names)):
        with open("data_tf/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_tf/ind.{}.test.index".format(dataset_str))
    test_idx_range = np.sort(test_idx_reorder)

    if dataset_str == 'citeseer':
        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, :]

    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])

    features = torch.FloatTensor(features.todense())
    labels = torch.LongTensor(labels)
    train_mask = torch.BoolTensor(train_mask)
    val_mask = torch.BoolTensor(val_mask)
    test_mask = torch.BoolTensor(test_mask)

    nfeats = features.shape[1]
    for i in range(labels.shape[0]):
        sum_ = torch.sum(labels[i])
        if sum_ != 1:
            labels[i] = torch.tensor([1, 0, 0, 0, 0, 0])
    labels = (labels == 1).nonzero()[:, 1]
    nclasses = torch.max(labels).item() + 1

    return features, nfeats, labels, nclasses, train_mask, val_mask, test_mask


def load_citation_network_halftrain(dataset_str):
    names = ['x', 'y', 'tx', 'ty', 'allx', 'ally', 'graph']
    objects = []
    for i in range(len(names)):
        with open("data_tf/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_tf/ind.{}.test.index".format(dataset_str))
    test_idx_range = np.sort(test_idx_reorder)

    if dataset_str == 'citeseer':
        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, :]

    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])

    features = torch.FloatTensor(features.todense())
    labels = torch.LongTensor(labels)
    train_mask = torch.BoolTensor(train_mask)
    val_mask = torch.BoolTensor(val_mask)
    test_mask = torch.BoolTensor(test_mask)

    nfeats = features.shape[1]
    for i in range(labels.shape[0]):
        sum_ = torch.sum(labels[i])
        if sum_ != 1:
            labels[i] = torch.tensor([1, 0, 0, 0, 0, 0])
    labels = (labels == 1).nonzero()[:, 1]
    nclasses = torch.max(labels).item() + 1

    if dataset_str == 'pubmed':
        colum_sum = torch.zeros((1, 3))
    elif dataset_str == 'cora':
        colum_sum = torch.zeros((1, 7))
    elif dataset_str == 'citeseer':
        colum_sum = torch.zeros((1, 6))

    for iii in range(y.shape[0]):
        colum_sum = colum_sum + y[iii, :]
        if colum_sum.max() > 10:
            colum_sum = colum_sum - y[iii, :]
            train_mask[iii] = 0

    return features, nfeats, labels, nclasses, train_mask, val_mask, test_mask





def load_citation_network_calculate_starved_nodes(dataset_str):
    names = ['x', 'y', 'tx', 'ty', 'allx', 'ally', 'graph']
    objects = []
    for i in range(len(names)):
        with open("data_tf/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)

    num_vertices = len(graph)

    adjacency = [[0 for j in range(num_vertices)] for i in range(num_vertices)]

    for i in range(num_vertices):
        for j in graph[i]:
            adjacency[i][j] = 1

    adjacency = np.array(adjacency)



    test_idx_reorder = parse_index_file("data_tf/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, :]

    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])

    features = torch.FloatTensor(features.todense())
    labels = torch.LongTensor(labels)
    train_mask = torch.BoolTensor(train_mask)
    val_mask = torch.BoolTensor(val_mask)
    test_mask = torch.BoolTensor(test_mask)

    nfeats = features.shape[1]
    for i in range(labels.shape[0]):  
        sum_ = torch.sum(labels[i])
        if sum_ != 1:
            labels[i] = torch.tensor([1, 0, 0, 0, 0, 0])
    labels = (labels == 1).nonzero()[:, 1]
    nclasses = torch.max(labels).item() + 1

    return features, nfeats, labels, nclasses, train_mask, val_mask, test_mask, adjacency