1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
import numpy as np
import pandas as pd
import pickle
import csv
import os
import torch
from torch_geometric.data import Data
from torch_geometric.nn import MessagePassing
import math
import torch
import torch.nn.functional as F
from torch.nn import Parameter
from torch_geometric.nn.conv import MessagePassing
import os
import os.path as osp
import torch
import torch.nn.functional as F
from torch_geometric.datasets import Planetoid
import torch_geometric.transforms as T
from torch_geometric.datasets import TUDataset
from torch_geometric.utils import degree
import torch_geometric.transforms as T
import time

import torch
import torch.nn.functional as F
from torch import tensor
from torch.optim import Adam
from sklearn.model_selection import StratifiedKFold
from torch_geometric.data import DataLoader, DenseDataLoader as DenseLoader
import torch
import torch.nn.functional as F
from torch.nn import Linear, Sequential, ReLU, BatchNorm1d as BN
from torch_geometric.nn import global_mean_pool, MessagePassing
from torch_geometric.utils import remove_self_loops
from itertools import product
np.random.seed(42)

import os
import pandas as pd
import numpy as np
import networkx as nx
import matplotlib.pyplot as plt
import tensorflow as tf
from tensorflow import keras
from keras import layers


import pandas as pd
import os

import stellargraph as sg
from stellargraph.mapper import FullBatchNodeGenerator
from stellargraph.layer import GCN

from keras import layers, optimizers, losses, metrics, Model
from sklearn import preprocessing, model_selection
from IPython.display import display, HTML
import matplotlib.pyplot as plt
%matplotlib inline

1
2
3
4
5
6
7
8
9
10
11
12
13
14
#Load dataset
zip_file = keras.utils.get_file(
    fname="cora.tgz",
    origin="https://linqs-data.soe.ucsc.edu/public/lbc/cora.tgz",
    extract=True,
)
data_dir = os.path.join(os.path.dirname(zip_file), "cora")
citations = pd.read_csv(
    os.path.join(data_dir, "cora.cites"),
    sep="\t",
    header=None,
    names=["target", "source"],
)
print("Citations shape:", citations.shape)

1
2
3
4
5
6
7
8
9
10
11
citations.sample(frac=1).head()

column_names = ["paper_id"] + [f"term_{idx}" for idx in range(1433)] + ["subject"]
papers = pd.read_csv(
    os.path.join(data_dir, "cora.content"), sep="\t", header=None, names=column_names,
)
print("Papers shape:", papers.shape)

print(papers.sample(5).T)
print(papers.subject.value_counts())

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
class_values = sorted(papers["subject"].unique())
class_idx = {name: id for id, name in enumerate(class_values)}
paper_idx = {name: idx for idx, name in enumerate(sorted(papers["paper_id"].unique()))}

papers["paper_id"] = papers["paper_id"].apply(lambda name: paper_idx[name])
citations["source"] = citations["source"].apply(lambda name: paper_idx[name])
citations["target"] = citations["target"].apply(lambda name: paper_idx[name])
papers["subject"] = papers["subject"].apply(lambda value: class_idx[value])

train_data, test_data = [], []

for _, group_data in papers.groupby("subject"):
    # Select around 50% of the dataset for training.
    random_selection = np.random.rand(len(group_data.index)) <= 0.5
    train_data.append(group_data[random_selection])
    test_data.append(group_data[~random_selection])

train_data = pd.concat(train_data).sample(frac=1)
test_data = pd.concat(test_data).sample(frac=1)

print("Train data shape:", train_data.shape)
print("Test data shape:", test_data.shape)

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
hidden_units = [32, 32]
learning_rate = 0.01
dropout_rate = 0.5
num_epochs = 300
batch_size = 256
def run_experiment(model, x_train, y_train):
    # Compile the model.
    model.compile(
        optimizer=keras.optimizers.Adam(learning_rate),
        loss=keras.losses.SparseCategoricalCrossentropy(from_logits=True),
        metrics=[keras.metrics.SparseCategoricalAccuracy(name="acc")],
    )
    # Create an early stopping callback.
    early_stopping = keras.callbacks.EarlyStopping(
        monitor="val_acc", patience=50, restore_best_weights=True
    )
    # Fit the model.
    history = model.fit(
        x=x_train,
        y=y_train,
        epochs=num_epochs,
        batch_size=batch_size,
        validation_split=0.15,
        callbacks=[early_stopping],
    )

    return history

def display_learning_curves(history):
    fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(15, 5))

    ax1.plot(history.history["loss"])
    ax1.plot(history.history["val_loss"])
    ax1.legend(["train", "test"], loc="upper right")
    ax1.set_xlabel("Epochs")
    ax1.set_ylabel("Loss")

    ax2.plot(history.history["acc"])
    ax2.plot(history.history["val_acc"])
    ax2.legend(["train", "test"], loc="upper right")
    ax2.set_xlabel("Epochs")
    ax2.set_ylabel("Accuracy")
    plt.show()

def create_ffn(hidden_units, dropout_rate, name=None):
    fnn_layers = []

    for units in hidden_units:
        fnn_layers.append(layers.BatchNormalization())
        fnn_layers.append(layers.Dropout(dropout_rate))
        fnn_layers.append(layers.Dense(units, activation=tf.nn.gelu))

    return keras.Sequential(fnn_layers, name=name)

1
2
3
4
5
6
7
8
9
10
11
feature_names = set(papers.columns) - {"paper_id", "subject"}
num_features = len(feature_names)
num_classes = len(class_idx)

# Create train and test features as a numpy array.
x_train = train_data[feature_names].to_numpy()
x_test = test_data[feature_names].to_numpy()
# Create train and test targets as a numpy array.
y_train = train_data["subject"]
y_test = test_data["subject"]

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
def create_baseline_model(hidden_units, num_classes, dropout_rate=0.2):
    inputs = layers.Input(shape=(num_features,), name="input_features")
    x = create_ffn(hidden_units, dropout_rate, name=f"ffn_block1")(inputs)
    for block_idx in range(4):
        # Create an FFN block.
        x1 = create_ffn(hidden_units, dropout_rate, name=f"ffn_block{block_idx + 2}")(x)
        # Add skip connection.
        x = layers.Add(name=f"skip_connection{block_idx + 2}")([x, x1])
    # Compute logits.
    logits = layers.Dense(num_classes, name="logits")(x)
    # Create the model.
    return keras.Model(inputs=inputs, outputs=logits, name="baseline")


baseline_model = create_baseline_model(hidden_units, num_classes, dropout_rate)
baseline_model.summary()

history = run_experiment(baseline_model, x_train, y_train)

display_learning_curves(history)

_, test_accuracy = baseline_model.evaluate(x=x_test, y=y_test, verbose=0)
print(f"Test accuracy: {round(test_accuracy * 100, 2)}%")

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
def generate_random_instances(num_instances):
    token_probability = x_train.mean(axis=0)
    instances = []
    for _ in range(num_instances):
        probabilities = np.random.uniform(size=len(token_probability))
        instance = (probabilities <= token_probability).astype(int)
        instances.append(instance)

    return np.array(instances)


def display_class_probabilities(probabilities):
    for instance_idx, probs in enumerate(probabilities):
        print(f"Instance {instance_idx + 1}:")
        for class_idx, prob in enumerate(probs):
            print(f"- {class_values[class_idx]}: {round(prob * 100, 2)}%")

new_instances = generate_random_instances(num_classes)
logits = baseline_model.predict(new_instances)
probabilities = keras.activations.softmax(tf.convert_to_tensor(logits)).numpy()
display_class_probabilities(probabilities)

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
# BUILD GNN
# build GNN
# Create an edges array (sparse adjacency matrix) of shape [2, num_edges].
edges = citations[["source", "target"]].to_numpy().T
# Create an edge weights array of ones.
edge_weights = tf.ones(shape=edges.shape[1])
# Create a node features array of shape [num_nodes, num_features].
node_features = tf.cast(
    papers.sort_values("paper_id")[feature_names].to_numpy(), dtype=tf.dtypes.float32
)
# Create graph info tuple with node_features, edges, and edge_weights.
graph_info = (node_features, edges, edge_weights)

print("Edges shape:", edges.shape)
print("Nodes shape:", node_features.shape)

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
class GraphConvLayer(layers.Layer):
    def __init__(
        self,
        hidden_units,
        dropout_rate=0.2,
        aggregation_type="mean",
        combination_type="concat",
        normalize=False,
        *args,
        **kwargs,
    ):
        super().__init__(*args, **kwargs)

        self.aggregation_type = aggregation_type
        self.combination_type = combination_type
        self.normalize = normalize

        self.ffn_prepare = create_ffn(hidden_units, dropout_rate)
        if self.combination_type == "gated":
            self.update_fn = layers.GRU(
                units=hidden_units,
                activation="tanh",
                recurrent_activation="sigmoid",
                dropout=dropout_rate,
                return_state=True,
                recurrent_dropout=dropout_rate,
            )
        else:
            self.update_fn = create_ffn(hidden_units, dropout_rate)

    def prepare(self, node_repesentations, weights=None):
        # node_repesentations shape is [num_edges, embedding_dim].
        messages = self.ffn_prepare(node_repesentations)
        if weights is not None:
            messages = messages * tf.expand_dims(weights, -1)
        return messages

    def aggregate(self, node_indices, neighbour_messages, node_repesentations):
        # node_indices shape is [num_edges].
        # neighbour_messages shape: [num_edges, representation_dim].
        # node_repesentations shape is [num_nodes, representation_dim]
        num_nodes = node_repesentations.shape[0]
        if self.aggregation_type == "sum":
            aggregated_message = tf.math.unsorted_segment_sum(
                neighbour_messages, node_indices, num_segments=num_nodes
            )
        elif self.aggregation_type == "mean":
            aggregated_message = tf.math.unsorted_segment_mean(
                neighbour_messages, node_indices, num_segments=num_nodes
            )
        elif self.aggregation_type == "max":
            aggregated_message = tf.math.unsorted_segment_max(
                neighbour_messages, node_indices, num_segments=num_nodes
            )
        else:
            raise ValueError(f"Invalid aggregation type: {self.aggregation_type}.")

        return aggregated_message

    def update(self, node_repesentations, aggregated_messages):
        # node_repesentations shape is [num_nodes, representation_dim].
        # aggregated_messages shape is [num_nodes, representation_dim].
        if self.combination_type == "gru":
            # Create a sequence of two elements for the GRU layer.
            h = tf.stack([node_repesentations, aggregated_messages], axis=1)
        elif self.combination_type == "concat":
            # Concatenate the node_repesentations and aggregated_messages.
            h = tf.concat([node_repesentations, aggregated_messages], axis=1)
        elif self.combination_type == "add":
            # Add node_repesentations and aggregated_messages.
            h = node_repesentations + aggregated_messages
        else:
            raise ValueError(f"Invalid combination type: {self.combination_type}.")

        # Apply the processing function.
        node_embeddings = self.update_fn(h)
        if self.combination_type == "gru":
            node_embeddings = tf.unstack(node_embeddings, axis=1)[-1]

        if self.normalize:
            node_embeddings = tf.nn.l2_normalize(node_embeddings, axis=-1)
        return node_embeddings

    def call(self, inputs):
        """Process the inputs to produce the node_embeddings.

        inputs: a tuple of three elements: node_repesentations, edges, edge_weights.
        Returns: node_embeddings of shape [num_nodes, representation_dim].
        """

        node_repesentations, edges, edge_weights = inputs
        # Get node_indices (source) and neighbour_indices (target) from edges.
        node_indices, neighbour_indices = edges[0], edges[1]
        # neighbour_repesentations shape is [num_edges, representation_dim].
        neighbour_repesentations = tf.gather(node_repesentations, neighbour_indices)

        # Prepare the messages of the neighbours.
        neighbour_messages = self.prepare(neighbour_repesentations, edge_weights)
        # Aggregate the neighbour messages.
        aggregated_messages = self.aggregate(
            node_indices, neighbour_messages, node_repesentations
        )
        # Update the node embedding with the neighbour messages.
        return self.update(node_repesentations, aggregated_messages)

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
class GNNNodeClassifier(tf.keras.Model):
    def __init__(
        self,
        graph_info,
        num_classes,
        hidden_units,
        aggregation_type="sum",
        combination_type="concat",
        dropout_rate=0.2,
        normalize=True,
        *args,
        **kwargs,
    ):
        super().__init__(*args, **kwargs)

        # Unpack graph_info to three elements: node_features, edges, and edge_weight.
        node_features, edges, edge_weights = graph_info
        self.node_features = node_features
        self.edges = edges
        self.edge_weights = edge_weights
        # Set edge_weights to ones if not provided.
        if self.edge_weights is None:
            self.edge_weights = tf.ones(shape=edges.shape[1])
        # Scale edge_weights to sum to 1.
        self.edge_weights = self.edge_weights / tf.math.reduce_sum(self.edge_weights)

        # Create a process layer.
        self.preprocess = create_ffn(hidden_units, dropout_rate, name="preprocess")
        # Create the first GraphConv layer.
        self.conv1 = GraphConvLayer(
            hidden_units,
            dropout_rate,
            aggregation_type,
            combination_type,
            normalize,
            name="graph_conv1",
        )
        # Create the second GraphConv layer.
        self.conv2 = GraphConvLayer(
            hidden_units,
            dropout_rate,
            aggregation_type,
            combination_type,
            normalize,
            name="graph_conv2",
        )
        # Create a postprocess layer.
        self.postprocess = create_ffn(hidden_units, dropout_rate, name="postprocess")
        # Create a compute logits layer.
        self.compute_logits = layers.Dense(units=num_classes, name="logits")

    def call(self, input_node_indices):
        # Preprocess the node_features to produce node representations.
        x = self.preprocess(self.node_features)
        # Apply the first graph conv layer.
        x1 = self.conv1((x, self.edges, self.edge_weights))
        # Skip connection.
        x = x1 + x
        # Apply the second graph conv layer.
        x2 = self.conv2((x, self.edges, self.edge_weights))
        # Skip connection.
        x = x2 + x
        # Postprocess node embedding.
        x = self.postprocess(x)
        # Fetch node embeddings for the input node_indices.
        node_embeddings = tf.gather(x, input_node_indices)
        # Compute logits
        return self.compute_logits(node_embeddings)

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
gnn_model = GNNNodeClassifier(
    graph_info=graph_info,
    num_classes=num_classes,
    hidden_units=hidden_units,
    dropout_rate=dropout_rate,
    name="gnn_model",
)

print("GNN output shape:", gnn_model([1, 10, 100]))

gnn_model.summary()

x_train = train_data.paper_id.to_numpy()
history = run_experiment(gnn_model, x_train, y_train)

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
x_test = test_data.paper_id.to_numpy()
_, test_accuracy = gnn_model.evaluate(x=x_test, y=y_test, verbose=0)
print(f"Test accuracy: {round(test_accuracy * 100, 2)}%")

# First we add the N new_instances as nodes to the graph
# by appending the new_instance to node_features.
num_nodes = node_features.shape[0]
new_node_features = np.concatenate([node_features, new_instances])
# Second we add the M edges (citations) from each new node to a set
# of existing nodes in a particular subject
new_node_indices = [i + num_nodes for i in range(num_classes)]
new_citations = []
for subject_idx, group in papers.groupby("subject"):
    subject_papers = list(group.paper_id)
    # Select random x papers specific subject.
    selected_paper_indices1 = np.random.choice(subject_papers, 5)
    # Select random y papers from any subject (where y < x).
    selected_paper_indices2 = np.random.choice(list(papers.paper_id), 2)
    # Merge the selected paper indices.
    selected_paper_indices = np.concatenate(
        [selected_paper_indices1, selected_paper_indices2], axis=0
    )
    # Create edges between a citing paper idx and the selected cited papers.
    citing_paper_indx = new_node_indices[subject_idx]
    for cited_paper_idx in selected_paper_indices:
        new_citations.append([citing_paper_indx, cited_paper_idx])

new_citations = np.array(new_citations).T
new_edges = np.concatenate([edges, new_citations], axis=1)

print("Original node_features shape:", gnn_model.node_features.shape)
print("Original edges shape:", gnn_model.edges.shape)
gnn_model.node_features = new_node_features
gnn_model.edges = new_edges
gnn_model.edge_weights = tf.ones(shape=new_edges.shape[1])
print("New node_features shape:", gnn_model.node_features.shape)
print("New edges shape:", gnn_model.edges.shape)

logits = gnn_model.predict(tf.convert_to_tensor(new_node_indices))
probabilities = keras.activations.softmax(tf.convert_to_tensor(logits)).numpy()
display_class_probabilities(probabilities)

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
from torch_geometric.datasets import Planetoid

dataset = Planetoid(root='/tmp/Cora', name='Cora')
graph = dataset[0]

import random
from torch_geometric.utils import to_networkx
import networkx as nx

def convert_to_networkx(graph, n_sample=None):

    g = to_networkx(graph, node_attrs=["x"])
    y = graph.y.numpy()

    if n_sample is not None:
        sampled_nodes = random.sample(g.nodes, n_sample)
        g = g.subgraph(sampled_nodes)
        y = y[sampled_nodes]

    return g, y


def plot_graph(g, y):

    plt.figure(figsize=(9, 7))
    #nx.draw_spring(g, node_size=30, arrows=False, node_color=y)
    plt.show() 
    
    
g, y = convert_to_networkx(graph, n_sample=1000)
#plot_graph(g, y)

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
import torch_geometric.transforms as T

split = T.RandomNodeSplit(num_val=0.1, num_test=0.2)
graph = split(graph)

import torch.nn as nn

class MLP(nn.Module):
    def __init__(self):
        super().__init__()
        self.layers = nn.Sequential(
        nn.Linear(dataset.num_node_features, 64),
        nn.ReLU(),
        nn.Linear(64, 32),
        nn.ReLU(),
        nn.Linear(32, dataset.num_classes)
        )

    def forward(self, data):
        x = data.x  # only using node features (x)
        output = self.layers(x)
        return output

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
def train_node_classifier(model, graph, optimizer, criterion, n_epochs=200):

    for epoch in range(1, n_epochs + 1):
        model.train()
        optimizer.zero_grad()
        out = model(graph)
        loss = criterion(out[graph.train_mask], graph.y[graph.train_mask])
        loss.backward()
        optimizer.step()

        pred = out.argmax(dim=1)
        acc = eval_node_classifier(model, graph, graph.val_mask)

        if epoch % 10 == 0:
            print(f'Epoch: {epoch:03d}, Train Loss: {loss:.3f}, Val Acc: {acc:.3f}')

    return model


def eval_node_classifier(model, graph, mask):

    model.eval()
    pred = model(graph).argmax(dim=1)
    correct = (pred[mask] == graph.y[mask]).sum()
    acc = int(correct) / int(mask.sum())

    return acc
  
  
mlp = MLP()
optimizer_mlp = torch.optim.Adam(mlp.parameters(), lr=0.01, weight_decay=5e-4)
criterion = nn.CrossEntropyLoss()
mlp = train_node_classifier(mlp, graph, optimizer_mlp, criterion, n_epochs=150)

test_acc = eval_node_classifier(mlp, graph, graph.test_mask)
print(f'Test Acc: {test_acc:.3f}')

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
from torch_geometric.nn import GCNConv
import torch.nn.functional as F

class GCN(torch.nn.Module):
    def __init__(self):
        super().__init__()
        self.conv1 = GCNConv(dataset.num_node_features, 16)
        self.conv2 = GCNConv(16, dataset.num_classes)

    def forward(self, data):
        x, edge_index = data.x, data.edge_index

        x = self.conv1(x, edge_index)
        x = F.relu(x)
        output = self.conv2(x, edge_index)

        return output
    
    
gcn = GCN()
optimizer_gcn = torch.optim.Adam(gcn.parameters(), lr=0.01, weight_decay=5e-4)
criterion = nn.CrossEntropyLoss()
gcn = train_node_classifier(gcn, graph, optimizer_gcn, criterion)

test_acc = eval_node_classifier(gcn, graph, graph.test_mask)
print(f'Test Acc: {test_acc:.3f}')

1
2
3
4
5
6
7
8
9
10
11
12
13
import pandas as pd
import os

import stellargraph as sg
from stellargraph.mapper import FullBatchNodeGenerator
from stellargraph.layer import GCN

from tensorflow.keras import layers, optimizers, losses, metrics, Model
from sklearn import preprocessing, model_selection
from IPython.display import display, HTML
import matplotlib.pyplot as plt
%matplotlib inline

1
2
3
4
5
6
7
8
9
10
11
12
13
dataset = sg.datasets.Cora()
display(HTML(dataset.description))
G, node_subjects = dataset.load()

print(G.info())
node_subjects.value_counts().to_frame()
train_subjects, test_subjects = model_selection.train_test_split(
    node_subjects, train_size=140, test_size=None, stratify=node_subjects
)
val_subjects, test_subjects = model_selection.train_test_split(
    test_subjects, train_size=500, test_size=None, stratify=test_subjects
)
train_subjects.value_counts().to_frame()

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
target_encoding = preprocessing.LabelBinarizer()

train_targets = target_encoding.fit_transform(train_subjects)
val_targets = target_encoding.transform(val_subjects)
test_targets = target_encoding.transform(test_subjects)

generator = FullBatchNodeGenerator(G, method="gcn")
train_gen = generator.flow(train_subjects.index, train_targets)
gcn = GCN(
    layer_sizes=[16, 16], activations=["relu", "relu"], generator=generator, dropout=0.5
)
x_inp, x_out = gcn.in_out_tensors()

x_out

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
predictions = layers.Dense(units=train_targets.shape[1], activation="softmax")(x_out)
model = Model(inputs=x_inp, outputs=predictions)
model.compile(
    optimizer=optimizers.Adam(lr=0.01),
    loss=losses.categorical_crossentropy,
    metrics=["acc"],
)

val_gen = generator.flow(val_subjects.index, val_targets)
from tensorflow.keras.callbacks import EarlyStopping

es_callback = EarlyStopping(monitor="val_acc", patience=50, restore_best_weights=True)

history = model.fit(
    train_gen,
    epochs=200,
    validation_data=val_gen,
    verbose=2,
    shuffle=False,  # this should be False, since shuffling data means shuffling the whole graph
    callbacks=[es_callback],
)

sg.utils.plot_history(history)

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
test_gen = generator.flow(test_subjects.index, test_targets)
test_metrics = model.evaluate(test_gen)
print("\nTest Set Metrics:")
for name, val in zip(model.metrics_names, test_metrics):
    print("\t{}: {:0.4f}".format(name, val))

all_nodes = node_subjects.index
all_gen = generator.flow(all_nodes)
all_predictions = model.predict(all_gen)

node_predictions = target_encoding.inverse_transform(all_predictions.squeeze())

df = pd.DataFrame({"Predicted": node_predictions, "True": node_subjects})
df.head(20)

embedding_model = Model(inputs=x_inp, outputs=x_out)
emb = embedding_model.predict(all_gen)
emb.shape

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
from sklearn.decomposition import PCA
from sklearn.manifold import TSNE

transform = TSNE  # or PCA

X = emb.squeeze(0)
X.shape

trans = transform(n_components=2)
X_reduced = trans.fit_transform(X)
X_reduced.shape

fig, ax = plt.subplots(figsize=(7, 7))
ax.scatter(
    X_reduced[:, 0],
    X_reduced[:, 1],
    c=node_subjects.astype("category").cat.codes,
    cmap="jet",
    alpha=0.7,
)
ax.set(
    aspect="equal",
    xlabel="$X_1$",
    ylabel="$X_2$",
    title=f"{transform.__name__} visualization of GCN embeddings for cora dataset",
)