def evaluate_embeddings(embeddings):
# data_path = join_path(dirname(dirname(__file__)),'data/wiki/wiki_labels.txt')
data_path = join_path(dirname(dirname(__file__)), 'data/bello_kg/graph_labels_last_version.txt')
data_path = join_path(dirname(dirname(__file__)), 'data/bello_kg/graph_labels_v1.1.txt')
X, Y = read_node_label(data_path)
tr_frac = 0.8
print("Training classifier using {:.2f}% nodes...".format(
tr_frac * 100))
clf = Classifier(embeddings=embeddings, clf=LogisticRegression())
clf.split_train_evaluate(X, Y, tr_frac)
def plot_embeddings(embeddings, ):
data_path = join_path(dirname(dirname(__file__)),
'data/bello_kg/graph_labels_last_version.txt')
X, Y = read_node_label(data_path, skip_head=True)
emb_list = []
for k in X:
emb_list.append(embeddings[k])
emb_list = np.array(emb_list)
model = TSNE(n_components=2)
node_pos = model.fit_transform(emb_list)
color_idx = {}
for i in range(len(X)):
color_idx.setdefault(Y[i][0], [])
color_idx[Y[i][0]].append(i)
for c, idx in color_idx.items():
plt.scatter(node_pos[idx, 0], node_pos[idx, 1],
label=c) # c=node_colors)
plt.legend()
plt.show()