def predict_missing_links(train_file_path, evaluation_file_path, model_path,
tensorboard_visualizations_path):
graph = load_from_csv('.', train_file_path, sep=',')
evaluation_samples = load_from_csv('.', evaluation_file_path, sep=',')
print('Head of the loaded graph: ')
print(graph[:5])
train_samples, test_samples = split(graph)
print(
f'Divided into train and test subsets with shapes {train_samples.shape} and {test_samples.shape} respectively.'
)
if not os.path.isfile(model_path):
model = train_transe(train_samples) # train_complex(train_samples)
save_model(model, model_path)
else:
model = restore_model(model_path)
metrics = compute_metrics(model, train_samples, test_samples)
print(f'{"metric":10s}: {"score":5s}')
for metric, score in metrics.items():
print(f'{metric:10s}: {score:<5.2f}')
scores, ranks = score_samples(model, evaluation_samples, train_samples)
evaluation_summary = summarize(scores, evaluation_samples, ranks)
print(evaluation_summary)
if tensorboard_visualizations_path:
os.makedirs(tensorboard_visualizations_path, exist_ok=True)
create_tensorboard_visualizations(model,
tensorboard_visualizations_path)
def test_create_tensorboard_visualizations():
# test if tensorflow API are still operative
X = np.array([['a', 'y', 'b'], ['b', 'y', 'a'], ['a', 'y', 'c'],
['c', 'y', 'a'], ['a', 'y', 'd'], ['c', 'y', 'd'],
['b', 'y', 'c'], ['f', 'y', 'e']])
model = TransE(batches_count=1,
seed=555,
epochs=20,
k=10,
loss='pairwise',
loss_params={'margin': 5})
model.fit(X)
create_tensorboard_visualizations(model, 'tensorboard_files')
unseen_filter = np.array(list({tuple(i) for i in np.vstack((positives_filter, X_unseen))}))
ranks_unseen = evaluate_performance(
X_unseen,
model=model,
filter_triples=unseen_filter, # Corruption strategy filter defined above
corrupt_side = 's+o',
use_default_protocol=False, # corrupt subj and obj separately while evaluating
verbose=True
)
scores = model.predict(X_unseen)
from scipy.special import expit
probs = expit(scores)
pd.DataFrame(list(zip([' '.join(x) for x in X_unseen],
ranks_unseen,
np.squeeze(scores),
np.squeeze(probs))),
columns=['statement', 'rank', 'score', 'prob']).sort_values("score")
"""---
# 7. Visualizing Embeddings with Tensorboard projector
"""
from ampligraph.utils import create_tensorboard_visualizations
create_tensorboard_visualizations(model, 'GoT_embeddings')