def test_fit_predict_HolE():
model = HolE(batches_count=1, seed=555, epochs=20, k=10,
loss='pairwise', loss_params={'margin': 1}, regularizer='LP',
regularizer_params={'lambda': 0.1, 'p': 2},
optimizer='adagrad', optimizer_params={'lr':0.1})
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.fit(X)
y_pred, _ = model.predict(np.array([['f', 'y', 'e'], ['b', 'y', 'd']]), get_ranks=True)
print(y_pred)
assert y_pred[0] > y_pred[1]
def select_kge(kge_name, batch_size, epochs, seed, verbose):
model = ''
# Select kge_name
if kge_name == 'complex':
# ComplEx model
model = ComplEx(
batches_count=batch_size,
epochs=epochs,
k=150,
eta=20,
optimizer='adam',
optimizer_params={'margin':
5}, #,'lr':learning_rate}, # default lr:0.1
loss='multiclass_nll',
loss_params={},
regularizer='LP',
regularizer_params={
'p': 2,
'lambda': 1e-4
},
seed=seed,
verbose=verbose)
elif kge_name == 'hole':
# HolE model
model = HolE(batches_count=batch_size,
epochs=epochs,
k=100,
eta=20,
optimizer='adam',
optimizer_params={'lr': learning_rate},
loss='multiclass_nll',
regularizer='LP',
regularizer_params={
'p': 3,
'lambda': 1e-5
},
seed=seed,
verbose=verbose)
elif kge_name == 'transe':
# TransE model
model = TransE(
batches_count=batch_size,
epochs=epochs,
k=350,
eta=20,
optimizer='adam',
optimizer_params={'margin':
5}, #,'lr':learning_rate}, # default lr:0.1
loss='multiclass_nll', #loss='pairwise',
loss_params={}, #loss_params={'margin:5'},
regularizer='LP',
regularizer_params={
'p': 2,
'lambda': 1e-4
},
seed=seed,
verbose=verbose)
else:
sys.exit('Given kge_name is not valid.')
return model
log_file = open("eval_log.txt", "a")
print("\n\n----"+log_key+"----", file=log_file)
print("------------------------------------------------")
print("%d) Implementation Model: %s" % (1, mdl[j]))
print("------------------------------------------------")
start_time = time.time() # START: Training Time Tracker
K.clear_session() # Kills current TF comp-graph & creates a new one
if (mdl[j] == "ComplEx"):
model = ComplEx(verbose=True)
elif (mdl[j] == "ConvKB"):
model = ConvKB(verbose=True)
elif (mdl[j] == "DistMult"):
model = DistMult(verbose=True)
elif (mdl[j] == "HolE"):
model = HolE(verbose=True)
elif (mdl[j] == "TransE"):
model = TransE(verbose=True)
elif (mdl[j] == "RandomBaseline"):
model = RandomBaseline(verbose=True)
tf.compat.v1.logging.set_verbosity(tf.compat.v1.logging.ERROR) # TensorFlow will tell you all messages that have the label ERROR
model.fit(train_X)
# Save model at its best-performance point
save_model(model, 'best_ampliGraph_model.pkl')
del model # Delete older model
# Load recently save best-performance model
model = restore_model('./best_ampliGraph_model.pkl')
if model.is_fitted:
print('The model is fit!')
else:
# International football matches triples
url = 'https://ampligraph.s3-eu-west-1.amazonaws.com/datasets/football.csv'
open('football.csv', 'wb').write(requests.get(url).content)
X = load_from_csv('.', 'football.csv', sep=',')[:, 1:]
# Train test split
X_train, X_test = train_test_split_no_unseen(X, test_size=10000)
# ComplEx model
model = HolE(batches_count=50,
epochs=300,
k=100,
eta=20,
optimizer='adam',
optimizer_params={'lr': 1e-4},
loss='multiclass_nll',
regularizer='LP',
regularizer_params={
'p': 3,
'lambda': 1e-5
},
seed=0,
verbose=True)
model.fit(X_train)
filter_triples = np.concatenate((X_train, X_test))
ranks = evaluate_performance(X_test,
model=model,
filter_triples=filter_triples,
use_default_protocol=True,
verbose=True)