def test_predict():
model = DistMult(batches_count=2,
seed=555,
epochs=1,
k=10,
loss='pairwise',
loss_params={'margin': 5},
optimizer='adagrad',
optimizer_params={'lr': 0.1})
X = np.array([['a', 'y', 'b'], ['b', 'y', 'a'], ['a', 'y', 'c'],
['c', 'z', 'a'], ['a', 'z', 'd']])
model.fit(X)
preds1 = model.predict(X)
preds2 = model.predict(to_idx(X, model.ent_to_idx, model.rel_to_idx),
from_idx=True)
np.testing.assert_array_equal(preds1, preds2)
def test_fit_predict_DistMult():
model = DistMult(batches_count=2, seed=555, epochs=20, k=10, loss='pairwise', loss_params={'margin': 5},
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 test_predict_twice():
model = DistMult(batches_count=2,
seed=555,
epochs=1,
k=10,
loss='pairwise',
loss_params={'margin': 5},
optimizer='adagrad',
optimizer_params={'lr': 0.1})
X = np.array([['a', 'y', 'b'], ['b', 'y', 'a'], ['a', 'y', 'c'],
['c', 'z', 'a'], ['a', 'z', 'd']])
model.fit(X)
X_test1 = np.array([['a', 'y', 'b'], ['b', 'y', 'a']])
X_test2 = np.array([['a', 'y', 'c'], ['c', 'z', 'a']])
preds1 = model.predict(X_test1)
preds2 = model.predict(X_test2)
assert not np.array_equal(preds1, preds2)
["Missandei", 'SPOUSE', 'Grey Worm'],
["Brienne of Tarth", 'SPOUSE', 'Jaime Lannister']
])
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
