def test_learning_factorization(verbose=False):
n = 9
m = 8
y_mat = toy_factorization_problem(n=n, m=m, rk=3, noise=1)
rank = 2
batch_size = n * m
tuples = mat2tuples(y_mat)
tuple_iterable = data_to_batches(tuples, minibatch_size=batch_size)
# tuple_iterable = positive_and_negative_tuple_sampler(mat2tuples(y_mat), minibatch_size=batch_size)
sampler, (x, y) = feed_dict_sampler(tuple_iterable, types=[np.int64, np.float32])
loss_op = tf.reduce_mean(loss_func(multilinear_tuple_scorer(x, rank=rank, n_emb=n+m)[0], y, 'quadratic'))
initial_losses = [tf_eval(loss_op, f) for _, f in sampler]
if verbose:
print(initial_losses)
# hooks = [lambda s, e, it, l: it and ((it % 100) == 0) and print("%d) loss=%f" % (it, l))]
hooks = [lambda it, b, l: it and ((it % 1) == 0) and print("{0}) train loss={1}".format(it, l[0]))]
emb, = learn(loss_op, sampler, tf.train.AdamOptimizer(learning_rate=0.1), hooks, max_epochs=200)
# emb, = learn(l, sampler, tf.train.GradientDescentOptimizer(learning_rate=0.5), hooks, max_epochs=500)
# emb, = learn(l, sampler, tf.train.AdagradOptimizer(0.01, initial_accumulator_value=0.01), hooks, max_epochs=500)
mat0 = svd_factorize_matrix(y_mat, rank=2) # exact svd solution
mat = emb[:n, :].dot(emb[n:, :].T)
if verbose:
print(np.linalg.norm(mat - mat0))
assert(np.linalg.norm(mat - mat0) < 1e-3)
def test_learning_factorization(verbose=False):
n = 9
m = 8
y_mat = toy_factorization_problem(n=n, m=m, rk=3, noise=1)
rank = 2
batch_size = n * m
tuples = mat2tuples(y_mat)
tuple_iterable = data_to_batches(tuples, minibatch_size=batch_size)
# tuple_iterable = positive_and_negative_tuple_sampler(mat2tuples(y_mat), minibatch_size=batch_size)
sampler, (x, y) = feed_dict_sampler(tuple_iterable,
types=[np.int64, np.float32])
loss_op = tf.reduce_mean(
loss_func(
multilinear_tuple_scorer(x, rank=rank, n_emb=n + m)[0], y,
'quadratic'))
initial_losses = [tf_eval(loss_op, f) for _, f in sampler]
if verbose:
print(initial_losses)
# hooks = [lambda s, e, it, l: it and ((it % 100) == 0) and print("%d) loss=%f" % (it, l))]
hooks = [
lambda it, b, l: it and (
(it % 1) == 0) and print("{0}) train loss={1}".format(it, l[0]))
]
emb, = learn(loss_op,
sampler,
tf.train.AdamOptimizer(learning_rate=0.1),
hooks,
max_epochs=200)
# emb, = learn(l, sampler, tf.train.GradientDescentOptimizer(learning_rate=0.5), hooks, max_epochs=500)
# emb, = learn(l, sampler, tf.train.AdagradOptimizer(0.01, initial_accumulator_value=0.01), hooks, max_epochs=500)
mat0 = svd_factorize_matrix(y_mat, rank=2) # exact svd solution
mat = emb[:n, :].dot(emb[n:, :].T)
if verbose:
print(np.linalg.norm(mat - mat0))
assert (np.linalg.norm(mat - mat0) < 1e-3)
missing_values = True
if missing_values:
mat0 = np.nan * np.ones((n, m))
observed_indices = [(np.random.randint(n), np.random.randint(m)) for _ in range(int(n * m))]
print(observed_indices)
for i, j in observed_indices:
mat0[i,j] = mat[i, j]
mat = mat0
print(mat)
tuples = [([i, n + j], mat[i, j]) for (i, j) in observed_indices]
else:
tuples = [([i, n + j], mat[i, j]) for i in range(n) for j in range(m)]
tuple_iterable = data_to_batches(tuples, minibatch_size=n * m)
batches = [batch for batch in tuple_iterable]
print(batches[0])
sampler, (x, y) = feed_dict_sampler(tuple_iterable, types=[np.int64, np.float32])
# sampler is an iterator return (bucket_id, dictionary containing the batch)
# x and y are "placeholder" (equivalent of symbolic variables used as input to your model)
# print([s for s in sampler])
print(x)
emb_var = tf.Variable(tf.cast(np.random.randn(n + m, rank), 'float32', name='embeddings'))