def test_save_load(random_matrix):
X = random_matrix
mod = TorchAutoencoder(hidden_dim=5, max_iter=2)
mod.fit(X)
mod.predict(X)
with tempfile.NamedTemporaryFile(mode='wb') as f:
name = f.name
mod.to_pickle(name)
mod2 = TorchAutoencoder.from_pickle(name)
mod2.predict(X)
mod2.fit(X)
def test_model(random_matrix, model_class, pandas):
"""Just makes sure that this code will run; it doesn't check that
it is creating good models.
"""
X = random_matrix
if pandas:
X = pd.DataFrame(X)
ae = TorchAutoencoder(hidden_dim=5, max_iter=100)
H = ae.fit(X)
ae.predict(X)
H_is_pandas = isinstance(H, pd.DataFrame)
assert H_is_pandas == pandas
def test_simple_example_params(random_low_rank_matrix, param, expected):
X = random_low_rank_matrix
ae = TorchAutoencoder()
H = ae.fit(X)
X_pred = ae.predict(X)
r2 = ae.score(X)
assert r2 > 0.92
def autoencoder_evaluation(nrow=1000, ncol=100, rank=20, max_iter=20000):
"""This an evaluation in which `TfAutoencoder` should be able
to perfectly reconstruct the input data, because the
hidden representations have the same dimensionality as
the rank of the input matrix.
"""
X = randmatrix(nrow, rank).dot(randmatrix(rank, ncol))
ae = TorchAutoencoder(hidden_dim=rank, max_iter=max_iter)
ae.fit(X)
X_pred = ae.predict(X)
mse = (0.5 * (X_pred - X)**2).mean()
return (X, X_pred, mse)
