def test_matrix_factorization_with_low_rank_random_matrix():
initialize_random_seed() # for reproducibility
solver = MatrixFactorization(learning_rate=0.01,
rank=3,
l2_penalty=0,
min_improvement=1e-6,
verbose=False)
XY_completed = solver.fit_transform(XY_incomplete)
_, missing_mae = reconstruction_error(XY,
XY_completed,
missing_mask,
name="MatrixFactorization")
assert missing_mae < 0.1, "Error too high!"
initialize_random_seed() # for reproducibility
solver = MatrixFactorization(learning_rate=0.01,
rank=3,
l2_penalty=0,
min_improvement=1e-6,
verbose=False)
XY_completed = solver.fit(XY_incomplete, missing_mask)
_, missing_mae = reconstruction_error(XY,
XY_completed,
missing_mask,
name="MatrixFactorization")
assert missing_mae < 0.1, "Error too high!"
XY_completed = solver.transform(XY_incomplete, missing_mask)
_, missing_mae = reconstruction_error(XY,
XY_completed,
missing_mask,
name="MatrixFactorization")
assert missing_mae < 0.1, "Error too high!"
def test_iterative_imputer_with_low_rank_random_matrix():
imputer = IterativeImputer(n_iter=50, random_state=0)
XY_completed = imputer.fit_transform(XY_incomplete)
_, missing_mae = reconstruction_error(XY,
XY_completed,
missing_mask,
name="IterativeImputer")
assert missing_mae < 0.1, "Error too high with IterativeImputer method!"
def test_nuclear_norm_minimization_with_low_rank_random_matrix():
solver = NuclearNormMinimization(max_iters=2000)
XY_completed = solver.fit_transform(XY_incomplete[:100])
_, missing_mae = reconstruction_error(XY[:100],
XY_completed,
missing_mask[:100],
name="NuclearNorm")
assert missing_mae < 0.1, "Error too high!"
def test_iterative_svd_with_low_rank_random_matrix():
solver = IterativeSVD(rank=3)
XY_completed = solver.fit_transform(XY_incomplete)
_, missing_mae = reconstruction_error(XY,
XY_completed,
missing_mask,
name="IterativeSVD")
assert missing_mae < 0.1, "Error too high!"
def test_soft_impute_with_low_rank_random_matrix():
solver = SoftImpute()
XY_completed = solver.fit_transform(XY_incomplete)
_, missing_mae = reconstruction_error(XY,
XY_completed,
missing_mask,
name="SoftImpute")
assert missing_mae < 0.1, "Error too high!"
def test_matrix_factorization_with_low_rank_random_matrix():
solver = MatrixFactorization(rank=3, l1_penalty=0, l2_penalty=0)
XY_completed = solver.complete(XY_incomplete)
_, missing_mae = reconstruction_error(XY,
XY_completed,
missing_mask,
name="MatrixFactorization")
assert missing_mae < 0.01, "Error too high!"
def test_missforest_all_continous():
solver = MissForest(n_estimators=500)
XY_completed = solver.fit_transform(XY_incomplete) #dont need to normalization
_, missing_mae = reconstruction_error(
XY,
XY_completed,
missing_mask,
name="MissForest")
assert missing_mae < 0.3, "Error too high!"
def test_mice_column_with_low_rank_random_matrix():
mice = MICE(n_imputations=100, impute_type='col')
XY_completed = mice.complete(XY_incomplete)
_, missing_mae = reconstruction_error(
XY,
XY_completed,
missing_mask,
name="MICE (impute_type=col)")
assert missing_mae < 0.1, "Error too high with column method!"
def test_mice_row_with_low_rank_random_matrix_approximate():
mice = MICE(n_imputations=100, impute_type='pmm', n_nearest_columns=5)
XY_completed = mice.complete(XY_incomplete)
_, missing_mae = reconstruction_error(
XY,
XY_completed,
missing_mask,
name="MICE (impute_type=row)")
assert missing_mae < 0.1, "Error too high with approximate PMM method!"
def test_solver_fill_methods_with_low_rank_random_matrix():
for fill_method in ("zero", "mean", "median", "min", "random"):
imputer = SimpleFill(fill_method=fill_method)
XY_completed = imputer.fit_transform(XY_incomplete)
_, missing_mae = reconstruction_error(
XY,
XY_completed,
missing_mask,
name="Solver with fill_method=%s" % fill_method)
assert missing_mae < 5, "Error too high for Solver with %s fill method!" % fill_method
def test_iterative_imputer_with_low_rank_random_matrix_approximate():
imputer = IterativeImputer(n_iter=50, n_nearest_features=5, random_state=0)
XY_completed = imputer.fit_transform(XY_incomplete)
_, missing_mae = reconstruction_error(
XY,
XY_completed,
missing_mask,
name="IterativeImputer with n_nearest_features=5")
assert missing_mae < 0.1, "Error too high with IterativeImputer " \
"method using n_nearest_features=5!"
def test_auto_encoder_with_low_rank_random_matrix():
solver = AutoEncoder(
hidden_layer_sizes=None,
hidden_activation="tanh",
optimizer="adam",
recurrent_weight=0.0)
XY_completed = solver.complete(
XY_incomplete)
_, missing_mae = reconstruction_error(XY, XY_completed, missing_mask)
assert missing_mae < 0.1, "Error too high!"
def test_matrix_factorization_with_low_rank_random_matrix():
solver = MatrixFactorization(learning_rate=0.01,
rank=3,
l2_penalty=0,
min_improvement=1e-6)
XY_completed = solver.complete(XY_incomplete)
_, missing_mae = reconstruction_error(XY,
XY_completed,
missing_mask,
name="MatrixFactorization")
assert missing_mae < 0.1, "Error too high!"
def test_matrix_factorization_with_low_rank_random_matrix():
solver = MatrixFactorization(
rank=3,
l1_penalty=0,
l2_penalty=0)
XY_completed = solver.complete(XY_incomplete)
_, missing_mae = reconstruction_error(
XY,
XY_completed,
missing_mask,
name="MatrixFactorization")
assert missing_mae < 0.01, "Error too high!"
def test_iterative_imputer_train_test_with_low_rank_random_matrix():
XY_incomplete_train = XY_incomplete[:250]
XY_incomplete_test = XY_incomplete[250:]
XY_test = XY[250:]
imputer = IterativeImputer(n_iter=50, random_state=0)
imputer.fit(XY_incomplete_train)
XY_completed_test = imputer.transform(XY_incomplete_test)
_, missing_mae = reconstruction_error(XY_test,
XY_completed_test,
missing_mask,
name="IterativeImputer Train/Test")
assert missing_mae < 0.1, "Error too high with IterativeImputer train/test method!"
def test_iterative_imputer_as_mice_with_low_rank_random_matrix_approximate():
n_imputations = 5
XY_completed = []
for i in range(n_imputations):
imputer = IterativeImputer(n_iter=5,
sample_posterior=True,
random_state=i)
XY_completed.append(imputer.fit_transform(XY_incomplete))
_, missing_mae = reconstruction_error(XY,
np.mean(XY_completed, axis=0),
missing_mask,
name="IterativeImputer as MICE")
assert missing_mae < 0.1, "Error too high with IterativeImputer as MICE!"
def test_auto_encoder_with_low_rank_random_matrix():
solver = AutoEncoder(hidden_layer_sizes=None, hidden_activation="tanh", optimizer="adam", recurrent_weight=0.0)
XY_completed = solver.complete(XY_incomplete)
_, missing_mae = reconstruction_error(XY, XY_completed, missing_mask)
assert missing_mae < 0.1, "Error too high!"
def test_nuclear_norm_minimization_with_low_rank_random_matrix():
solver = NuclearNormMinimization(require_symmetric_solution=False)
XY_completed = solver.complete(XY_incomplete[:100])
_, missing_mae = reconstruction_error(
XY[:100], XY_completed, missing_mask[:100], name="NuclearNorm")
assert missing_mae < 0.1, "Error too high!"
def test_matrix_factorization_with_low_rank_random_matrix():
solver = MatrixFactorization(learning_rate=0.02, rank=5)
XY_completed = solver.fit_transform(XY_incomplete)
_, missing_mae = reconstruction_error(XY, XY_completed, missing_mask, name="MatrixFactorization")
assert missing_mae < 0.1, "Error too high!"
