def test_batch_mean_center():
X = data.generate_positive_sparse_matrix()
sample_idx = np.random.choice([0, 1], X.shape[0], replace=True)
X[sample_idx == 1] += 1
Y = X.copy()
Y[sample_idx == 0] -= np.mean(Y[sample_idx == 0], axis=0)[None, :]
Y[sample_idx == 1] -= np.mean(Y[sample_idx == 1], axis=0)[None, :]
utils.assert_all_close(np.mean(Y[sample_idx == 0], axis=0), 0)
utils.assert_all_close(np.mean(Y[sample_idx == 1], axis=0), 0)
matrix.test_dense_matrix_types(
X, utils.assert_transform_equivalent, Y=Y,
transform=partial(
scprep.normalize.batch_mean_center,
sample_idx=sample_idx))
matrix.test_sparse_matrix_types(
X, utils.assert_transform_raises,
transform=partial(
scprep.normalize.batch_mean_center,
sample_idx=sample_idx),
exception=ValueError)
X = data.generate_positive_sparse_matrix()
Y = X.copy()
Y -= np.mean(Y, axis=0)[None, :]
matrix.test_dense_matrix_types(
X, utils.assert_transform_equivalent, Y=Y,
transform=partial(
scprep.normalize.batch_mean_center))
matrix.test_sparse_matrix_types(
X, utils.assert_transform_raises,
transform=partial(
scprep.normalize.batch_mean_center),
exception=ValueError)
def test_batch_mean_center_one_sample(self):
Y = self.X.copy()
Y -= np.mean(Y, axis=0)[None, :]
matrix.test_dense_matrix_types(
self.X,
utils.assert_transform_equivalent,
Y=Y,
transform=scprep.normalize.batch_mean_center)
def test_batch_mean_center(self):
X = self.X.copy()
X[self.sample_idx == 1] += 1
Y = X.copy()
Y[self.sample_idx == 0] -= np.mean(Y[self.sample_idx == 0],
axis=0)[None, :]
Y[self.sample_idx == 1] -= np.mean(Y[self.sample_idx == 1],
axis=0)[None, :]
utils.assert_all_close(np.mean(Y[self.sample_idx == 0], axis=0), 0)
utils.assert_all_close(np.mean(Y[self.sample_idx == 1], axis=0), 0)
matrix.test_dense_matrix_types(
X,
utils.assert_transform_equivalent,
Y=Y,
transform=scprep.normalize.batch_mean_center,
sample_idx=self.sample_idx)
def test_log_transform():
X = data.generate_positive_sparse_matrix()
Y = np.log10(X + 1)
matrix.test_all_matrix_types(
X,
utils.assert_transform_equivalent,
Y=Y,
transform=scprep.transform.log,
base=10,
)
Y = np.log(X + 1)
matrix.test_all_matrix_types(
X,
utils.assert_transform_equivalent,
Y=Y,
transform=scprep.transform.log,
base="e",
)
Y = np.log2(X + 1)
matrix.test_all_matrix_types(
X,
utils.assert_transform_equivalent,
Y=Y,
transform=scprep.transform.log,
base=2,
)
Y = np.log2(X + 5)
def test_fun(X):
utils.assert_warns_message(
RuntimeWarning,
"log transform on sparse data requires pseudocount = 1",
scprep.transform.log,
data=X,
base=2,
pseudocount=5,
)
matrix.test_sparse_matrix_types(X, test_fun)
matrix.test_dense_matrix_types(
X,
utils.assert_transform_equivalent,
Y=Y,
transform=scprep.transform.log,
base=2,
pseudocount=5,
)
def test_dense(self):
matrix.test_dense_matrix_types(
self.X,
utils.assert_transform_equals,
Y=self.Y_random,
transform=scprep.reduce.pca,
n_components=100,
seed=42,
)
matrix.test_all_matrix_types(
self.X,
utils.assert_transform_equals,
Y=self.Y_random,
transform=scprep.reduce.pca,
n_components=100,
seed=42,
method="dense",
check=partial(utils.assert_all_close, atol=1e-10),
)
def test_pca():
X = data.generate_positive_sparse_matrix(shape=[100, 1000])
Y = decomposition.PCA(100, random_state=42).fit_transform(X)
matrix.test_dense_matrix_types(X,
utils.assert_transform_equals,
Y=Y,
transform=scprep.reduce.pca,
n_pca=100,
seed=42)
Y = decomposition.PCA(50, svd_solver='full').fit_transform(X)
matrix.test_sparse_matrix_types(X,
utils.assert_transform_equals,
Y=Y,
transform=scprep.reduce.pca,
check=partial(utils.assert_all_close,
rtol=1e-3,
atol=1e-5),
n_pca=50,
svd_multiples=8,
seed=42)
def test_log_transform():
X = data.generate_positive_sparse_matrix()
Y = np.log10(X + 1)
matrix.test_all_matrix_types(X,
utils.assert_transform_equivalent,
Y=Y,
transform=scprep.transform.log,
base=10)
Y = np.log(X + 1)
matrix.test_all_matrix_types(X,
utils.assert_transform_equivalent,
Y=Y,
transform=scprep.transform.log,
base='e')
Y = np.log2(X + 1)
matrix.test_all_matrix_types(X,
utils.assert_transform_equivalent,
Y=Y,
transform=scprep.transform.log,
base=2)
Y = np.log2(X + 5)
assert_warns_message(
RuntimeWarning,
"log transform on sparse data requires pseudocount = 1",
scprep.transform.log,
data=sparse.csr_matrix(X),
base=2,
pseudocount=5)
assert_warns_message(
RuntimeWarning,
"log transform on sparse data requires pseudocount = 1",
scprep.transform.log,
data=pd.SparseDataFrame(X, default_fill_value=0.0),
base=2,
pseudocount=5)
matrix.test_dense_matrix_types(X,
utils.assert_transform_equivalent,
Y=Y,
transform=scprep.transform.log,
base=2,
pseudocount=5)