def _mat_mat_corr_sparse(
X: csr_matrix,
Y: np.ndarray,
) -> np.ndarray:
"""\
This function is borrow from cellrank
"""
n = X.shape[1]
X_bar = np.reshape(np.array(X.mean(axis=1)), (-1, 1))
X_std = np.reshape(np.sqrt(np.array(X.power(2).mean(axis=1)) - (X_bar**2)),
(-1, 1))
y_bar = np.reshape(np.mean(Y, axis=0), (1, -1))
y_std = np.reshape(np.std(Y, axis=0), (1, -1))
with np.warnings.catch_warnings():
np.warnings.filterwarnings(
"ignore", r"invalid value encountered in true_divide")
return (X @ Y - (n * X_bar * y_bar)) / ((n - 1) * X_std * y_std)
def t_test(
X: csr_matrix,
cluster_labels: List[str],
cond_labels: List[str],
gene_names: List[str],
n_jobs: int,
temp_folder: str,
verbose: bool,
) -> List[pd.DataFrame]:
""" Run Welch's t-test, triggering calc_t in parallel
"""
start = time.time()
sum_vec = sum2_vec = None
if cond_labels is None:
sum_vec = X.sum(axis=0).A1
sum2_vec = X.power(2).sum(axis=0).A1
result_list = Parallel(n_jobs=n_jobs,
max_nbytes=1e7,
temp_folder=temp_folder)(delayed(calc_t)(
clust_id,
X.data,
X.indices,
X.indptr,
X.shape,
cluster_labels,
cond_labels,
gene_names,
sum_vec,
sum2_vec,
verbose,
) for clust_id in cluster_labels.categories)
end = time.time()
if verbose:
logger.info(
"Welch's t-test is done. Time spent = {:.2f}s.".format(end -
start))
return result_list
def axis_norms(X: sparse.csr_matrix,
norm: str = "l1",
axis: int = 1) -> np.ndarray:
if norm == "l1":
return np.asarray(X.sum(axis=axis)).reshape(-1)
return np.sqrt(np.asarray(X.power(2).sum(axis=axis)).reshape(-1))