def test_mean(self, x, xd):
if sys.version_info[0] == 2 and isinstance(
xd, zappy.beam.array.BeamZappyArray): # TODO: fix this
return
meand = np.mean(xd)
mean = np.mean(x)
assert meand == pytest.approx(mean)
def filter_genes_fano_deprecated(X, Ecutoff, Vcutoff):
"""Filter genes by fano factor and mean.
See `filter_genes_dispersion`.
Reference: Weinreb et al. (2017).
"""
if issparse(X):
raise ValueError('Not defined for sparse input. See `filter_genes_dispersion`.')
mean_filter = np.mean(X, axis=0) > Ecutoff
var_filter = np.var(X, axis=0) / (np.mean(X, axis=0) + .0001) > Vcutoff
gene_subset = np.nonzero(np.all([mean_filter, var_filter], axis=0))[0]
return gene_subset
def filter_genes_cv_deprecated(X, Ecutoff, cvFilter):
"""Filter genes by coefficient of variance and mean.
See `filter_genes_dispersion`.
Reference: Weinreb et al. (2017).
"""
if issparse(X):
raise ValueError('Not defined for sparse input. See `filter_genes_dispersion`.')
mean_filter = np.mean(X, axis=0) > Ecutoff
var_filter = np.std(X, axis=0) / (np.mean(X, axis=0) + .0001) > cvFilter
gene_subset = np.nonzero(np.all([mean_filter, var_filter], axis=0))[0]
return gene_subset
def normalize_per_cell_weinreb16_deprecated(X,
max_fraction=1,
mult_with_mean=False):
"""Normalize each cell [Weinreb17]_.
This is a deprecated version. See `normalize_per_cell` instead.
Normalize each cell by UMI count, so that every cell has the same total
count.
Parameters
----------
X : np.ndarray
Expression matrix. Rows correspond to cells and columns to genes.
max_fraction : float, optional
Only use genes that make up more than max_fraction of the total
reads in every cell.
mult_with_mean: bool, optional
Multiply the result with the mean of total counts.
Returns
-------
X_norm : np.ndarray
Normalized version of the original expression matrix.
"""
if issparse(X):
raise ValueError('Sparse input not allowed. '
'Consider `sc.pp.normalize_per_cell` instead.')
if max_fraction < 0 or max_fraction > 1:
raise ValueError('Choose max_fraction between 0 and 1.')
counts_per_cell = np.sum(X, axis=1)
if max_fraction == 1:
X_norm = X / counts_per_cell[:, np.newaxis]
return X_norm
# restrict computation of counts to genes that make up less than
# constrain_theshold of the total reads
tc_tiled = np.tile(counts_per_cell[:, np.newaxis], (1, X.shape[1]))
included = np.all(X <= tc_tiled * max_fraction, axis=0)
tc_include = np.sum(X[:, included], axis=1)
tc_tiled = np.tile(tc_include[:, np.newaxis], (1, X.shape[1])) + 1e-6
X_norm = X / tc_tiled
if mult_with_mean:
X_norm *= np.mean(counts_per_cell)
return X_norm
def zscore_deprecated(X):
"""Z-score standardize each variable/gene in X.
Use `scale` instead.
Reference: Weinreb et al. (2017).
Parameters
----------
X : np.ndarray
Data matrix. Rows correspond to cells and columns to genes.
Returns
-------
XZ : np.ndarray
Z-score standardized version of the data matrix.
"""
means = np.tile(np.mean(X, axis=0)[None, :], (X.shape[0], 1))
stds = np.tile(np.std(X, axis=0)[None, :], (X.shape[0], 1))
return (X - means) / (stds + .0001)
def normalize_per_cell_weinreb16_deprecated(X,
max_fraction=1,
mult_with_mean=False):
"""Normalize each cell [Weinreb17]_.
This is a deprecated version. See `normalize_per_cell` instead.
Normalize each cell by UMI count, so that every cell has the same total
count.
Parameters
----------
X : np.ndarray
Expression matrix. Rows correspond to cells and columns to genes.
max_fraction : float, optional
Only use genes that make up more than max_fraction of the total
reads in every cell.
mult_with_mean: bool, optional
Multiply the result with the mean of total counts.
Returns
-------
X_norm : np.ndarray
Normalized version of the original expression matrix.
"""
if max_fraction < 0 or max_fraction > 1:
raise ValueError('Choose max_fraction between 0 and 1.')
counts_per_cell = X.sum(1).A1 if issparse(X) else X.sum(1)
gene_subset = np.all(X <= counts_per_cell[:, None] * max_fraction, axis=0)
if issparse(X): gene_subset = gene_subset.A1
tc_include = X[:, gene_subset].sum(1).A1 if issparse(
X) else X[:, gene_subset].sum(1)
X_norm = X.multiply(csr_matrix(
1 / tc_include[:, None])) if issparse(X) else X / tc_include[:, None]
if mult_with_mean:
X_norm *= np.mean(counts_per_cell)
return X_norm
def test_mean_rows(self, x, xd):
xd = np.mean(xd, axis=1)
x = np.mean(x, axis=1)
assert_allclose(xd.asndarray(), x)