def __compute_statistics(self):
# Since data matrices can of mixed sparsity, we need to compute
# attributes separately for each of them.
matrices = [self.__attributes, self.__class_vars, self.__metas]
# Filter out any matrices with size 0
matrices = list(filter(lambda tup: tup[1].size, matrices))
self._variable_types = np.array([type(var) for var in self.variables])
self._variable_names = np.array(
[var.name.lower() for var in self.variables])
self._min = self.__compute_stat(
matrices,
discrete_f=lambda x: ut.nanmin(x, axis=0),
continuous_f=lambda x: ut.nanmin(x, axis=0),
time_f=lambda x: ut.nanmin(x, axis=0),
)
self._dispersion = self.__compute_stat(
matrices,
discrete_f=_categorical_entropy,
continuous_f=coefficient_of_variation,
)
self._missing = self.__compute_stat(
matrices,
discrete_f=lambda x: ut.countnans(x, axis=0),
continuous_f=lambda x: ut.countnans(x, axis=0),
string_f=lambda x: (x == StringVariable.Unknown).sum(axis=0),
time_f=lambda x: ut.countnans(x, axis=0),
default_val=len(matrices[0]) if matrices else 0)
self._max = self.__compute_stat(
matrices,
discrete_f=lambda x: ut.nanmax(x, axis=0),
continuous_f=lambda x: ut.nanmax(x, axis=0),
time_f=lambda x: ut.nanmax(x, axis=0),
)
# Since scipy apparently can't do mode on sparse matrices, cast it to
# dense. This can be very inefficient for large matrices, and should
# be changed
def __mode(x, *args, **kwargs):
if sp.issparse(x):
x = x.todense(order="C")
# return ss.mode(x, *args, **kwargs)[0]
# Temporary replacement for scipy
return ut.nanmode(x, *args, **kwargs)[0]
self._center = self.__compute_stat(
matrices,
discrete_f=None,
continuous_f=lambda x: ut.nanmean(x, axis=0),
time_f=lambda x: ut.nanmean(x, axis=0),
)
self._median = self.__compute_stat(
matrices,
discrete_f=lambda x: __mode(x, axis=0),
continuous_f=lambda x: ut.nanmedian(x, axis=0),
time_f=lambda x: ut.nanmedian(x, axis=0),
)
def test_nanmedian_more_nonzeros(self, array):
X = np.ones((10, 10))
X[:5, 0] = np.nan
X[:6, 1] = 0
X_sparse = array(X)
np.testing.assert_array_equal(
nanmedian(X_sparse),
np.nanmedian(X)
)
def test_nanmedian_more_nonzeros(self, array):
X = np.ones((10, 10))
X[:5, 0] = np.nan
X[:6, 1] = 0
X_sparse = array(X)
np.testing.assert_array_equal(
nanmedian(X_sparse),
np.nanmedian(X)
)
def fit(self, X, Y=None):
"""
Infer row normalization parameters from the data.
:param X: Continuous data matrix.
:param Y: Grouping values
:return:
"""
# Equalize based on read depth per library / match mean read count per cell
# Must not store indices
if Y is not None:
libraries = {lib: np.where(Y == lib)[0] for lib in set(Y)}
lib_sizes = {}
for lib, rows in libraries.items():
lib_sizes[lib] = nanmedian(nansum(X[rows, :], axis=1))
self.target_row_mean = min(lib_sizes.values())
for lib in libraries:
self.size_factors[lib] = self.target_row_mean / lib_sizes[lib]
else:
self.target_row_mean = nanmedian(nansum(X, axis=1))
def test_nanmedian(self, array):
for X in self.data:
X_sparse = array(X)
np.testing.assert_array_equal(nanmedian(X_sparse), np.nanmedian(X))
def test_nanmedian(self, array):
for X in self.data:
X_sparse = array(X)
np.testing.assert_array_equal(
nanmedian(X_sparse),
np.nanmedian(X))
