fork/cellxgene
1
0
Fork 0
mirror of https://github.com/chanzuckerberg/cellxgene.git synced 2026-10-01 07:38:11 +08:00
Code Issues Packages Projects Releases Wiki Activity

remove --nan-to-num CLI parameter (#548)

Browse Source 
* remove --nan-to-num CLI parameter

* factor tests better

* lint - remove unused variables
This commit is contained in:
Bruce Martin
2019-01-10 15:03:03 -08:00
committed by GitHub
parent f876a0091a
commit 5d60505407
8 changed files with 34 additions and 183 deletions
Download Patch File Download Diff File Expand all files Collapse all files
server/app/scanpy_engine/scanpy_engine.py
+3 -70
View File
@@ -42,10 +42,6 @@ class ScanpyEngine(CXGDriver):
self.diffexp_options = ["ttest"]
self._create_schema()
# TODO: temporary work-arounds
if args["nan_to_num"]:
self._IEEE754_special_values_workaround()
def _alias_annotation_names(self, axis, name):
"""
Do all user-specified annotation aliasing.
@@ -201,71 +197,6 @@ class ScanpyEngine(CXGDriver):
f"to solve this problem. "
)
def _IEEE754_special_values_workaround(self):
"""
TODO: temporary workaround
Because all floating point data is serialized to JSON, and JSON has no means of representing
non-finite, floating point special values (NaN, +/-Infinity, etc), we include this temporary
work-around.
This will likely be removed in the future, contingent upon improved marshalling.
Where non-finite floating point is present in obs, var or X:
* issue a warning to the user that these values will be convert to finite numbers.
* set NaN to zero, and Infinities to min/max of the element.
"""
# annotations
for ax in Axis:
curr_axis = getattr(self.data, str(ax))
for ann in curr_axis:
dtype = curr_axis[ann].dtype
if dtype.kind == "f":
finite_idx = np.isfinite(curr_axis[ann])
if not finite_idx.all():
curr_axis.loc[np.isnan(curr_axis[ann]), ann] = 0
curr_axis.loc[np.isneginf(curr_axis[ann]), ann] = curr_axis[
ann
][finite_idx].min()
curr_axis.loc[np.isposinf(curr_axis[ann]), ann] = curr_axis[
ann
][finite_idx].max()
warnings.warn(
f"{str(ax).title()} annotation '{ann}' contains floating point NaN or Infinities. "
f"These will be converted to finite values."
)
# X
non_finite_X_found = False
if sparse.issparse(self.data._X):
coo = self.data._X.tocoo()
finite_idx = np.isfinite(coo.data)
if not finite_idx.all():
non_finite_X_found = True
coo.data[np.isnan(coo.data)] = 0
coo.data[np.isneginf(coo.data)] = np.min(coo.data[finite_idx])
coo.data[np.isposinf(coo.data)] = np.max(coo.data[finite_idx])
coo.eliminate_zeros()
_X = coo.asformat(self.data._X.getformat())
self.data._X = _X
else:
_X = self.data._X
finite_idx = np.isfinite(_X.flat)
if not finite_idx.all():
non_finite_X_found = True
min_X = _X.flat[finite_idx].min()
max_X = _X.flat[finite_idx].max()
_X[np.isnan(_X)] = 0
_X[np.isneginf(_X)] = min_X
_X[np.isposinf(_X)] = max_X
if non_finite_X_found:
warnings.warn(
"Dataframe X contains floating point NaN or Infinities. "
"These will be converted to finite values."
)
def filter_dataframe(self, filter):
"""
Filter cells from data and return a subset of the data. They can operate on both obs and var dimension with
@@ -480,7 +411,9 @@ class ScanpyEngine(CXGDriver):
raise FilterError("filtering on obs unsupported")
# Currently only handles VAR dimension
X = self.data._X[:, var_selector]
X = self.data._X
if var_selector is not None:
X = X[:, var_selector]
return encode_matrix_fbs(X, col_idx=np.nonzero(var_selector)[0], row_idx=None)
def diffexp_topN(self, obsFilterA, obsFilterB, top_n=None, interactive_limit=None):