fork/cellxgene
1
0
Fork 0
mirror of https://github.com/chanzuckerberg/cellxgene.git synced 2026-10-02 13:58:12 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix for incorrect stats computation in diff exp t-test (#2318)

Browse Source 
* 2211 fixes

* lint

* lint

* add missing test and bug found by test

* change terminology for count distribution

* update scanpy requirement

* update scanpy requirement
This commit is contained in:
Bruce Martin
2021-07-23 11:36:26 -07:00
committed by GitHub
parent 1ebde2213d
commit 1ea2b7fe80
28 changed files with 336 additions and 90 deletions
Download Patch File Download Diff File Expand all files Collapse all files
backend/server/data_anndata/anndata_adaptor.py
+26 -1
View File
@@ -7,8 +7,9 @@ from pandas.core.dtypes.dtypes import CategoricalDtype
from scipy import sparse
import backend.common.compute.diffexp_generic as diffexp_generic
import backend.common.compute.estimate_distribution as estimate_distribution
from backend.common.colors import convert_anndata_category_colors_to_cxg_category_colors
from backend.common.constants import Axis, MAX_LAYOUTS
from backend.common.constants import Axis, MAX_LAYOUTS, XApproxDistribution
from backend.server.common.corpora import corpora_get_props_from_anndata
from backend.common.errors import PrepareError, DatasetAccessError
from backend.common.utils.type_conversion_utils import get_schema_type_hint_of_array
@@ -28,6 +29,7 @@ class AnndataAdaptor(DataAdaptor):
def __init__(self, data_locator, app_config=None, dataset_config=None):
super().__init__(data_locator, app_config, dataset_config)
self.data = None
self.X_approx_distribution = None
self._load_data(data_locator)
self._validate_and_initialize()
@@ -190,6 +192,13 @@ class AnndataAdaptor(DataAdaptor):
self.gene_count = self.data.shape[1]
self._create_schema()
if self.dataset_config.X_approx_distribution == "auto":
"""Lazy evaluate the heuristic if we are backed."""
if not self.data.isbacked:
self.X_approx_distribution = estimate_distribution.estimate_approximate_distribution(self.data.X)
else:
self.X_approx_distribution = self.dataset_config.X_approx_distribution
# heuristic
n_values = self.data.shape[0] * self.data.shape[1]
if (n_values > 1e8 and self.server_config.adaptor__anndata_adaptor__backed is True) or (n_values > 5e8):
@@ -309,13 +318,29 @@ class AnndataAdaptor(DataAdaptor):
return convert_anndata_category_colors_to_cxg_category_colors(self.data)
def get_X_array(self, obs_mask=None, var_mask=None):
# H5Py does not support boolean indexing (masks), so convert to integer indexing
# when backed (ie, when AnnData is using H5Py indexing)
if obs_mask is None:
obs_mask = slice(None)
elif self.data.isbacked and obs_mask.dtype == bool:
obs_mask = obs_mask.nonzero()[0]
if var_mask is None:
var_mask = slice(None)
elif self.data.isbacked and var_mask.dtype == bool:
var_mask = var_mask.nonzero()[0]
X = self.data.X[obs_mask, var_mask]
return X
def get_X_approx_distribution(self) -> XApproxDistribution:
"""return the approximate distribution of the X matrix."""
if self.X_approx_distribution is None:
"""Not yet evaluated."""
assert(self.dataset_config.X_approx_distribution == "auto")
self.data = self.data.to_memory() # loads data
self.X_approx_distribution = estimate_distribution.estimate_approximate_distribution(self.data.X)
return self.X_approx_distribution
def get_shape(self):
return self.data.shape