mirror of
https://github.com/chanzuckerberg/cellxgene.git
synced 2026-10-01 20:18:11 +08:00
bmccandless
907cc634f5
This PR contains a refactoring to make adding new features easier. The new features include supporting the tiledb format, and the multi dataset application. The refactoring includes Simplifying the directory structure and files. a class structure to handle annotations (currently one type: AnnotationsLocalFile). a class to handle application configuration a class structure to handle matrix data (currently AnndataAdaptor and CxgAdaptor). CxgAdaptor uses tiledb. Algorithms that were previously dependent on the scanpy anndata object are now generalized to work with an abstract interface. The multi dataset option is not fully supported yet, and so the option to use it is hidden. Use "cli launch --dataroot ..." To access this feature. All combinations of app single dataset/ app multi dataset and AnndataAdaptor/CxgAdaptor work with all the features, such as annotations, ontologies, diffexp.
67 lines
2.8 KiB
Python
67 lines
2.8 KiB
Python
import pytest
|
|
import unittest
|
|
import warnings
|
|
import math
|
|
|
|
import decode_fbs
|
|
|
|
from server.data_anndata.anndata_adaptor import AnndataAdaptor
|
|
from server.common.errors import FilterError
|
|
from server.common.data_locator import DataLocator
|
|
|
|
|
|
class NaNTest(unittest.TestCase):
|
|
def setUp(self):
|
|
self.args = {
|
|
"layout": ["umap"],
|
|
"max_category_items": 100,
|
|
"obs_names": None,
|
|
"var_names": None,
|
|
"diffexp_lfc_cutoff": 0.01,
|
|
}
|
|
with warnings.catch_warnings():
|
|
warnings.simplefilter("ignore", category=UserWarning)
|
|
self.data = AnndataAdaptor(DataLocator("test/test_datasets/nan.h5ad"), self.args)
|
|
self.data._create_schema()
|
|
|
|
def test_load(self):
|
|
with self.assertWarns(UserWarning):
|
|
AnndataAdaptor(DataLocator("test/test_datasets/nan.h5ad"), self.args)
|
|
|
|
def test_init(self):
|
|
self.assertEqual(self.data.cell_count, 100)
|
|
self.assertEqual(self.data.gene_count, 100)
|
|
epsilon = 0.000_005
|
|
self.assertTrue(self.data.data.X[0, 0] - -0.171_469_51 < epsilon)
|
|
|
|
def test_dataframe(self):
|
|
data_frame_var = decode_fbs.decode_matrix_FBS(self.data.data_frame_to_fbs_matrix(None, "var"))
|
|
self.assertIsNotNone(data_frame_var)
|
|
self.assertEqual(data_frame_var["n_rows"], 100)
|
|
self.assertEqual(data_frame_var["n_cols"], 100)
|
|
self.assertTrue(math.isnan(data_frame_var["columns"][3][3]))
|
|
|
|
with pytest.raises(FilterError):
|
|
self.data.data_frame_to_fbs_matrix("an erroneous filter", "var")
|
|
with pytest.raises(FilterError):
|
|
filter_ = {"filter": {"obs": {"index": [1, 99, [200, 300]]}}}
|
|
self.data.data_frame_to_fbs_matrix(filter_["filter"], "var")
|
|
|
|
def test_dataframe_obs_not_implemented(self):
|
|
with self.assertRaises(ValueError) as cm:
|
|
decode_fbs.decode_matrix_FBS(self.data.data_frame_to_fbs_matrix(None, "obs"))
|
|
self.assertIsNotNone(cm.exception)
|
|
|
|
def test_annotation(self):
|
|
annotations = decode_fbs.decode_matrix_FBS(self.data.annotation_to_fbs_matrix("obs"))
|
|
obs_index_col_name = self.data.schema["annotations"]["obs"]["index"]
|
|
self.assertEqual(annotations["col_idx"], [obs_index_col_name, "n_genes", "percent_mito", "n_counts", "louvain"])
|
|
self.assertEqual(annotations["n_rows"], 100)
|
|
self.assertTrue(math.isnan(annotations["columns"][2][0]))
|
|
|
|
annotations = decode_fbs.decode_matrix_FBS(self.data.annotation_to_fbs_matrix("var"))
|
|
var_index_col_name = self.data.schema["annotations"]["var"]["index"]
|
|
self.assertEqual(annotations["col_idx"], [var_index_col_name, "n_cells", "var_with_nans"])
|
|
self.assertEqual(annotations["n_rows"], 100)
|
|
self.assertTrue(math.isnan(annotations["columns"][2][0]))
|