mirror of
https://github.com/chanzuckerberg/cellxgene.git
synced 2026-09-20 11:28:47 +08:00
Bruce Martin
3660a6cc27
* icons, partway * redux for values * onChange * cancel * annotations lifecycle for category names * copy categorical * edit category * add Dataframe.withColsFrom * render user annotations; default add/delete annotation category * add label name to actions * category name edit * error checking improvements * change schema field isUserAnnotation to writable * always have an unassigned label; implement delete label * implement add new label and edit label name * label current cell selection * fix select exact bug in crossfilter * clean up categorical reducer * fix tests * remove debugging printf * implement subset/reset for user annotations * undo redo support for user annotations * remove duplicate button from categories * add modal * remove obsolete duplicate annotation reducers * remove old debugging printf * connect modal to annotation create and dup * initial full-stack wiring * finish up end-to-end wiring * fix existing unit tests * fix pytests to match new schema API * remove debugging printfs * add label file rotation * remove obsolete comment * add fbs encode/decode tests * add tests for writable annotations * simplify code * fix hashing bug with FBS encoding * lint * fix smoke tests * improve error checking in Dataframe.withColsFrom * add unit test for Dataframe.withColsFrom * add unit test for Dataframe.columns and Dataframe.renameCol * fix bug in FBS encode, add better error checks, refactor * add FBS encode/decode test * add clarifying comment * clean up action type names; fix state inconsistency in crossfilter update * change autosave timer to 2.5sec * sort categorical metadata render order so it remains consistent * add temporary autogenerated label for add-new-label operation * fix hover-over label menu interference with cell highlighting * remove debugging code * add missing reducer cases & fix typo * make dataframe memoize more general purpose * add dev mode for annos * fix error on select duplicate * handle zero occupancy categories * correctly maintain unclipped AND clipped world * correctly handle zero length FBS matrix and label files * ensure all writable categorical schema contains an unassigned category * handle case where building occupancy stack for category with no members * dialog for creating label, disable button if duplicate or empty * visually separate writeable * edit category * fix edit category name * remove debugging code * fix edit annotation label * visually define unassigned, change options * Pull in requirements.txt from `master` * label currently selected cells * duplicate label * lint * fix pytest merge issues * rename --label-file to --experimental-label-file * remove debugging console log * spelling error fix; fix bug found in PR review. * lint
95 lines
3.7 KiB
Python
95 lines
3.7 KiB
Python
import unittest
|
|
import pandas as pd
|
|
import numpy as np
|
|
from scipy import sparse
|
|
|
|
import decode_fbs
|
|
from server.app.util.fbs.matrix import encode_matrix_fbs, decode_matrix_fbs
|
|
|
|
|
|
class FbsTests(unittest.TestCase):
|
|
"""Test Case for Matrix FBS data encode/decode """
|
|
|
|
def test_encode_boundary(self):
|
|
""" test various boundary checks """
|
|
|
|
# row indexing is unsupported
|
|
with self.assertRaises(ValueError):
|
|
encode_matrix_fbs(matrix=pd.DataFrame(), row_idx=[])
|
|
|
|
# matrix must be 2D
|
|
with self.assertRaises(ValueError):
|
|
encode_matrix_fbs(matrix=np.zeros((3, 2, 1)))
|
|
with self.assertRaises(ValueError):
|
|
encode_matrix_fbs(matrix=np.ones((10,)))
|
|
|
|
def fbs_checks(self, fbs, dims, expected_types, expected_column_idx):
|
|
d = decode_fbs.decode_matrix_FBS(fbs)
|
|
print(d)
|
|
self.assertEqual(d["n_rows"], dims[0])
|
|
self.assertEqual(d["n_cols"], dims[1])
|
|
self.assertIsNone(d["row_idx"])
|
|
self.assertEqual(len(d["columns"]), dims[1])
|
|
for i in range(0, len(d["columns"])):
|
|
self.assertEqual(len(d["columns"][i]), dims[0])
|
|
self.assertIsInstance(d["columns"][i], expected_types[i][0])
|
|
if (expected_types[i][1] is not None):
|
|
self.assertEqual(d["columns"][i].dtype, expected_types[i][1])
|
|
if expected_column_idx is not None:
|
|
self.assertSetEqual(set(expected_column_idx), set(d["col_idx"]))
|
|
|
|
def test_encode_DataFrame(self):
|
|
df = pd.DataFrame(
|
|
data={
|
|
'a': np.zeros((10,), dtype=np.float32),
|
|
'b': np.ones((10,), dtype=np.int64),
|
|
'c': np.array([i for i in range(0, 10)], dtype=np.uint16),
|
|
'd': pd.Series(['x', 'y', 'z', 'x', 'y', 'z', 'a', 'x', 'y', 'z'], dtype='category')
|
|
})
|
|
expected_types = (
|
|
(np.ndarray, np.float32),
|
|
(np.ndarray, np.int32),
|
|
(np.ndarray, np.uint32),
|
|
(list, None)
|
|
)
|
|
fbs = encode_matrix_fbs(matrix=df, row_idx=None, col_idx=df.columns)
|
|
self.fbs_checks(fbs, (10, 4), expected_types, ['a', 'b', 'c', 'd'])
|
|
|
|
def test_encode_ndarray(self):
|
|
arr = np.zeros((3, 2), dtype=np.float32)
|
|
expected_types = (
|
|
(np.ndarray, np.float32),
|
|
(np.ndarray, np.float32),
|
|
(np.ndarray, np.float32)
|
|
)
|
|
fbs = encode_matrix_fbs(matrix=arr, row_idx=None, col_idx=None)
|
|
self.fbs_checks(fbs, (3, 2), expected_types, None)
|
|
|
|
def test_encode_sparse(self):
|
|
csc = sparse.csc_matrix(np.array([[0, 1, 2], [3, 0, 4]]))
|
|
expected_types = (
|
|
(np.ndarray, np.int32),
|
|
(np.ndarray, np.int32),
|
|
(np.ndarray, np.int32)
|
|
)
|
|
fbs = encode_matrix_fbs(matrix=csc, row_idx=None, col_idx=None)
|
|
self.fbs_checks(fbs, (2, 3), expected_types, None)
|
|
|
|
def test_roundtrip(self):
|
|
dfSrc = pd.DataFrame(
|
|
data={
|
|
'a': np.zeros((10,), dtype=np.float32),
|
|
'b': np.ones((10,), dtype=np.int64),
|
|
'c': np.array([i for i in range(0, 10)], dtype=np.uint16),
|
|
'd': pd.Series(['x', 'y', 'z', 'x', 'y', 'z', 'a', 'x', 'y', 'z'], dtype='category')
|
|
})
|
|
dfDst = decode_matrix_fbs(encode_matrix_fbs(matrix=dfSrc, col_idx=dfSrc.columns))
|
|
self.assertEqual(dfSrc.shape, dfDst.shape)
|
|
self.assertEqual(set(dfSrc.columns), set(dfDst.columns))
|
|
for c in dfSrc.columns:
|
|
self.assertTrue(c in dfDst.columns)
|
|
if isinstance(dfSrc[c], pd.Series):
|
|
self.assertTrue(np.all(dfSrc[c] == dfDst[c]))
|
|
else:
|
|
self.assertEqual(dfSrc[c], dfDst[c])
|