Files
cellxgene/server/test/test_scanpy_engine_data_load.py
Bruce Martin 3660a6cc27 Experimental - manual annotations (#837)
* 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
2019-09-18 07:33:41 -04:00

89 lines
2.9 KiB
Python

import unittest
import json
from server.app.scanpy_engine.scanpy_engine import ScanpyEngine
from server.app.util.errors import DriverError
from server.app.util.data_locator import DataLocator
class DataLoadEngineTest(unittest.TestCase):
"""
Test file loading, including deferred loading/update.
"""
def setUp(self):
self.data_file = DataLocator("example-dataset/pbmc3k.h5ad")
self.data = ScanpyEngine()
def test_init(self):
self.assertIsNone(self.data.data)
def test_delayed_load_args(self):
args = {
"layout": ["tsne"],
"max_category_items": 1000,
"obs_names": "foo",
"var_names": "bar",
"diffexp_lfc_cutoff": 0.1,
"label_file": None,
}
self.data.update(args=args)
self.assertEqual(args, self.data.config)
def test_requires_data(self):
with self.assertRaises(DriverError):
self.data._create_schema()
def test_delayed_load_data(self):
self.data.update(data=self.data_file)
self.data._create_schema()
self.assertEqual(self.data.cell_count, 2638)
self.assertEqual(self.data.gene_count, 1838)
epsilon = 0.000_005
self.assertTrue(self.data.data.X[0, 0] - -0.171_469_51 < epsilon)
def test_diffexp_topN(self):
self.data.update(data=self.data_file)
f1 = {"filter": {"obs": {"index": [[0, 500]]}}}
f2 = {"filter": {"obs": {"index": [[500, 1000]]}}}
result = json.loads(self.data.diffexp_topN(f1["filter"], f2["filter"]))
self.assertEqual(len(result), 10)
result = json.loads(self.data.diffexp_topN(f1["filter"], f2["filter"], 20))
self.assertEqual(len(result), 20)
class DataLocatorEngineTest(unittest.TestCase):
"""
Test various types of data locators we expect to consume
"""
def setUp(self):
self.args = {
"layout": ["umap"],
"max_category_items": 100,
"obs_names": None,
"var_names": None,
"diffexp_lfc_cutoff": 0.01,
}
def stdAsserts(self, data):
""" run these each time we load the data """
self.assertIsNotNone(data)
self.assertEqual(data.cell_count, 2638)
self.assertEqual(data.gene_count, 1838)
def test_posix_file(self):
locator = DataLocator("example-dataset/pbmc3k.h5ad")
data = ScanpyEngine(locator, self.args)
self.stdAsserts(data)
def test_url_https(self):
url = "https://raw.githubusercontent.com/chanzuckerberg/cellxgene/master/example-dataset/pbmc3k.h5ad"
locator = DataLocator(url)
data = ScanpyEngine(locator, self.args)
self.stdAsserts(data)
def test_url_http(self):
url = "http://raw.githubusercontent.com/chanzuckerberg/cellxgene/master/example-dataset/pbmc3k.h5ad"
locator = DataLocator(url)
data = ScanpyEngine(locator, self.args)
self.stdAsserts(data)