Files
cellxgene/server/test/test_scanpy_engine_data_load.py
Bruce Martin 20317fd08f Add URL data locators to launch sub-command (#920)
* initial commit of URL support for launch

* lint

* modify tests to use new data locator

* add locator unit tests

* fix typo in faq

* more lint

* update faq per PR review
2019-09-15 09:01:53 -07:00

88 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,
}
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)