From d44d267bda540cd258b5ec3acbb5a4c2b58214c7 Mon Sep 17 00:00:00 2001 From: Charlotte Weaver Date: Fri, 10 Aug 2018 16:40:13 -0700 Subject: [PATCH] Initial tests for the rest v2 refactor testing the annotations and the data format validation --- .travis.yml | 3 -- pytest.ini | 3 ++ server/app/scanpy_engine/scanpy_engine.py | 4 +- server/test/test_scanpy_engine.py | 60 ++++------------------- 4 files changed, 15 insertions(+), 55 deletions(-) create mode 100644 pytest.ini diff --git a/.travis.yml b/.travis.yml index 0333cbda..1b509187 100644 --- a/.travis.yml +++ b/.travis.yml @@ -14,6 +14,3 @@ script: - set -eo pipefail - flake8 server/app/ - pytest -s server/test/test_filter.py server/test/test_scanpy_engine.py - - cellxgene scanpy example-dataset/ & - - for i in {1..90}; do if http :5005/api/v0.1/initialize > /dev/null; then break; else echo "Waiting for server..."; sleep 1; fi; done - - pytest server/test/test_api.py diff --git a/pytest.ini b/pytest.ini new file mode 100644 index 00000000..d776a2bd --- /dev/null +++ b/pytest.ini @@ -0,0 +1,3 @@ +[pytest] +filterwarnings = + ignore::UserWarning \ No newline at end of file diff --git a/server/app/scanpy_engine/scanpy_engine.py b/server/app/scanpy_engine/scanpy_engine.py index 89e8acb6..c08964be 100644 --- a/server/app/scanpy_engine/scanpy_engine.py +++ b/server/app/scanpy_engine/scanpy_engine.py @@ -9,6 +9,7 @@ from scipy import stats from server.app.app import cache from server.app.driver.driver import CXGDriver + class ScanpyEngine(CXGDriver): def __init__(self, data, graph_method="umap", diffexp_method="ttest"): @@ -49,7 +50,8 @@ class ScanpyEngine(CXGDriver): def _validatate_data_types(self): if self.data.X.dtype != 'float32': - warnings.warn(f"Scanpy data matrix is in {self.data.X.dtype} format not float32. Precision may be truncated.") + warnings.warn(f"Scanpy data matrix is in {self.data.X.dtype} format not float32. " + f"Precision may be truncated.") def cells(self): return list(self.data.obs.index) diff --git a/server/test/test_scanpy_engine.py b/server/test/test_scanpy_engine.py index e346fb6c..15bff582 100644 --- a/server/test/test_scanpy_engine.py +++ b/server/test/test_scanpy_engine.py @@ -5,7 +5,7 @@ from server.app.scanpy_engine.scanpy_engine import ScanpyEngine class UtilTest(unittest.TestCase): def setUp(self): - self.data = ScanpyEngine("example-dataset/", schema="data_schema.json") + self.data = ScanpyEngine("example-dataset/") def test_init(self): self.assertEqual(self.data.cell_count, 2638) @@ -13,57 +13,15 @@ class UtilTest(unittest.TestCase): epsilon = 0.000005 self.assertTrue(self.data.data.X[0,0] - -0.17146951 < epsilon) - def test_schema(self): - self.assertEqual(self.data.schema, {'CellName': {'type': 'string', 'variabletype': 'categorical', 'displayname': 'Name', 'include': True}, 'n_genes': {'type': 'int', 'variabletype': 'continuous', 'displayname': 'Num Genes', 'include': True}, 'percent_mito': {'type': 'float', 'variabletype': 'continuous', 'displayname': 'Mitochondrial Percentage', 'include': True}, 'n_counts': {'type': 'float', 'variabletype': 'continuous', 'displayname': 'Num Counts', 'include': True}, 'louvain': {'type': 'string', 'variabletype': 'categorical', 'displayname': 'Louvain Cluster', 'include': True}}) - - def test_cells(self): - cells = self.data.cells() - self.assertIn("AAACATACAACCAC-1", cells) - self.assertEqual(len(cells), 2638) - - def test_genes(self): - genes = self.data.genes() - self.assertIn("SEPT4", genes) - self.assertEqual(len(genes), 1838) - - def test_filter_categorical(self): - filter = {"louvain": {"variable_type": "categorical", "value_type": "string", "query": ["B cells"]}} - filtered_data = self.data.filter_cells(filter) - self.assertEqual(filtered_data.shape, (342, 1838)) - louvain_vals = filtered_data.obs['louvain'].tolist() - self.assertIn("B cells", louvain_vals) - self.assertNotIn("NK cells", louvain_vals) - - def test_filter_continuous(self): - # print(self.data.data.obs["n_genes"].tolist()) - filter = {"n_genes": {"variable_type": "continuous", "value_type": "int", "query": {"min": 300, "max": 400}}} - filtered_data = self.data.filter_cells(filter) - self.assertEqual(filtered_data.shape, (71, 1838)) - n_genes_vals = filtered_data.obs['n_genes'].tolist() - for val in n_genes_vals: - self.assertTrue(300 <= val <= 400) - - def test_metadata(self): - metadata = self.data.metadata(df=self.data.data) - self.assertEqual(len(metadata), 2638) - self.assertIn('louvain', metadata[0]) - - @unittest.skip("Umap not producing the same graph on different systems, even with the same seed. Skipping for now") - def test_create_graph(self): - graph = self.data.create_graph(df=self.data.data) - self.assertEqual(graph[0][1], 0.5545382653143183) - self.assertEqual(graph[0][2], 0.6021833809031731) - - def test_diffexp(self): - diffexp = self.data.diffexp(["AAACATACAACCAC-1", "AACCGATGGTCATG-1"], ["CCGATAGACCTAAG-1", "GGTGGAGAAGTAGA-1"], 0.5, 7) - self.assertEqual(diffexp["celllist1"]["topgenes"], ['EBNA1BP2', 'DIAPH1', 'SLC25A11', 'SNRNP27', 'COMMD8', 'COTL1', 'GTF3A']) - - def test_expression(self): - expression = self.data.expression(cells=["AAACATACAACCAC-1"]) - data_exp = self.data.data[["AAACATACAACCAC-1"], :].X - for idx in range(len(expression["cells"][0]["e"])): - self.assertEqual(expression["cells"][0]["e"][idx], data_exp[idx]) + def test_mandatory_annotations(self): + self.assertIn("name", self.data.data.obs) + self.assertEqual(list(self.data.data.obs.index), list(range(2638))) + self.assertIn("name", self.data.data.var) + self.assertEqual(list(self.data.data.var.index), list(range(1838))) + def test_data_type(self): + self.data.data.X = self.data.data.X.astype("float64") + self.assertWarns(UserWarning, self.data._validatate_data_types()) if __name__ == '__main__': unittest.main()