remove --nan-to-num CLI parameter (#548)

* remove --nan-to-num CLI parameter

* factor tests better

* lint - remove unused variables

server/test/test_nan_rest.py

@@ -49,48 +49,3 @@ class WithNaNs(unittest.TestCase):
             url = f"{URL_BASE}{endpoint}"
             result = self.session.get(url)
             self.assertEqual(result.status_code, HTTPStatus.INTERNAL_SERVER_ERROR)
-
-
-class WithoutNaNs(unittest.TestCase):
-    """Test Case for endpoints"""
-
-    @classmethod
-    def setUpClass(cls):
-        cls.ps = Popen(
-            [
-                "cellxgene",
-                "launch",
-                "server/test/test_datasets/nan.h5ad",
-                "--nan-to-num",
-                "--debug",
-            ]
-        )
-        session = requests.Session()
-        for i in range(90):
-            try:
-                session.get(f"{URL_BASE}schema")
-            except requests.exceptions.ConnectionError:
-                time.sleep(1)
-
-    @classmethod
-    def tearDownClass(cls):
-        try:
-            cls.ps.terminate()
-        except ProcessLookupError:
-            pass
-
-    def setUp(self):
-        self.session = requests.Session()
-
-    def test_initialize(self):
-        endpoint = "schema"
-        url = f"{URL_BASE}{endpoint}"
-        result = self.session.get(url)
-        self.assertEqual(result.status_code, HTTPStatus.OK)
-
-    def test_errors(self):
-        endpoints = ["annotations/obs", "annotations/var", "data/obs", "data/var"]
-        for endpoint in endpoints:
-            url = f"{URL_BASE}{endpoint}"
-            result = self.session.get(url)
-            self.assertEqual(result.status_code, HTTPStatus.OK)

server/test/test_nan_scanpy_engine.py

@@ -2,6 +2,9 @@ import json
 import pytest
 import unittest
 import warnings
+import math
+
+import decode_fbs
 
 from server.app.scanpy_engine.scanpy_engine import ScanpyEngine
 from server.app.util.errors import JSONEncodingValueError
@@ -16,24 +19,15 @@ class NaNTest(unittest.TestCase):
             "obs_names": None,
             "var_names": None,
             "diffexp_lfc_cutoff": 0.01,
-            "nan_to_num": False,
         }
         with warnings.catch_warnings():
             warnings.simplefilter("ignore", category=UserWarning)
             self.data = ScanpyEngine("server/test/test_datasets/nan.h5ad", self.args)
             self.data._create_schema()
-        self.args_nan = dict(self.args)
-        self.args_nan["nan_to_num"] = True
-        with warnings.catch_warnings():
-            warnings.simplefilter("ignore", category=UserWarning)
-            self.data_nan = ScanpyEngine(
-                "server/test/test_datasets/nan.h5ad", self.args_nan
-            )
-            self.data_nan._create_schema()
 
     def test_load(self):
         with self.assertWarns(UserWarning):
-            ScanpyEngine("server/test/test_datasets/nan.h5ad", self.args_nan)
+            ScanpyEngine("server/test/test_datasets/nan.h5ad", self.args)
 
     def test_init(self):
         self.assertEqual(self.data.cell_count, 100)
@@ -41,45 +35,38 @@ class NaNTest(unittest.TestCase):
         epsilon = 0.000_005
         self.assertTrue(self.data.data.X[0, 0] - -0.171_469_51 < epsilon)
 
-        self.assertEqual(self.data_nan.cell_count, 100)
-        self.assertEqual(self.data_nan.gene_count, 100)
-        epsilon = 0.000_005
-        self.assertTrue(self.data_nan.data.X[0, 0] - -0.171_469_51 < epsilon)
-
     def test_dataframe(self):
-        data_frame_obs = json.loads(self.data_nan.data_frame(None, "obs"))
-        self.assertEqual(len(data_frame_obs["var"]), 100)
-        self.assertEqual(len(data_frame_obs["obs"]), 100)
-        data_frame_var = json.loads(self.data_nan.data_frame(None, "var"))
-        self.assertEqual(len(data_frame_var["var"]), 100)
-        self.assertEqual(len(data_frame_var["obs"]), 100)
-        with pytest.raises(JSONEncodingValueError):
-            data_frame_obs = json.loads(self.data.data_frame(None, "obs"))
-        with pytest.raises(JSONEncodingValueError):
-            data_frame_var = json.loads(self.data.data_frame(None, "var"))
+        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]))
 
-    def test_dataframe_nan_to_0(self):
-        data_frame_obs = json.loads(self.data_nan.data_frame(None, "obs"))
-        self.assertEqual(data_frame_obs["obs"][1][3], 0.0)
-        data_frame_var = json.loads(self.data_nan.data_frame(None, "var"))
-        self.assertEqual(data_frame_var["var"][1][5], 0.0)
+        with pytest.raises(JSONEncodingValueError):
+            json.loads(self.data.data_frame(None, "obs"))
+        with pytest.raises(JSONEncodingValueError):
+            json.loads(self.data.data_frame(None, "var"))
 
-    def test_annotation_nan_to_0(self):
-        annotations_obs = json.loads(self.data_nan.annotation(None, "obs"))
-        self.assertEqual(annotations_obs["data"][0][3], 0.0)
-        annotations_var = json.loads(self.data_nan.annotation(None, "var"))
-        self.assertEqual(annotations_var["data"][0][3], 0.0)
+    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 = json.loads(self.data_nan.annotation(None, "obs"))
+        annotations = decode_fbs.decode_matrix_FBS(self.data.annotation_to_fbs_matrix("obs"))
         self.assertEqual(
-            annotations["names"],
-            ["name", "n_genes", "percent_mito", "n_counts", "louvain"],
+            annotations["col_idx"],
+            ["name", "n_genes", "percent_mito", "n_counts", "louvain"]
         )
-        annotations = json.loads(self.data_nan.annotation(None, "var"))
-        self.assertEqual(annotations["names"], ["name", "n_cells", "var_with_nans"])
-        self.assertEqual(len(annotations["data"]), 100)
+        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"))
+        self.assertEqual(annotations["col_idx"], ["name", "n_cells", "var_with_nans"])
+        self.assertEqual(annotations["n_rows"], 100)
+        self.assertTrue(math.isnan(annotations["columns"][2][0]))
+
         with pytest.raises(JSONEncodingValueError):
-            annotations = json.loads(self.data.annotation(None, "obs"))
+            json.loads(self.data.annotation(None, "obs"))
         with pytest.raises(JSONEncodingValueError):
-            annotations = json.loads(self.data.annotation(None, "var"))
+            json.loads(self.data.annotation(None, "var"))

server/test/test_scanpy_engine.py

@@ -19,7 +19,6 @@ class UtilTest(unittest.TestCase):
             "obs_names": None,
             "var_names": None,
             "diffexp_lfc_cutoff": 0.01,
-            "nan_to_num": True,
         }
 
         self.data = ScanpyEngine("example-dataset/pbmc3k.h5ad", args)