Merge pull request #117 from chanzuckerberg/csweaver/tests

Csweaver/tests

MANIFEST.in

@@ -1,2 +1,3 @@
 recursive-include server/app/web/templates *
 recursive-include server/app/web/static *
+

server/app/scanpy_engine/scanpy_engine.py

@@ -61,11 +61,11 @@ class ScanpyEngine(CXGDriver):
             else:
                 min_ = value["query"]["min"]
                 max_ = value["query"]["max"]
-                if min_:
+                if min_ is not None:
                     key_idx = np.array((getattr(self.data.obs, key) >= min_).data)
                     cell_idx = np.logical_and(cell_idx, key_idx)
-                if max_:
+                if max_ is not None:
-                    key_idx = np.array((getattr(self.data.obs, key) <= min_).data)
+                    key_idx = np.array((getattr(self.data.obs, key) <= max_).data)
                     cell_idx = np.logical_and(cell_idx, key_idx)
         return self.data[cell_idx, :]
 
@@ -124,6 +124,7 @@ class ScanpyEngine(CXGDriver):
         expression_1 = self.data.X[cells_idx_1, :]
         expression_2 = self.data.X[cells_idx_2, :]
         diff_exp = stats.ttest_ind(expression_1, expression_2)
+        # TODO break this up into functions
         set1 = np.logical_and(diff_exp.pvalue < pval, diff_exp.statistic > 0)
         set2 = np.logical_and(diff_exp.pvalue < pval, diff_exp.statistic < 0)
         stat1 = diff_exp.statistic[set1]

server/requirements.txt

@@ -1,5 +1,5 @@
 aniso8601==3.0.2
-anndata==0.6.4
+anndata==0.6.1
 certifi==2018.4.16
 chardet==3.0.4
 click==6.7

server/test/test_filter.py

@@ -1,9 +1,7 @@
 import unittest
-
 from unittest.mock import MagicMock
-import sys
+
-sys.path.insert(0, "../app")
+from server.app.util.filter import _convert_variable, parse_filter
-from util.filter import _convert_variable, parse_filter
 
 
 class UtilTest(unittest.TestCase):
@@ -72,3 +70,6 @@ class UtilTest(unittest.TestCase):
         filterMock.getlist.return_value = ["0,*"]
         query = parse_filter(filterMock, self.schema)
         assert query == {"n_genes": {"variable_type": "continuous", "value_type": "int", "query": {"min": 0, "max": None}}}
+
+if __name__ == '__main__':
+    unittest.main()

server/test/test_scanpy_engine.py

@@ -0,0 +1,68 @@
+import unittest
+
+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")
+
+    def test_init(self):
+        self.assertEqual(self.data.cell_count, 2638)
+        self.assertEqual(self.data.gene_count, 1838)
+        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])
+
+    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])
+
+
+if __name__ == '__main__':
+    unittest.main()