Performance work (#334)

* range encode filter range lists

* speed up data load

* add comment on scanpy read params

* update to latest scanpy/anndata

* performance improvments in data loading

* fix typo

* work around scanpy bug

* remove debugging print statements

server/app/scanpy_engine/scanpy_engine.py

@@ -30,7 +30,7 @@ class ScanpyEngine(CXGDriver):
         self.cell_count = self.data.shape[0]
         self.gene_count = self.data.shape[1]
         self._create_schema()
-        self.layout(None)
+        self.layout({})
 
     def _create_schema(self):
         self.schema = {
@@ -78,7 +78,11 @@ class ScanpyEngine(CXGDriver):
 
     @staticmethod
     def _load_data(data):
-        return sc.read(os.path.join(data, "data.h5ad"))
+        # See https://scanpy.readthedocs.io/en/latest/api/scanpy.api.read.html
+        # Based upon this advice, setting cache=True parameter
+        # Note: as of current scanpy/anndata release, setting backed='r' will
+        # result in an error.
+        return sc.read(os.path.join(data, "data.h5ad"), cache=True)
 
     @staticmethod
     def _top_sort(values, sort_order, top_n=None):

server/requirements.txt

@@ -1,4 +1,4 @@
-anndata==0.6.10
+anndata==0.6.11
 Flask==0.12.4
 Flask-Caching==1.4.0
 Flask-Compress==1.4.0
@@ -7,5 +7,5 @@ Flask-RESTful==0.3.6
 flask-restful-swagger-2==0.35
 numpy==1.14.5
 pandas==0.23.1
-scanpy==1.3.1
+scanpy==1.3.2
 scipy==1.1.0