Add validation rules to MostRecentDateHandler

newgene · Feb 22, 2023 · 79a9959 · 79a9959
1 parent 992ae23
commit 79a9959
Show file tree

Hide file tree

Showing 3 changed files with 41 additions and 24 deletions.
diff --git a/config_web/genomics.py b/config_web/genomics.py
@@ -23,6 +23,14 @@
         r"/{pre}/{ver}/prevalence-by-position",
         "web.handlers.v2.genomics.PrevalenceByAAPositionHandler",
     ),
+    (
+        r"/{pre}/{ver}/most-recent-collection-date-by-location",
+        "web.handlers.v2.genomics.MostRecentCollectionDateHandler",
+    ),
+    (
+        r"/{pre}/{ver}/most-recent-submission-date-by-location",
+        "web.handlers.v2.genomics.MostRecentSubmissionDateHandler",
+    ),
 ]
 
 APP_LIST_SWITCHED_TO_V2 = [

diff --git a/web/handlers/v2/genomics/__init__.py b/web/handlers/v2/genomics/__init__.py
@@ -2,6 +2,7 @@
 from .lineage import LineageHandler
 from .lineage_mutations import LineageMutationsHandler
 from .location import LocationHandler
-from .prevalence_all_lineages_by_location import PrevalenceAllLineagesByLocationHandler
 from .prevalence_by_aa_position import PrevalenceByAAPositionHandler
+from .most_recent_date import MostRecentCollectionDateHandler, MostRecentSubmissionDateHandler
+from .prevalence_all_lineages_by_location import PrevalenceAllLineagesByLocationHandler
 from .prevalence_by_location_and_time import PrevalenceByLocationAndTimeHandler
diff --git a/web/handlers/v2/genomics/most_recent_date.py b/web/handlers/v2/genomics/most_recent_date.py
@@ -1,30 +1,38 @@
+import pandas as pd
+
+from web.handlers.genomics.base import BaseHandler
+from web.handlers.genomics.util import create_nested_mutation_query
+
 
 class MostRecentDateHandler(BaseHandler):
     field = "date_collected"
+    name = "most-recent-date"
+    kwargs = dict(BaseHandler.kwargs)
+    kwargs["GET"] = {
+        "pangolin_lineage": {"type": str, "default": None},
+        "mutations": {"type": str, "default": None},
+        "location_id": {"type": str, "default": None},
+    }
 
-    @gen.coroutine
-    def _get(self):
-        query_pangolin_lineage = self.get_argument("pangolin_lineage", None)
-        query_location = self.get_argument("location_id", None)
-        query_mutations = self.get_argument("mutations", None)
+    async def _get(self):
+        query_pangolin_lineage = self.args.pangolin_lineage
+        query_location = self.args.location_id
+        query_mutations = self.args.mutations
         query_mutations = query_mutations.split(",") if query_mutations is not None else []
         query = {
             "size": 0,
             "query": {},
-            "aggs": {
-                "date_collected": {
-                    "terms": {
-                        "field": self.field,
-                        "size": 10000
-                    }
-                }
-            }
+            "aggs": {"date_collected": {"terms": {"field": self.field, "size": 10000}}},
         }
-        query_pangolin_lineage = query_pangolin_lineage.split(",") if query_pangolin_lineage is not None else []
-        query_obj = create_nested_mutation_query(lineages = query_pangolin_lineage, mutations = query_mutations, location_id = query_location)
+        query_pangolin_lineage = (
+            query_pangolin_lineage.split(",") if query_pangolin_lineage is not None else []
+        )
+        query_obj = create_nested_mutation_query(
+            lineages=query_pangolin_lineage, mutations=query_mutations, location_id=query_location
+        )
         query["query"] = query_obj
-        resp = yield self.asynchronous_fetch(query)
-        #print(resp)
+        resp = await self.asynchronous_fetch(query)
+        # print(resp)
         path_to_results = ["aggregations", "date_collected", "buckets"]
         buckets = resp
         for i in path_to_results:
@@ -35,15 +43,12 @@ def _get(self):
         for i in buckets:
             if len(i["key"].split("-")) == 1 or "XX" in i["key"]:
                 continue
-            flattened_response.append({
-                "date": i["key"],
-                "date_count": i["doc_count"]
-            })
+            flattened_response.append({"date": i["key"], "date_count": i["doc_count"]})
         df_response = (
             pd.DataFrame(flattened_response)
             .assign(
-                date = lambda x: pd.to_datetime(x["date"], format="%Y-%m-%d"),
-                date_count = lambda x: x["date_count"].astype(int)
+                date=lambda x: pd.to_datetime(x["date"], format="%Y-%m-%d"),
+                date_count=lambda x: x["date_count"].astype(int),
             )
             .sort_values("date")
         )
@@ -57,6 +62,9 @@ def _get(self):
 
 class MostRecentCollectionDateHandler(MostRecentDateHandler):
     field = "date_collected"
+    name = "most-recent-collection-date-by-location"
+
 
 class MostRecentSubmissionDateHandler(MostRecentDateHandler):
     field = "date_submitted"
+    name = "most-recent-submission-date-by-location"