Merge pull request #572 from cmu-delphi/sgratzl/coverage_endpoint

add a simple coverage endpoint

Author: sgratzl

integrations/server/test_covidcast_endpoints.py

@@ -84,7 +84,7 @@ def from_json(json: Dict[str, Any]) -> "CovidcastRow":
             sample_size=json["sample_size"],
             missing_value=json["missing_value"],
             missing_stderr=json["missing_stderr"],
-            missing_sample_size=json["missing_sample_size"]
+            missing_sample_size=json["missing_sample_size"],
         )
 
     @property
@@ -361,3 +361,28 @@ def test_meta(self):
             self.assertEqual(out[0]["source"], first.source)
             out = self._fetch("/meta", signal=f"{first.source}:X")
             self.assertEqual(len(out), 0)
+
+    def test_coverage(self):
+        """Request a signal the /coverage endpoint."""
+
+        num_geos_per_date = [10, 20, 30, 40, 44]
+        dates = [20200401 + i for i in range(len(num_geos_per_date))]
+        rows = [CovidcastRow(time_value=dates[i], value=i, geo_value=str(geo_value)) for i, num_geo in enumerate(num_geos_per_date) for geo_value in range(num_geo)]
+        self._insert_rows(rows)
+        first = rows[0]
+
+        with self.subTest("default"):
+            out = self._fetch("/coverage", signal=first.signal_pair, latest=dates[-1], format="json")
+            self.assertEqual(len(out), len(num_geos_per_date))
+            self.assertEqual([o["time_value"] for o in out], dates)
+            self.assertEqual([o["count"] for o in out], num_geos_per_date)
+
+        with self.subTest("specify window"):
+            out = self._fetch("/coverage", signal=first.signal_pair, window=f"{dates[0]}-{dates[1]}", format="json")
+            self.assertEqual(len(out), 2)
+            self.assertEqual([o["time_value"] for o in out], dates[:2])
+            self.assertEqual([o["count"] for o in out], num_geos_per_date[:2])
+
+        with self.subTest("invalid geo_type"):
+            out = self._fetch("/coverage", signal=first.signal_pair, geo_type="state", format="json")
+            self.assertEqual(len(out), 0)

src/server/endpoints/covidcast.py

@@ -1,6 +1,6 @@
 from typing import List, Optional, Union, Tuple, Dict, Any, Set
 from itertools import groupby
-from datetime import date, datetime
+from datetime import date, datetime, timedelta
 from flask import Blueprint, request
 from flask.json import loads, jsonify
 from bisect import bisect_right
@@ -34,7 +34,7 @@
 from .._db import sql_table_has_columns
 from .._pandas import as_pandas
 from .covidcast_utils import compute_trend, compute_trends, compute_correlations, compute_trend_value, CovidcastMetaEntry, AllSignalsMap
-from ..utils import shift_time_value, date_to_time_value, time_value_to_iso
+from ..utils import shift_time_value, date_to_time_value, time_value_to_iso, time_value_to_date
 
 # first argument is the endpoint name
 bp = Blueprint("covidcast", __name__)
@@ -150,7 +150,6 @@ def handle():
         q.set_order("source", "signal", "time_type", "time_value", "geo_type", "geo_value", "issue")
     q.set_fields(fields_string, fields_int, fields_float)
 
-
     # basic query info
     # data type of each field
     # build the source, signal, time, and location (type and id) filters
@@ -493,3 +492,45 @@ def handle_meta():
         entry.intergrate(row)
 
     return jsonify([r.asdict() for r in out.values()])
+
+
+@bp.route("/coverage", methods=("GET", "POST"))
+def handle_coverage():
+    """
+    similar to /signal_dashboard_coverage for a specific signal returns the coverage (number of locations for a given geo_type)
+    """
+
+    signal = parse_source_signal_arg("signal")
+    geo_type = request.args.get("geo_type", "county")
+    if "window" in request.values:
+        time_window = parse_day_range_arg("window")
+    else:
+        now_time = extract_date("latest")
+        now = date.today() if now_time is None else time_value_to_date(now_time)
+        last = extract_integer("days")
+        if last is None:
+            last = 30
+        time_window = (date_to_time_value(now - timedelta(days=last)), date_to_time_value(now))
+
+    q = QueryBuilder("covidcast", "c")
+    fields_string = ["source", "signal"]
+    fields_int = ["time_value"]
+
+    q.set_fields(fields_string, fields_int)
+
+    # manually append the count column because of grouping
+    fields_int.append("count")
+    q.fields.append(f"count({q.alias}.geo_value) as count")
+
+    if geo_type == "only-county":
+        q.where(geo_type="county")
+        q.conditions.append('geo_value not like "%000"')
+    else:
+        q.where(geo_type=geo_type)
+    q.where_source_signal_pairs("source", "signal", signal)
+    q.where_time_pairs("time_type", "time_value", [TimePair("day", [time_window])])
+    q.group_by = "c.source, c.signal, c.time_value"
+
+    _handle_lag_issues_as_of(q, None, None, None)
+
+    return execute_query(q.query, q.params, fields_string, fields_int, [])