Merge pull request #708 from nextstrain/filter-date-bounds-inclusive

Filter date bounds inclusive

augur/filter.py

@@ -105,8 +105,8 @@ def register_arguments(parser):
         Uses Pandas Dataframe querying, see https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#indexing-query for syntax.
         (e.g., --query "country == 'Colombia'" or --query "(country == 'USA' & (division == 'Washington'))")"""
     )
-    metadata_filter_group.add_argument('--min-date', type=numeric_date, help="minimal cutoff for date; may be specified as an Augur-style numeric date (with the year as the integer part) or YYYY-MM-DD")
-    metadata_filter_group.add_argument('--max-date', type=numeric_date, help="maximal cutoff for date; may be specified as an Augur-style numeric date (with the year as the integer part) or YYYY-MM-DD")
+    metadata_filter_group.add_argument('--min-date', type=numeric_date, help="minimal cutoff for date, the cutoff date is inclusive; may be specified as an Augur-style numeric date (with the year as the integer part) or YYYY-MM-DD")
+    metadata_filter_group.add_argument('--max-date', type=numeric_date, help="maximal cutoff for date, the cutoff date is inclusive; may be specified as an Augur-style numeric date (with the year as the integer part) or YYYY-MM-DD")
     metadata_filter_group.add_argument('--exclude-ambiguous-dates-by', choices=['any', 'day', 'month', 'year'],
                                 help='Exclude ambiguous dates by day (e.g., 2020-09-XX), month (e.g., 2020-XX-XX), year (e.g., 200X-10-01), or any date fields. An ambiguous year makes the corresponding month and day ambiguous, too, even if those fields have unambiguous values (e.g., "201X-10-01"). Similarly, an ambiguous month makes the corresponding day ambiguous (e.g., "2010-XX-01").')
     metadata_filter_group.add_argument('--exclude', type=str, nargs="+", help="file(s) with list of strains to exclude")
@@ -348,9 +348,9 @@ def run(args):
         dates = get_numerical_dates(meta_dict, fmt="%Y-%m-%d")
         tmp = {s for s in seq_keep if dates[s] is not None}
         if args.min_date:
-            tmp = {s for s in tmp if (np.isscalar(dates[s]) or all(dates[s])) and np.max(dates[s])>args.min_date}
+            tmp = {s for s in tmp if (np.isscalar(dates[s]) or all(dates[s])) and np.max(dates[s])>=args.min_date}
         if args.max_date:
-            tmp = {s for s in tmp if (np.isscalar(dates[s]) or all(dates[s])) and np.min(dates[s])<args.max_date}
+            tmp = {s for s in tmp if (np.isscalar(dates[s]) or all(dates[s])) and np.min(dates[s])<=args.max_date}
         num_excluded_by_date = len(seq_keep) - len(tmp)
         seq_keep = tmp
 

tests/test_filter.py

@@ -215,3 +215,31 @@ def test_filter_run_with_query_and_include_where(self, tmpdir, fasta_fn, argpars
         augur.filter.run(args)
         output = SeqIO.to_dict(SeqIO.parse(out_fn, "fasta"))
         assert list(output.keys()) == ["SEQ_1", "SEQ_3"]
+
+    def test_filter_run_min_date(self, tmpdir, fasta_fn, argparser):
+        """Test that filter --min-date is inclusive"""
+        out_fn = str(tmpdir / "out.fasta")
+        min_date = "2020-02-26"
+        meta_fn = write_metadata(tmpdir, (("strain","date"),
+                                          ("SEQ_1","2020-02-XX"),
+                                          ("SEQ_2","2020-02-26"),
+                                          ("SEQ_3","2020-02-25")))
+        args = argparser('-s %s --metadata %s -o %s --min-date %s'
+                         % (fasta_fn, meta_fn, out_fn, min_date))
+        augur.filter.run(args)
+        output = SeqIO.to_dict(SeqIO.parse(out_fn, "fasta"))
+        assert list(output.keys()) == ["SEQ_1", "SEQ_2"]
+
+    def test_filter_run_max_date(self, tmpdir, fasta_fn, argparser):
+        """Test that filter --max-date is inclusive"""
+        out_fn = str(tmpdir / "out.fasta")
+        max_date = "2020-03-01"
+        meta_fn = write_metadata(tmpdir, (("strain","date"),
+                                          ("SEQ_1","2020-03-XX"),
+                                          ("SEQ_2","2020-03-01"),
+                                          ("SEQ_3","2020-03-02")))
+        args = argparser('-s %s --metadata %s -o %s --max-date %s'
+                         % (fasta_fn, meta_fn, out_fn, max_date))
+        augur.filter.run(args)
+        output = SeqIO.to_dict(SeqIO.parse(out_fn, "fasta"))
+        assert list(output.keys()) == ["SEQ_1", "SEQ_2"]