From 3f72c40897a80132099729d5d00a6718e76e0e9e Mon Sep 17 00:00:00 2001
From: Cornelius Roemer <cornelius.roemer@gmail.com>
Date: Wed, 13 Nov 2024 13:37:50 +0100
Subject: [PATCH] Support pandas v2 (#1671)

---
 CHANGES.md     | 5 +++++
 augur/parse.py | 6 +++---
 setup.py       | 4 ++--
 3 files changed, 10 insertions(+), 5 deletions(-)

diff --git a/CHANGES.md b/CHANGES.md
index 297f92ba2..7cfe82974 100644
--- a/CHANGES.md
+++ b/CHANGES.md
@@ -4,11 +4,14 @@
 
 ### Features
 
+- support pandas v2. [#1671] (@corneliusroemer and @victorlin)
 - curate: change output metadata to [RFC 4180 CSV-like TSVs][] to match the TSV format output by other Augur subcommands and the Nextstrain ecosystem as discussed in [#1566][]. [#1565][] (@joverlee521)
 
+
 [#1565]: https://github.com/nextstrain/augur/pull/1565
 [#1566]: https://github.com/nextstrain/augur/issues/1566
 [RFC 4180 CSV-like TSVs]: https://datatracker.ietf.org/doc/html/rfc4180
+[#1671]: https://github.com/nextstrain/augur/pull/1671
 
 ## 26.1.0 (12 November 2024)
 
@@ -22,7 +25,9 @@
 
 * index: Previously specifying a directory that does not exist in the path to `--output` would result in an incorrect error stating that the input file does not exist. It now shows the correct path responsible for the error. [#1644][] (@victorlin)
 * curate format-dates: Update help docs and improve failure messages to show use of `--expected-date-formats`. [#1653][] (@joverlee521)
+* parse: fix test failure with pandas 2.2. [#1471] (@emollier)
 
+[#1471]: https://github.com/nextstrain/augur/pull/1471
 [#1644]: https://github.com/nextstrain/augur/issues/1644
 [#1547]: https://github.com/nextstrain/augur/pull/1547
 [#1653]: https://github.com/nextstrain/augur/pull/1653
diff --git a/augur/parse.py b/augur/parse.py
index 1aaeec5b5..7e1a094ee 100644
--- a/augur/parse.py
+++ b/augur/parse.py
@@ -25,7 +25,7 @@
      '\\': '_'}
 )
 
-def fix_dates(d, dayfirst=True):
+def fix_dates(d: str, dayfirst: bool = True) -> str:
     '''
     attempt to parse a date string using pandas date parser. If ambiguous,
     the argument 'dayfirst' determines whether month or day is assumed to be
@@ -35,7 +35,7 @@ def fix_dates(d, dayfirst=True):
     try:
         try:
             # pandas <= 2.1
-            from pandas.core.tools.datetimes import parsing
+            from pandas.core.tools.datetimes import parsing  # type: ignore
         except ImportError:
             # pandas >= 2.2
             from pandas._libs.tslibs import parsing
@@ -44,7 +44,7 @@ def fix_dates(d, dayfirst=True):
             results = parsing.parse_datetime_string_with_reso(d, dayfirst=dayfirst)
         except AttributeError:
             # pandas 1.x
-            results = parsing.parse_time_string(d, dayfirst=dayfirst)
+            results = parsing.parse_time_string(d, dayfirst=dayfirst)  # type: ignore
         if len(results) == 2:
             dto, res = results
         else:
diff --git a/setup.py b/setup.py
index a924fe534..863e67fa0 100644
--- a/setup.py
+++ b/setup.py
@@ -61,7 +61,7 @@
         "networkx >= 2.5, <4",
         "numpy ==1.*",
         "packaging >=19.2",
-        "pandas >=1.0.0, ==1.*",
+        "pandas >=1.0.0, <3",
         "phylo-treetime >=0.11.2, <0.12",
         "pyfastx >=1.0.0, <3.0",
         "python_calamine >=0.2.0",
@@ -76,7 +76,7 @@
             "freezegun >=0.3.15",
             "mypy",
             "nextstrain-sphinx-theme >=2022.5",
-            "pandas-stubs >=1.0.0, ==1.*",
+            "pandas-stubs >=1.0.0, <3",
             "pylint >=1.7.6",
             "pytest >=5.4.1",
             "pytest-cov >=2.8.1",