Dependencies: Add compatibility with pandas 2

Author: amotl

CHANGES.rst

@@ -12,7 +12,7 @@ development
 - CI: Add GHA configuration to invoke software tests
 - CI/Tests: Fix installation on Python 3.7 to 3.9
 - Dependencies: Switch from ``appdirs`` to ``platformdirs``
-- Dependencies: Update to ``pandas<2`
+- Dependencies: Add compatibility with pandas 2
 - Docs: Add `examples` snippets to README and tests
 - Tests: Add code snippet in README to test suite, per doctest
 - Docs: Add configuration for "Read the Docs"

phenodata/dwd/cdc.py

@@ -102,12 +102,12 @@ def csv_to_dataframe(self, stream, index_column=None, coerce_int=False):
         #    return
 
         # Read CSV into pandas DataFrame.
-        # https://pandas.pydata.org/pandas-docs/stable/io.html
+        # https://pandas.pydata.org/pandas-docs/stable/user_guide/io.html#csv-text-files
         df = pd.read_csv(
             stream, engine='c', encoding='utf-8',
             delimiter=';', skipinitialspace=True,
             skip_blank_lines=True,
-            error_bad_lines=False,
+            on_bad_lines="warn",
             low_memory=False
         )
 

phenodata/dwd/pheno.py

@@ -288,7 +288,7 @@ def query(self, partition=None, files=None):
             # Coerce "Eintrittsdatum" column into date format
             data['Eintrittsdatum'] = pd.to_datetime(data['Eintrittsdatum'], errors='coerce', format='%Y%m%d')
 
-            results = results.append(data, sort=False)
+            results = pd.concat([results, data], sort=False)
 
         # Sanity checks
         if results.empty:

setup.py

@@ -11,7 +11,7 @@
     'docopt>=0.6.2',
     'dogpile.cache>=0.6.5,<1',  # Verified to work on 1.1.1.
     'future',
-    'pandas>=0.23.4,<2',
+    'pandas>=0.23.4,<2.1',
     'platformdirs<4',
     'requests>=2.18.4,<3',
     'requests-ftp>=0.3.1,<4',  # Verified to work on 0.3.1.

tests/test_examples.py

@@ -6,7 +6,7 @@ def test_example_stations(capfd):
     os.system(f"{sys.executable} examples/stations.py")
 
     out, err = capfd.readouterr()
-    assert "Int64Index: 323 entries" in out
+    assert "Index: 323 entries" in out
     assert "Data columns (total 10 columns)" in out
     assert "Stationsname" in out
     assert "[323 rows x 10 columns]" in out
@@ -16,6 +16,6 @@ def test_example_observations(capfd):
     os.system(f"{sys.executable} examples/observations.py")
 
     out, err = capfd.readouterr()
-    assert "Int64Index: 6 entries" in out
+    assert "Index: 6 entries" in out
     assert "Data columns (total 8 columns)" in out
     assert "Stations_id" in out