wip

Author: MarcoGorelli

pandas/core/tools/datetimes.py

@@ -139,6 +139,8 @@ def _guess_datetime_format_for_array(arr, dayfirst: bool | None = False) -> str
             )
             if guessed_format is not None:
                 return guessed_format
+            # If there are multiple non-null elements, warn about
+            # how parsing might not be consistent
             if tslib.first_non_null(arr[first_non_null + 1 :]) != -1:
                 warnings.warn(
                     "Could not infer format, so each element will be parsed "

pandas/tests/io/parser/test_parse_dates.py

@@ -1252,13 +1252,15 @@ def test_bad_date_parse(all_parsers, cache_dates, value):
     parser = all_parsers
     s = StringIO((f"{value},\n") * 50000)
 
-    if parser.engine == "pyarrow":
+    if parser.engine == "pyarrow" and not cache_dates:
         # None in input gets converted to 'None', for which
         # pandas tries to guess the datetime format, triggering
         # the warning. TODO: parse dates directly in pyarrow, see
         # https://github.com/pandas-dev/pandas/issues/48017
         warn = UserWarning
     else:
+        # Note: warning is not raised if 'cache_dates', because here there is only a
+        # single unique date and hence no risk of inconsistent parsing.
         warn = None
     parser.read_csv_check_warnings(
         warn,
@@ -1285,6 +1287,10 @@ def test_bad_date_parse_with_warning(all_parsers, cache_dates, value):
         # TODO: parse dates directly in pyarrow, see
         # https://github.com/pandas-dev/pandas/issues/48017
         warn = None
+    elif cache_dates:
+        # Note: warning is not raised if 'cache_dates', because here there is only a
+        # single unique date and hence no risk of inconsistent parsing.
+        warn = None
     else:
         warn = UserWarning
     parser.read_csv_check_warnings(
@@ -1737,9 +1743,7 @@ def test_parse_timezone(all_parsers):
 def test_invalid_parse_delimited_date(all_parsers, date_string):
     parser = all_parsers
     expected = DataFrame({0: [date_string]}, dtype="object")
-    result = parser.read_csv_check_warnings(
-        UserWarning,
-        "Could not infer format",
+    result = parser.read_csv(
         StringIO(date_string),
         header=None,
         parse_dates=[0],
@@ -2063,9 +2067,7 @@ def test_infer_first_column_as_index(all_parsers):
     # GH#11019
     parser = all_parsers
     data = "a,b,c\n1970-01-01,2,3,4"
-    result = parser.read_csv_check_warnings(
-        UserWarning,
-        "Could not infer format",
+    result = parser.read_csv(
         StringIO(data),
         parse_dates=["a"],
     )

pandas/tests/io/parser/usecols/test_parse_dates.py

@@ -124,9 +124,7 @@ def test_usecols_with_parse_dates4(all_parsers):
     }
     expected = DataFrame(cols, columns=["a_b"] + list("cdefghij"))
 
-    result = parser.read_csv_check_warnings(
-        UserWarning,
-        "Could not infer format",
+    result = parser.read_csv(
         StringIO(data),
         usecols=usecols,
         parse_dates=parse_dates,