fix: tz attribute check, it was checking dtype instead of dt (#…

…2855)

* fix: `tz` attribute check, it was checking `dtype` instead of `dt`

This will fix the issue reported here: #2410

* fix test_timezone_raw_values

* fix formatting

---------

Co-authored-by: Leon Luttenberger <luttenberger.leon@gmail.com>

awswrangler/_arrow.py

@@ -72,13 +72,17 @@ def _apply_timezone(df: pd.DataFrame, metadata: dict[str, Any]) -> pd.DataFrame:
         if col_name in df.columns and c["pandas_type"] == "datetimetz":
             column_metadata: dict[str, Any] = c["metadata"] if c.get("metadata") else {}
             timezone_str: str | None = column_metadata.get("timezone")
+
             if timezone_str:
                 timezone: datetime.tzinfo = pa.lib.string_to_tzinfo(timezone_str)
                 _logger.debug("applying timezone (%s) on column %s", timezone, col_name)
-                if hasattr(df[col_name].dtype, "tz") is False:
+
+                if hasattr(df[col_name].dt, "tz") is False or df[col_name].dt.tz is None:
                     df[col_name] = df[col_name].dt.tz_localize(tz="UTC")
+
                 if timezone is not None and timezone != pytz.UTC and hasattr(df[col_name].dt, "tz_convert"):
                     df[col_name] = df[col_name].dt.tz_convert(tz=timezone)
+
     return df
 
 

tests/unit/test_s3_parquet.py

@@ -645,13 +645,17 @@ def test_timezone_raw_values(path):
     df["c3"] = pd.to_datetime(datetime(2011, 11, 4, 0, 5, 23, tzinfo=timezone(-timedelta(seconds=14400))))
     df["c4"] = pd.to_datetime(datetime(2011, 11, 4, 0, 5, 23, tzinfo=timezone(timedelta(hours=-8))))
     wr.s3.to_parquet(partition_cols=["par"], df=df, path=path, dataset=True, sanitize_columns=False)
+
     df2 = wr.s3.read_parquet(path, dataset=True, use_threads=False, pyarrow_additional_kwargs={"ignore_metadata": True})
+
     # Use pandas to read because of Modin "Internal Error: Internal and external indices on axis 1 do not match."
     import pandas
 
     df3 = pandas.read_parquet(path)
+
     df2["par"] = df2["par"].astype("string")
     df3["par"] = df3["par"].astype("string")
+
     assert_pandas_equals(df2, df3)