fix: empty record dtypes (#2147)

* fix: empty record dtypes

* update pandas minimum version

* fix coverage

* fix test_pandas

---------

Co-authored-by: Lingqing Gan <[email protected]>

Author: yokomotod

google/cloud/bigquery/table.py

@@ -2648,31 +2648,25 @@ def to_dataframe(
                 if pyarrow.types.is_timestamp(col.type)
             )
 
-        if len(record_batch) > 0:
-            df = record_batch.to_pandas(
+        df = record_batch.to_pandas(
+            date_as_object=date_as_object,
+            timestamp_as_object=timestamp_as_object,
+            integer_object_nulls=True,
+            types_mapper=_pandas_helpers.default_types_mapper(
                 date_as_object=date_as_object,
-                timestamp_as_object=timestamp_as_object,
-                integer_object_nulls=True,
-                types_mapper=_pandas_helpers.default_types_mapper(
-                    date_as_object=date_as_object,
-                    bool_dtype=bool_dtype,
-                    int_dtype=int_dtype,
-                    float_dtype=float_dtype,
-                    string_dtype=string_dtype,
-                    date_dtype=date_dtype,
-                    datetime_dtype=datetime_dtype,
-                    time_dtype=time_dtype,
-                    timestamp_dtype=timestamp_dtype,
-                    range_date_dtype=range_date_dtype,
-                    range_datetime_dtype=range_datetime_dtype,
-                    range_timestamp_dtype=range_timestamp_dtype,
-                ),
-            )
-        else:
-            # Avoid "ValueError: need at least one array to concatenate" on
-            # older versions of pandas when converting empty RecordBatch to
-            # DataFrame. See: https://github.com/pandas-dev/pandas/issues/41241
-            df = pandas.DataFrame([], columns=record_batch.schema.names)
+                bool_dtype=bool_dtype,
+                int_dtype=int_dtype,
+                float_dtype=float_dtype,
+                string_dtype=string_dtype,
+                date_dtype=date_dtype,
+                datetime_dtype=datetime_dtype,
+                time_dtype=time_dtype,
+                timestamp_dtype=timestamp_dtype,
+                range_date_dtype=range_date_dtype,
+                range_datetime_dtype=range_datetime_dtype,
+                range_timestamp_dtype=range_timestamp_dtype,
+            ),
+        )
 
         for column in dtypes:
             df[column] = pandas.Series(df[column], dtype=dtypes[column], copy=False)

pyproject.toml

@@ -72,7 +72,7 @@ bqstorage = [
   "pyarrow >= 4.0.0",
 ]
 pandas = [
-  "pandas >= 1.1.4",
+  "pandas >= 1.3.0",
   "pandas-gbq >= 0.26.1",
   "grpcio >= 1.47.0, < 2.0.0",
   "grpcio >= 1.49.1, < 2.0.0; python_version >= '3.11'",

testing/constraints-3.9.txt

@@ -21,7 +21,7 @@ opentelemetry-api==1.1.0
 opentelemetry-instrumentation==0.20b0
 opentelemetry-sdk==1.1.0
 packaging==24.2.0
-pandas==1.1.4
+pandas==1.3.0
 pandas-gbq==0.26.1
 proto-plus==1.22.3
 protobuf==3.20.2

tests/system/test_pandas.py

@@ -1222,12 +1222,7 @@ def test_list_rows_nullable_scalars_extreme_dtypes_w_custom_dtype(
 
     # These pandas dtypes are handled by the custom dtypes.
     assert df.dtypes["bool_col"].name == "boolean"
-    # Result is dependent upon which version of pandas is being used.
-    # Float64 was not introduced until pandas version 1.4.
-    if PANDAS_INSTALLED_VERSION >= "1.4":
-        assert df.dtypes["float64_col"].name == "Float64"
-    else:
-        assert df.dtypes["float64_col"].name == "string"
+    assert df.dtypes["float64_col"].name == "Float64"
     assert df.dtypes["int64_col"].name == "Int64"
     assert df.dtypes["string_col"].name == "string"
 

tests/unit/test_table.py

@@ -4143,14 +4143,8 @@ def test_to_dataframe_w_dtypes_mapper(self):
         )
         self.assertEqual(df.name.dtype.name, "string")
 
-        # While pyproject.toml lists pandas 1.1 as the lowest supported version of
-        # pandas, the pip resolver is not able to resolve pandas 1.1 and numpy
-        if hasattr(pandas, "Float64Dtype"):
-            self.assertEqual(list(df.miles), [1.77, 6.66, 2.0])
-            self.assertEqual(df.miles.dtype.name, "Float64")
-        else:
-            self.assertEqual(list(df.miles), ["1.77", "6.66", "2.0"])
-            self.assertEqual(df.miles.dtype.name, "string")
+        self.assertEqual(list(df.miles), [1.77, 6.66, 2.0])
+        self.assertEqual(df.miles.dtype.name, "Float64")
 
         if hasattr(pandas, "ArrowDtype"):
             self.assertEqual(