clib.converison._to_numpy: Add tests for pandas.Series with pandas numeric dtypes

pygmt/clib/conversion.py

@@ -162,19 +162,37 @@ def _to_numpy(data: Any) -> np.ndarray:
         "date64[ms][pyarrow]": np.datetime64,
     }
 
-    if (
-        hasattr(data, "isna")
-        and data.isna().any()
-        and Version(pd.__version__) < Version("2.2")
-    ):
-        # Workaround for dealing with pd.NA with pandas < 2.2.
-        # Bug report at: https://github.com/GenericMappingTools/pygmt/issues/2844
-        # Following SPEC0, pandas 2.1 will be dropped in 2025 Q3, so it's likely
-        # we can remove the workaround in PyGMT v0.17.0.
-        array = np.ascontiguousarray(data.astype(float))
-    else:
-        vec_dtype = str(getattr(data, "dtype", ""))
-        array = np.ascontiguousarray(data, dtype=dtypes.get(vec_dtype))
+    # pandas numeric dtypes were converted to np.object_ dtype prior pandas 2.2, and are
+    # converted to suitable numpy dtypes since pandas 2.2. Refer to the following link
+    # for details: https://pandas.pydata.org/docs/whatsnew/v2.2.0.html#to-numpy-for-numpy-nullable-and-arrow-types-converts-to-suitable-numpy-dtype
+    # Here are the workarounds for pandas < 2.2.
+    # Following SPEC 0, pandas 2.1 should be dropped in 2025 Q3, so it's likely we can
+    # remove the workaround in PyGMT v0.17.0.
+    if Version(pd.__version__) < Version("2.2"):
+        # Specify mapping from pandas nullable dtypes to suitable numpy dtypes
+        dtypes.update(
+            {
+                "Int8": np.int8,
+                "Int16": np.int16,
+                "Int32": np.int32,
+                "Int64": np.int64,
+                "UInt8": np.uint8,
+                "UInt16": np.uint16,
+                "UInt32": np.uint32,
+                "UInt64": np.uint64,
+                "Float32": np.float32,
+                "Float64": np.float64,
+            }
+        )
+        # For pandas.Index/pandas.Series, pandas/pyarrow integer dtypes with missing
+        # values should be cast to NumPy float dtypes and NaN is used as missing value
+        # indicator.
+        if getattr(data, "hasnans", False):  # pandas.Index/pandas.Series has 'hasnans'
+            dtype = np.float64 if data.dtype.kind in "iu" else data.dtype.numpy_dtype
+            data = data.to_numpy(na_value=np.nan).astype(dtype=dtype)
+
+    vec_dtype = str(getattr(data, "dtype", ""))
+    array = np.ascontiguousarray(data, dtype=dtypes.get(vec_dtype))
     return array
 
 

pygmt/tests/test_clib_to_numpy.py

@@ -161,6 +161,57 @@ def test_to_numpy_pandas_series_numpy_dtypes_numeric(dtype, expected_dtype):
     npt.assert_array_equal(result, series)
 
 
+@pytest.mark.parametrize(
+    ("dtype", "expected_dtype"),
+    [
+        pytest.param(pd.Int8Dtype(), np.int8, id="Int8"),
+        pytest.param(pd.Int16Dtype(), np.int16, id="Int16"),
+        pytest.param(pd.Int32Dtype(), np.int32, id="Int32"),
+        pytest.param(pd.Int64Dtype(), np.int64, id="Int64"),
+        pytest.param(pd.UInt8Dtype(), np.uint8, id="UInt8"),
+        pytest.param(pd.UInt16Dtype(), np.uint16, id="UInt16"),
+        pytest.param(pd.UInt32Dtype(), np.uint32, id="UInt32"),
+        pytest.param(pd.UInt64Dtype(), np.uint64, id="UInt64"),
+        pytest.param(pd.Float32Dtype(), np.float32, id="Float32"),
+        pytest.param(pd.Float64Dtype(), np.float64, id="Float64"),
+    ],
+)
+def test_to_numpy_pandas_series_pandas_dtypes_numeric(dtype, expected_dtype):
+    """
+    Test the _to_numpy function with pandas.Series of pandas numeric dtypes.
+    """
+    series = pd.Series([1, 2, 3, 4, 5, 6], dtype=dtype)[::2]  # Not C-contiguous
+    result = _to_numpy(series)
+    _check_result(result, expected_dtype)
+    npt.assert_array_equal(result, series)
+
+
+@pytest.mark.parametrize(
+    ("dtype", "expected_dtype"),
+    [
+        pytest.param(pd.Int8Dtype(), np.float64, id="Int8"),
+        pytest.param(pd.Int16Dtype(), np.float64, id="Int16"),
+        pytest.param(pd.Int32Dtype(), np.float64, id="Int32"),
+        pytest.param(pd.Int64Dtype(), np.float64, id="Int64"),
+        pytest.param(pd.UInt8Dtype(), np.float64, id="UInt8"),
+        pytest.param(pd.UInt16Dtype(), np.float64, id="UInt16"),
+        pytest.param(pd.UInt32Dtype(), np.float64, id="UInt32"),
+        pytest.param(pd.UInt64Dtype(), np.float64, id="UInt64"),
+        pytest.param(pd.Float32Dtype(), np.float32, id="Float32"),
+        pytest.param(pd.Float64Dtype(), np.float64, id="Float64"),
+    ],
+)
+def test_to_numpy_pandas_series_pandas_dtypes_numeric_with_na(dtype, expected_dtype):
+    """
+    Test the _to_numpy function with pandas.Series of pandas numeric dtypes and NA.
+    """
+    series = pd.Series([1, 2, pd.NA, 4, 5, 6], dtype=dtype)[::2]  # Not C-contiguous
+    assert series.isna().any()
+    result = _to_numpy(series)
+    _check_result(result, expected_dtype)
+    npt.assert_array_equal(result, np.array([1.0, np.nan, 5.0], dtype=expected_dtype))
+
+
 ########################################################################################
 # Test the _to_numpy function with PyArrow arrays.
 #

pygmt/tests/test_clib_vectors_to_arrays.py

@@ -69,17 +69,6 @@ def test_vectors_to_arrays_not_c_contiguous():
     _check_arrays(arrays)
 
 
-def test_vectors_to_arrays_pandas_nan():
-    """
-    Test the vectors_to_arrays function with pandas Series containing NaNs.
-    """
-    vectors = [pd.Series(data=[0, 4, pd.NA, 8, 6], dtype=pd.Int32Dtype())]
-    arrays = vectors_to_arrays(vectors)
-    npt.assert_equal(arrays[0], np.array([0, 4, np.nan, 8, 6], dtype=np.float64))
-    assert arrays[0].dtype == np.float64
-    _check_arrays(arrays)
-
-
 @pytest.mark.skipif(not _HAS_PYARROW, reason="pyarrow is not installed.")
 def test_vectors_to_arrays_pyarrow_datetime():
     """