pyarrow: Support date32[day] and date64[ms] dtypes in pandas objects (#2845)

* Convert pyarrow date32/date64 dtypes to np.datetime64

Handle date columns in pandas.DataFrame with pyarrow dtypes
like date32[day][pyarrow] or date64[ms][pyarrow] by modifying
the vectors_to_arrays conversion function. Added some parametrized
unit tests to test_info.py to ensure this works.

* Handle Python lists without dtype attr and use as_c_contiguous

Need to handle Python lists that don't have the dtype attribute, unlike
pandas.Series objects. Also ensure that we return a C-contiguous array.

* Add doctest to check that date32/date64 are converted to datetime64

Ensure that pyarrow date32 and date64 dtypes are converted to
numpy.datetime64 dtype. Added pyarrow dependency to ci_doctests.yaml.
Also changed from using `"date" in vec_dtype` to `vec_dtype.startswith("date")`.

* Refactor to use pygmt.helpers.testing.skip_if_no

* Document that PyArrow date32/date64 dtypes are now supported in PyGMT

* Refactor to use dict mapping instead of if-then

---------

Co-authored-by: Dongdong Tian <[email protected]>

Author: weiji14

.github/workflows/ci_doctests.yaml

@@ -58,6 +58,7 @@ jobs:
             contextily
             geopandas
             ipython
+            pyarrow
             rioxarray
             build
             make

doc/install.rst

@@ -112,8 +112,8 @@ The following are optional dependencies:
     If you have `PyArrow <https://arrow.apache.org/docs/python/index.html>`__
     installed, PyGMT does have some initial support for ``pandas.Series`` and
     ``pandas.DataFrame`` objects with Apache Arrow-backed arrays. Specifically,
-    only uint/int/float dtypes are supported for now. Support for datetime and
-    string Arrow dtypes are still working in progress. For more details, see
+    only uint/int/float and date32/date64 dtypes are supported for now. Support
+    for string Arrow dtypes is still a work in progress. For more details, see
     `issue #2800 <https://github.com/GenericMappingTools/pygmt/issues/2800>`__.
 
 Installing GMT and other dependencies

pygmt/clib/conversion.py

@@ -162,11 +162,42 @@ def vectors_to_arrays(vectors):
     True
     >>> all(isinstance(i, np.ndarray) for i in arrays)
     True
+
     >>> data = [[1, 2], (3, 4), range(5, 7)]
     >>> all(isinstance(i, np.ndarray) for i in vectors_to_arrays(data))
     True
+
+    >>> import datetime
+    >>> import pytest
+    >>> pa = pytest.importorskip("pyarrow")
+    >>> vectors = [
+    ...     pd.Series(
+    ...         data=[datetime.date(2020, 1, 1), datetime.date(2021, 12, 31)],
+    ...         dtype="date32[day][pyarrow]",
+    ...     ),
+    ...     pd.Series(
+    ...         data=[datetime.date(2022, 1, 1), datetime.date(2023, 12, 31)],
+    ...         dtype="date64[ms][pyarrow]",
+    ...     ),
+    ... ]
+    >>> arrays = vectors_to_arrays(vectors)
+    >>> all(a.flags.c_contiguous for a in arrays)
+    True
+    >>> all(isinstance(a, np.ndarray) for a in arrays)
+    True
+    >>> all(isinstance(a.dtype, np.dtypes.DateTime64DType) for a in arrays)
+    True
     """
-    arrays = [as_c_contiguous(np.asarray(i)) for i in vectors]
+    dtypes = {
+        "date32[day][pyarrow]": np.datetime64,
+        "date64[ms][pyarrow]": np.datetime64,
+    }
+    arrays = []
+    for vector in vectors:
+        vec_dtype = str(getattr(vector, "dtype", ""))
+        array = np.asarray(a=vector, dtype=dtypes.get(vec_dtype, None))
+        arrays.append(as_c_contiguous(array))
+
     return arrays
 
 

pygmt/tests/test_info.py

@@ -119,14 +119,22 @@ def test_info_numpy_array_time_column():
     assert output == expected_output
 
 
-def test_info_pandas_dataframe_time_column():
+@pytest.mark.parametrize(
+    "dtype",
+    [
+        "datetime64[ns]",
+        pytest.param("date32[day][pyarrow]", marks=skip_if_no(package="pyarrow")),
+        pytest.param("date64[ms][pyarrow]", marks=skip_if_no(package="pyarrow")),
+    ],
+)
+def test_info_pandas_dataframe_date_column(dtype):
     """
-    Make sure info works on pandas.DataFrame inputs with a time column.
+    Make sure info works on pandas.DataFrame inputs with a date column.
     """
     table = pd.DataFrame(
         data={
             "z": [10, 13, 12, 15, 14],
-            "time": pd.date_range(start="2020-01-01", periods=5),
+            "date": pd.date_range(start="2020-01-01", periods=5).astype(dtype=dtype),
         }
     )
     output = info(data=table)