Add support for new pandas UDF engine

Author: datapythonista

src/blosc2/proxy.py

@@ -676,3 +676,50 @@ def wrapper(*args, **func_kwargs):
         return decorator
     else:
         return decorator(func)
+
+
+class PandasUdfEngine:
+    @staticmethod
+    def _ensure_numpy_data(data):
+        if not isinstance(data, np.ndarray):
+            try:
+                data = data.values
+            except AttributeError as err:
+                raise ValueError(
+                    "blosc2.jit received an object of type {data.__name__}, which is not supported. "
+                    "Try casting your Series or DataFrame to a NumPy dtype."
+                ) from err
+        return data
+
+    @classmethod
+    def map(cls, data, func, args, kwargs, decorator, skip_na):
+        """
+        JIT a NumPy array element-wise. In the case of Blosc2, functions are
+        expected to be vectorized NumPy operations, so the function is called
+        with the NumPy array as the function parameter, instead of calling the
+        function once for each element.
+        """
+        data = cls._ensure_numpy_data(data)
+        func = decorator(func)
+        return func(data, *args, **kwargs)
+
+    @classmethod
+    def apply(cls, data, func, args, kwargs, decorator, axis):
+        """
+        JIT a NumPy array by column or row. In the case of Blosc2, functions are
+        expected to be vectorized NumPy operations, so the function is called
+        with the NumPy array as the function parameter, instead of calling the
+        function once for each column or row.
+        """
+        data = cls._ensure_numpy_data(data)
+        func = decorator(func)
+        if data.ndim in (1, 2):
+            return func(data, *args, **kwargs)
+        else:
+            raise NotImplementedError(
+                "The blosc2 engine only supports data with with 1 or 2 dimensions. "
+                f"A NumPy array with {data.ndim} dimensions has been received."
+            )
+
+
+jit.__pandas_udf__ = PandasUdfEngine

tests/test_pandas_udf_engine.py

@@ -0,0 +1,125 @@
+#######################################################################
+# Copyright (c) 2019-present, Blosc Development Team <[email protected]>
+# All rights reserved.
+#
+# This source code is licensed under a BSD-style license (found in the
+# LICENSE file in the root directory of this source tree)
+#######################################################################
+
+import numpy as np
+
+import blosc2
+
+
+class TestPandasUDF:
+    def test_map_1d(self):
+        def add_one(x):
+            return x + 1
+
+        data = np.array([1, 2])
+
+        result = blosc2.jit.__pandas_udf__.map(
+            data,
+            add_one,
+            args=(),
+            kwargs={},
+            decorator=blosc2.jit,
+            skip_na=False,
+        )
+        assert result.shape == (2,)
+        assert result[0] == 2
+        assert result[1] == 3
+
+    def test_map_1d_with_args(self):
+        def add_numbers(x, num1, num2):
+            return x + num1 + num2
+
+        data = np.array([1, 2])
+
+        result = blosc2.jit.__pandas_udf__.map(
+            data,
+            add_numbers,
+            args=(10,),
+            kwargs={"num2": 100},
+            decorator=blosc2.jit,
+            skip_na=False,
+        )
+        assert result.shape == (2,)
+        assert result[0] == 111
+        assert result[1] == 112
+
+    def test_map_2d(self):
+        def add_one(x):
+            return x + 1
+
+        data = np.array([[1, 2], [3, 4]])
+
+        result = blosc2.jit.__pandas_udf__.map(
+            data,
+            add_one,
+            args=(),
+            kwargs={},
+            decorator=blosc2.jit,
+            skip_na=False,
+        )
+        assert result.shape == (2, 2)
+        assert result[0, 0] == 2
+        assert result[0, 1] == 3
+        assert result[1, 0] == 4
+        assert result[1, 1] == 5
+
+    def test_apply_1d(self):
+        def add_one(x):
+            return x + 1
+
+        data = np.array([1, 2])
+
+        result = blosc2.jit.__pandas_udf__.apply(
+            data,
+            add_one,
+            args=(),
+            kwargs={},
+            decorator=blosc2.jit,
+            axis=0,
+        )
+        assert result.shape == (2,)
+        assert result[0] == 2
+        assert result[1] == 3
+
+    def test_apply_1d_with_args(self):
+        def add_numbers(x, num1, num2):
+            return x + num1 + num2
+
+        data = np.array([1, 2])
+
+        result = blosc2.jit.__pandas_udf__.apply(
+            data,
+            add_numbers,
+            args=(10,),
+            kwargs={"num2": 100},
+            decorator=blosc2.jit,
+            axis=0,
+        )
+        assert result.shape == (2,)
+        assert result[0] == 111
+        assert result[1] == 112
+
+    def test_apply_2d(self):
+        def add_one(x):
+            return x + 1
+
+        data = np.array([[1, 2], [3, 4]])
+
+        result = blosc2.jit.__pandas_udf__.apply(
+            data,
+            add_one,
+            args=(),
+            kwargs={},
+            decorator=blosc2.jit,
+            axis=0,
+        )
+        assert result.shape == (2, 2)
+        assert result[0, 0] == 2
+        assert result[0, 1] == 3
+        assert result[1, 0] == 4
+        assert result[1, 1] == 5