AlenkaF commented on code in PR #40354:
URL: https://github.com/apache/arrow/pull/40354#discussion_r1521058670
##########
python/pyarrow/array.pxi:
##########
@@ -4320,6 +4320,134 @@ cdef class FixedShapeTensorArray(ExtensionArray):
)
+cdef class VariableShapeTensorArray(ExtensionArray):
+ """
+ Concrete class for variable shape tensor extension arrays.
+
+ Examples
+ --------
+ Define the extension type for tensor array
+
+ >>> import pyarrow as pa
+ >>> tensor_type = pa.variable_shape_tensor(pa.float64(), 2)
+
+ Create an extension array
+
+ >>> shapes = pa.array([[2, 3], [1, 2]], pa.list_(pa.int32(), 2))
+ >>> values = pa.array([[1, 2, 3, 4, 5, 6], [7, 8]], pa.list_(pa.float64()))
+ >>> arr = pa.StructArray.from_arrays([shapes, values], names=["shape",
"data"])
+ >>> pa.ExtensionArray.from_storage(tensor_type, arr)
+ <pyarrow.lib.VariableShapeTensorArray object at ...>
+ -- is_valid: all not null
+ -- child 0 type: fixed_size_list<item: int32>[2]
+ [
+ [
+ 2,
+ 3
+ ],
+ [
+ 1,
+ 2
+ ]
+ ]
+ -- child 1 type: list<item: double>
+ [
+ [
+ 1,
+ 2,
+ 3,
+ 4,
+ 5,
+ 6
+ ],
+ [
+ 7,
+ 8
+ ]
+ ]
+ """
+
+ @staticmethod
+ def from_numpy_ndarray(obj):
+ """
+ Convert a list of numpy arrays ndarrays to a variable shape tensor
extension array.
+ The length of the list will become the length of the variable shape
tensor array.
+
+ Parameters
+ ----------
+ obj : list of numpy.ndarray
+
+ Examples
+ --------
+ >>> import pyarrow as pa
+ >>> import numpy as np
+ >>> ndarray_list = [
+ ... np.array([[1, 2, 3], [4, 5, 6]], dtype=np.float32),
+ ... np.array([[7, 8]], dtype=np.float32),
Review Comment:
Could we add one more row to see the connection between the length of the
list and the length of the lists in the `VariableShapeTensorArray`?
##########
python/pyarrow/array.pxi:
##########
@@ -4320,6 +4320,134 @@ cdef class FixedShapeTensorArray(ExtensionArray):
)
+cdef class VariableShapeTensorArray(ExtensionArray):
+ """
+ Concrete class for variable shape tensor extension arrays.
+
+ Examples
+ --------
+ Define the extension type for tensor array
+
+ >>> import pyarrow as pa
+ >>> tensor_type = pa.variable_shape_tensor(pa.float64(), 2)
+
+ Create an extension array
+
+ >>> shapes = pa.array([[2, 3], [1, 2]], pa.list_(pa.int32(), 2))
+ >>> values = pa.array([[1, 2, 3, 4, 5, 6], [7, 8]], pa.list_(pa.float64()))
+ >>> arr = pa.StructArray.from_arrays([shapes, values], names=["shape",
"data"])
+ >>> pa.ExtensionArray.from_storage(tensor_type, arr)
+ <pyarrow.lib.VariableShapeTensorArray object at ...>
+ -- is_valid: all not null
+ -- child 0 type: fixed_size_list<item: int32>[2]
+ [
+ [
+ 2,
+ 3
+ ],
+ [
+ 1,
+ 2
+ ]
+ ]
+ -- child 1 type: list<item: double>
+ [
+ [
+ 1,
+ 2,
+ 3,
+ 4,
+ 5,
+ 6
+ ],
+ [
+ 7,
+ 8
+ ]
+ ]
+ """
+
+ @staticmethod
+ def from_numpy_ndarray(obj):
+ """
+ Convert a list of numpy arrays ndarrays to a variable shape tensor
extension array.
+ The length of the list will become the length of the variable shape
tensor array.
Review Comment:
Variable shape tensor array is a struct array so this is a bit confusing for
me. What if we add a bit more context here and explain that the length of the
list will actually become the length of the child arrays? If I am not mistaken,
that is.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
