jorisvandenbossche commented on code in PR #34883:
URL: https://github.com/apache/arrow/pull/34883#discussion_r1159603634
##########
python/pyarrow/array.pxi:
##########
@@ -3076,6 +3076,111 @@ cdef class ExtensionArray(Array):
return Array._to_pandas(self.storage, options, **kwargs)
+class FixedShapeTensorArray(ExtensionArray):
+ """
+ Concrete class for fixed shape tensor extension arrays.
+
+ Examples
+ --------
+ Define the extension type for tensor array
+
+ >>> import pyarrow as pa
+ >>> tensor_type = pa.fixed_shape_tensor(pa.int32(), [2, 2])
+
+ Create an extension array
+
+ >>> arr = [[1, 2, 3, 4], [10, 20, 30, 40], [100, 200, 300, 400]]
+ >>> storage = pa.array(arr, pa.list_(pa.int32(), 4))
+ >>> pa.ExtensionArray.from_storage(tensor_type, storage)
+ <pyarrow.lib.FixedShapeTensorArray object at ...>
+ [
+ [
+ 1,
+ 2,
+ 3,
+ 4
+ ],
+ [
+ 10,
+ 20,
+ 30,
+ 40
+ ],
+ [
+ 100,
+ 200,
+ 300,
+ 400
+ ]
+ ]
+ """
+
+ def to_numpy_ndarray(self):
+ """
+ Convert fixed shape tensor extension array to a numpy array (with
dim+1).
+ """
+ np_flat = np.asarray(self.storage.values)
+ numpy_tensor = np_flat.reshape((len(self),) + tuple(self.type.shape),
+ order='C')
+
+ return numpy_tensor
+
+ @staticmethod
+ def from_numpy_ndarray(obj):
+ """
+ Convert numpy tensors (ndarrays) to a fixed shape tensor extension
array.
+ The first dimension of ndarray will become the length of the fixed
+ shape tensor array.
+
+ Numpy array needs to be C-contiguous in memory
+ (``obj.flags["C_CONTIGUOUS"]==True``).
+
+ Parameters
+ ----------
+ obj : ndarray
Review Comment:
```suggestion
obj : numpy.ndarray
```
##########
python/pyarrow/array.pxi:
##########
@@ -3076,6 +3076,111 @@ cdef class ExtensionArray(Array):
return Array._to_pandas(self.storage, options, **kwargs)
+class FixedShapeTensorArray(ExtensionArray):
+ """
+ Concrete class for fixed shape tensor extension arrays.
+
+ Examples
+ --------
+ Define the extension type for tensor array
+
+ >>> import pyarrow as pa
+ >>> tensor_type = pa.fixed_shape_tensor(pa.int32(), [2, 2])
+
+ Create an extension array
+
+ >>> arr = [[1, 2, 3, 4], [10, 20, 30, 40], [100, 200, 300, 400]]
+ >>> storage = pa.array(arr, pa.list_(pa.int32(), 4))
+ >>> pa.ExtensionArray.from_storage(tensor_type, storage)
+ <pyarrow.lib.FixedShapeTensorArray object at ...>
+ [
+ [
+ 1,
+ 2,
+ 3,
+ 4
+ ],
+ [
+ 10,
+ 20,
+ 30,
+ 40
+ ],
+ [
+ 100,
+ 200,
+ 300,
+ 400
+ ]
+ ]
+ """
+
+ def to_numpy_ndarray(self):
+ """
+ Convert fixed shape tensor extension array to a numpy array (with
dim+1).
+ """
+ np_flat = np.asarray(self.storage.values)
+ numpy_tensor = np_flat.reshape((len(self),) + tuple(self.type.shape),
+ order='C')
+
+ return numpy_tensor
+
+ @staticmethod
+ def from_numpy_ndarray(obj):
+ """
+ Convert numpy tensors (ndarrays) to a fixed shape tensor extension
array.
+ The first dimension of ndarray will become the length of the fixed
+ shape tensor array.
+
+ Numpy array needs to be C-contiguous in memory
+ (``obj.flags["C_CONTIGUOUS"]==True``).
+
+ Parameters
+ ----------
+ obj : ndarray
+
+ Examples
+ --------
+ >>> import pyarrow as pa
+ >>> import numpy as np
+ >>> arr = np.array(
+ ... [[[1, 2, 3], [4, 5, 6]], [[1, 2, 3], [4, 5, 6]]],
+ ... dtype=np.float32)
+ >>> pa.FixedShapeTensorArray.from_numpy_ndarray(arr)
+ <pyarrow.lib.FixedShapeTensorArray object at ...>
+ [
+ [
+ 1,
+ 2,
+ 3,
+ 4,
+ 5,
+ 6
+ ],
+ [
+ 1,
+ 2,
+ 3,
+ 4,
+ 5,
+ 6
+ ]
+ ]
+ """
+ if obj.flags["F_CONTIGUOUS"]:
Review Comment:
```suggestion
if not obj.flags["C_CONTIGUOUS"]:
```
An array can be neither F nor C contiguous, so checking that has to be C is
better here
##########
python/pyarrow/array.pxi:
##########
@@ -3076,6 +3076,111 @@ cdef class ExtensionArray(Array):
return Array._to_pandas(self.storage, options, **kwargs)
+class FixedShapeTensorArray(ExtensionArray):
+ """
+ Concrete class for fixed shape tensor extension arrays.
+
+ Examples
+ --------
+ Define the extension type for tensor array
+
+ >>> import pyarrow as pa
+ >>> tensor_type = pa.fixed_shape_tensor(pa.int32(), [2, 2])
+
+ Create an extension array
+
+ >>> arr = [[1, 2, 3, 4], [10, 20, 30, 40], [100, 200, 300, 400]]
+ >>> storage = pa.array(arr, pa.list_(pa.int32(), 4))
+ >>> pa.ExtensionArray.from_storage(tensor_type, storage)
+ <pyarrow.lib.FixedShapeTensorArray object at ...>
+ [
+ [
+ 1,
+ 2,
+ 3,
+ 4
+ ],
+ [
+ 10,
+ 20,
+ 30,
+ 40
+ ],
+ [
+ 100,
+ 200,
+ 300,
+ 400
+ ]
+ ]
+ """
+
+ def to_numpy_ndarray(self):
+ """
+ Convert fixed shape tensor extension array to a numpy array (with
dim+1).
+ """
+ np_flat = np.asarray(self.storage.values)
+ numpy_tensor = np_flat.reshape((len(self),) + tuple(self.type.shape),
+ order='C')
+
+ return numpy_tensor
+
+ @staticmethod
+ def from_numpy_ndarray(obj):
+ """
+ Convert numpy tensors (ndarrays) to a fixed shape tensor extension
array.
+ The first dimension of ndarray will become the length of the fixed
+ shape tensor array.
+
+ Numpy array needs to be C-contiguous in memory
+ (``obj.flags["C_CONTIGUOUS"]==True``).
+
+ Parameters
+ ----------
+ obj : ndarray
+
+ Examples
+ --------
+ >>> import pyarrow as pa
+ >>> import numpy as np
+ >>> arr = np.array(
+ ... [[[1, 2, 3], [4, 5, 6]], [[1, 2, 3], [4, 5, 6]]],
+ ... dtype=np.float32)
+ >>> pa.FixedShapeTensorArray.from_numpy_ndarray(arr)
+ <pyarrow.lib.FixedShapeTensorArray object at ...>
+ [
+ [
+ 1,
+ 2,
+ 3,
+ 4,
+ 5,
+ 6
+ ],
+ [
+ 1,
+ 2,
+ 3,
+ 4,
+ 5,
+ 6
+ ]
+ ]
+ """
+ if obj.flags["F_CONTIGUOUS"]:
+ raise ValueError('The data in the numpy array need to be in a
single, '
+ 'C-style contiguous segment.')
Review Comment:
We could maybe first resolve the discussion in #34797 before trying to add
it here? (it's not strictly needed to already make this useful)
There are also two possible behaviours: make a copy to ensure C contiguous
preserving the shape, or reshape to get a C contiguous view (but with different
shape).
Leaving it as is for now leaves this choice to the user to do this
explicitly (we could add examples for both). Or could add a keyword to control
how this is done.
--
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]
