def __iter__(self):
stream = pa.output_stream(self.filename)
for item in self.parent:
tensor = pa.Tensor.from_numpy(item)
pa.write_tensor(tensor, stream)
yield
stream.close()
def test_tensor_ipc_strided(tmpdir):
data = np.random.randn(10, 4)
tensor = pa.Tensor.from_numpy(data[::2])
path = os.path.join(str(tmpdir), 'pyarrow-tensor-ipc-strided')
with pytest.raises(ValueError):
mmap = pa.create_memory_map(path, 1024)
pa.write_tensor(tensor, mmap)
def test_tensor_ipc_strided(tmpdir):
data = np.random.randn(10, 4)
tensor = pa.Tensor.from_numpy(data[::2])
path = os.path.join(str(tmpdir), 'pyarrow-tensor-ipc-strided')
with pytest.raises(ValueError):
mmap = pa.create_memory_map(path, 1024)
pa.write_tensor(tensor, mmap)
def test_tensor_ipc_strided():
data = np.random.randn(10, 4)
tensor = pa.Tensor.from_numpy(data[::2])
path = 'pyarrow-tensor-ipc-strided'
try:
with pytest.raises(ValueError):
mmap = pa.create_memory_map(path, 1024)
pa.write_tensor(tensor, mmap)
finally:
_try_delete(path)
def test_read_tensor(tmpdir):
# Create and write tensor tensor
data = np.random.randn(10, 4)
tensor = pa.Tensor.from_numpy(data)
data_size = pa.get_tensor_size(tensor)
path = os.path.join(str(tmpdir), 'pyarrow-tensor-ipc-read-tensor')
write_mmap = pa.create_memory_map(path, data_size)
pa.write_tensor(tensor, write_mmap)
# Try to read tensor
read_mmap = pa.memory_map(path, mode='r')
array = pa.read_tensor(read_mmap).to_numpy()
np.testing.assert_equal(data, array)
def test_read_tensor(tmpdir):
# Create and write tensor tensor
data = np.random.randn(10, 4)
tensor = pa.Tensor.from_numpy(data)
data_size = pa.get_tensor_size(tensor)
path = os.path.join(str(tmpdir), 'pyarrow-tensor-ipc-read-tensor')
write_mmap = pa.create_memory_map(path, data_size)
pa.write_tensor(tensor, write_mmap)
# Try to read tensor
read_mmap = pa.memory_map(path, mode='r')
array = pa.read_tensor(read_mmap).to_numpy()
np.testing.assert_equal(data, array)
def test_tensor_ipc_roundtrip(tmpdir):
data = np.random.randn(10, 4)
tensor = pa.Tensor.from_numpy(data)
path = os.path.join(str(tmpdir), 'pyarrow-tensor-ipc-roundtrip')
mmap = pa.create_memory_map(path, 1024)
pa.write_tensor(tensor, mmap)
mmap.seek(0)
result = pa.read_tensor(mmap)
assert result.equals(tensor)
def test_tensor_ipc_roundtrip(tmpdir):
data = np.random.randn(10, 4)
tensor = pa.Tensor.from_numpy(data)
path = os.path.join(str(tmpdir), 'pyarrow-tensor-ipc-roundtrip')
mmap = pa.create_memory_map(path, 1024)
pa.write_tensor(tensor, mmap)
mmap.seek(0)
result = pa.read_tensor(mmap)
assert result.equals(tensor)
def test_tensor_ipc_read_from_compressed(tempdir):
# ARROW-5910
data = np.random.randn(10, 4)
tensor = pa.Tensor.from_numpy(data)
path = tempdir / 'tensor-compressed-file'
out_stream = pa.output_stream(path, compression='gzip')
pa.write_tensor(tensor, out_stream)
out_stream.close()
result = pa.read_tensor(pa.input_stream(path, compression='gzip'))
assert result.equals(tensor)
def test_store_arrow_objects(self):
data = np.random.randn(10, 4)
# Write an arrow object.
object_id = random_object_id()
tensor = pa.Tensor.from_numpy(data)
data_size = pa.get_tensor_size(tensor)
buf = self.plasma_client.create(object_id, data_size)
stream = pa.FixedSizeBufferWriter(buf)
pa.write_tensor(tensor, stream)
self.plasma_client.seal(object_id)
# Read the arrow object.
[tensor] = self.plasma_client.get_buffers([object_id])
reader = pa.BufferReader(tensor)
array = pa.read_tensor(reader).to_numpy()
# Assert that they are equal.
np.testing.assert_equal(data, array)
def test_store_arrow_objects(self):
data = np.random.randn(10, 4)
# Write an arrow object.
object_id = random_object_id()
tensor = pa.Tensor.from_numpy(data)
data_size = pa.get_tensor_size(tensor)
buf = self.plasma_client.create(object_id, data_size)
stream = pa.FixedSizeBufferWriter(buf)
pa.write_tensor(tensor, stream)
self.plasma_client.seal(object_id)
# Read the arrow object.
[tensor] = self.plasma_client.get_buffers([object_id])
reader = pa.BufferReader(tensor)
array = pa.read_tensor(reader).to_numpy()
# Assert that they are equal.
np.testing.assert_equal(data, array)
def test_tensor_ipc_roundtrip():
data = np.random.randn(10, 4)
tensor = pa.Tensor.from_numpy(data)
path = 'pyarrow-tensor-ipc-roundtrip'
try:
mmap = pa.create_memory_map(path, 1024)
pa.write_tensor(tensor, mmap)
mmap.seek(0)
result = pa.read_tensor(mmap)
assert result.equals(tensor)
finally:
_try_delete(path)
def test_tensor_ipc_strided(tmpdir):
data1 = np.random.randn(10, 4)
tensor1 = pa.Tensor.from_numpy(data1[::2])
data2 = np.random.randn(10, 6, 4)
tensor2 = pa.Tensor.from_numpy(data2[::, ::2, ::])
path = os.path.join(str(tmpdir), 'pyarrow-tensor-ipc-strided')
mmap = pa.create_memory_map(path, 2048)
for tensor in [tensor1, tensor2]:
mmap.seek(0)
pa.write_tensor(tensor, mmap)
mmap.seek(0)
result = pa.read_tensor(mmap)
assert result.equals(tensor)
def test_tensor_ipc_strided(tmpdir):
data1 = np.random.randn(10, 4)
tensor1 = pa.Tensor.from_numpy(data1[::2])
data2 = np.random.randn(10, 6, 4)
tensor2 = pa.Tensor.from_numpy(data2[::, ::2, ::])
path = os.path.join(str(tmpdir), 'pyarrow-tensor-ipc-strided')
mmap = pa.create_memory_map(path, 2048)
for tensor in [tensor1, tensor2]:
mmap.seek(0)
pa.write_tensor(tensor, mmap)
mmap.seek(0)
result = pa.read_tensor(mmap)
assert result.equals(tensor)
#!/usr/bin/env python
import pyarrow as pa
import numpy as np
ndarray = np.random.randn(10, 6)
print(ndarray)
tensor = pa.Tensor.from_numpy(ndarray)
with pa.OSFile("/tmp/tensor.arrow", "wb") as sink:
pa.write_tensor(tensor, sink)
