def test_init_v7(self):
# list of array
fa = FieldArray(
"x", [np.array([[1, 2], [3, 4]]),
np.array([[1, 2], [3, 4]])],
is_input=True)
self.assertEqual(fa.pytype, int)
self.assertEqual(fa.dtype, np.int)
def test_getitem_v1(self):
fa = FieldArray("y", [[1.1, 2.2, 3.3, 4.4, 5.5], [1, 2, 3, 4, 5]],
is_input=True)
self.assertEqual(fa[0], [1.1, 2.2, 3.3, 4.4, 5.5])
ans = fa[[0, 1]]
self.assertTrue(isinstance(ans, np.ndarray))
self.assertTrue(isinstance(ans[0], np.ndarray))
self.assertEqual(ans[0].tolist(), [1.1, 2.2, 3.3, 4.4, 5.5])
self.assertEqual(ans[1].tolist(), [1, 2, 3, 4, 5])
self.assertEqual(ans.dtype, np.float64)
def add_field(self, name, fields, padder=AutoPadder(pad_val=0), is_input=False, is_target=False):
"""Add a new field to the DataSet.
:param str name: the name of the field.
:param fields: a list of int, float, or other objects.
:param int padder: PadBase对象，如何对该Field进行padding。大部分情况使用默认值即可
:param bool is_input: whether this field is model input.
:param bool is_target: whether this field is label or target.
"""
if len(self.field_arrays) != 0:
if len(self) != len(fields):
raise RuntimeError(f"The field to append must have the same size as dataset. "
f"Dataset size {len(self)} != field size {len(fields)}")
self.field_arrays[name] = FieldArray(name, fields, is_target=is_target, is_input=is_input,
padder=padder)
def append(self, ins):
"""Add an instance to the DataSet.
If the DataSet is not empty, the instance must have the same field names as the rest instances in the DataSet.
:param ins: an Instance object
"""
if len(self.field_arrays) == 0:
# DataSet has no field yet
for name, field in ins.fields.items():
self.field_arrays[name] = FieldArray(name, [field])
else:
assert len(self.field_arrays) == len(ins.fields)
for name, field in ins.fields.items():
assert name in self.field_arrays
self.field_arrays[name].append(field)
def test_main(self):
fa = FieldArray("x", [1, 2, 3, 4, 5], is_input=True)
self.assertEqual(len(fa), 5)
fa.append(6)
self.assertEqual(len(fa), 6)
self.assertEqual(fa[-1], 6)
self.assertEqual(fa[0], 1)
fa[-1] = 60
self.assertEqual(fa[-1], 60)
self.assertEqual(fa.get(0), 1)
self.assertTrue(isinstance(fa.get([0, 1, 2]), np.ndarray))
self.assertListEqual(list(fa.get([0, 1, 2])), [1, 2, 3])
def test_support_np_array(self):
fa = FieldArray("y", [np.array([1.1, 2.2, 3.3, 4.4, 5.5])],
is_input=True)
self.assertEqual(fa.dtype, np.ndarray)
self.assertEqual(fa.pytype, np.ndarray)
fa.append(np.array([1.1, 2.2, 3.3, 4.4, 5.5]))
self.assertEqual(fa.dtype, np.ndarray)
self.assertEqual(fa.pytype, np.ndarray)
fa = FieldArray("my_field", np.random.rand(3, 5), is_input=True)
# in this case, pytype is actually a float. We do not care about it.
self.assertEqual(fa.dtype, np.float64)
def append(self, ins):
"""Add an instance to the DataSet.
If the DataSet is not empty, the instance must have the same field names as the rest instances in the DataSet.
:param ins: an Instance object
"""
if len(self.field_arrays) == 0:
# DataSet has no field yet
for name, field in ins.fields.items():
field = field.tolist() if isinstance(field, np.ndarray) else field
self.field_arrays[name] = FieldArray(name, [field]) # 第一个样本，必须用list包装起来
else:
if len(self.field_arrays) != len(ins.fields):
raise ValueError(
"DataSet object has {} fields, but attempt to append an Instance object with {} fields."
.format(len(self.field_arrays), len(ins.fields)))
for name, field in ins.fields.items():
assert name in self.field_arrays
self.field_arrays[name].append(field)
def add_field(self,
name,
fields,
padding_val=0,
is_input=False,
is_target=False):
"""Add a new field to the DataSet.
:param str name: the name of the field.
:param fields: a list of int, float, or other objects.
:param int padding_val: integer for padding.
:param bool is_input: whether this field is model input.
:param bool is_target: whether this field is label or target.
"""
if len(self.field_arrays) != 0:
assert len(self) == len(fields)
self.field_arrays[name] = FieldArray(name,
fields,
padding_val=padding_val,
is_target=is_target,
is_input=is_input)
def add_field(self,
name,
fields,
padding_val=0,
is_input=False,
is_target=False):
"""Add a new field to the DataSet.
:param str name: the name of the field.
:param fields: a list of int, float, or other objects.
:param int padding_val: integer for padding.
:param bool is_input: whether this field is model input.
:param bool is_target: whether this field is label or target.
"""
if len(self.field_arrays) != 0:
if len(self) != len(fields):
raise RuntimeError(
f"The field to append must have the same size as dataset. "
f"Dataset size {len(self)} != field size {len(fields)}")
self.field_arrays[name] = FieldArray(name,
fields,
padding_val=padding_val,
is_target=is_target,
is_input=is_input)
def test_nested_list(self):
fa = FieldArray("y",
[[1.1, 2.2, 3.3, 4.4, 5.5], [1.1, 2.2, 3.3, 4.4, 5.5]],
is_input=True)
self.assertEqual(fa.pytype, float)
self.assertEqual(fa.dtype, np.float64)
def test_type_conversion(self):
fa = FieldArray("x", [1.2, 2.2, 3, 4, 5], is_input=True)
self.assertEqual(fa.pytype, float)
self.assertEqual(fa.dtype, np.float64)
fa = FieldArray("x", [1, 2, 3, 4, 5], is_input=True)
fa.append(1.3333)
self.assertEqual(fa.pytype, float)
self.assertEqual(fa.dtype, np.float64)
fa = FieldArray("y", [1.1, 2.2, 3.3, 4.4, 5.5], is_input=True)
fa.append(10)
self.assertEqual(fa.pytype, float)
self.assertEqual(fa.dtype, np.float64)
fa = FieldArray("y", ["a", "b", "c", "d"], is_input=True)
fa.append("e")
self.assertEqual(fa.dtype, np.str)
self.assertEqual(fa.pytype, str)
def test_getitem_v2(self):
x = np.random.rand(10, 5)
fa = FieldArray("my_field", x, is_input=True)
indices = [0, 1, 3, 4, 6]
for a, b in zip(fa[indices], x[indices]):
self.assertListEqual(a.tolist(), b.tolist())
def test_init_v7(self):
# 二维list
val = np.array([[1, 2], [3, 4]])
fa = FieldArray("x", [val], is_input=True)
fa.append(val)
def test_init_v6(self):
# 二维array
val = [[1, 2], [3, 4]]
fa = FieldArray("x", [val], is_input=True)
fa.append(val)
def test_init_v5(self):
# 一维array
val = np.array([1, 2, 3, 4])
fa = FieldArray("x", [val], is_input=True)
fa.append(val)
def test_init_v4(self):
# 一维list
val = [1, 2, 3, 4]
fa = FieldArray("x", [val], is_input=True)
fa.append(val)
def test_init_v3(self):
# 三维list
fa = FieldArray("x", [[[1, 2], [3, 4]], [[1, 2], [3, 4]]],
is_input=True)
def test_init_v2(self):
# 二维array
fa = FieldArray("x", np.array([[1, 2], [3, 4]] * 5), is_input=True)
def test_init_v1(self):
# 二维list
fa = FieldArray("x", [[1, 2], [3, 4]] * 5, is_input=True)
def test_append(self):
with self.assertRaises(Exception):
fa = FieldArray("y", [[1.1, 2.2, 3.3, 4.4, 5.5], [1, 2, 3, 4, 5]],
is_input=True)
fa.append(0)
with self.assertRaises(Exception):
fa = FieldArray("y", [1.1, 2.2, 3.3, 4.4, 5.5], is_input=True)
fa.append([1, 2, 3, 4, 5])
with self.assertRaises(Exception):
fa = FieldArray("y", [[1.1, 2.2, 3.3, 4.4, 5.5], [1, 2, 3, 4, 5]],
is_input=True)
fa.append([])
with self.assertRaises(Exception):
fa = FieldArray("y", [[1.1, 2.2, 3.3, 4.4, 5.5], [1, 2, 3, 4, 5]],
is_input=True)
fa.append(["str", 0, 0, 0, 1.89])
fa = FieldArray("y", [[1.1, 2.2, 3.3, 4.4, 5.5], [1, 2, 3, 4, 5]],
is_input=True)
fa.append([1.2, 2.3, 3.4, 4.5, 5.6])
self.assertEqual(len(fa), 3)
self.assertEqual(fa[2], [1.2, 2.3, 3.4, 4.5, 5.6])