Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

C++ refactoring: ak.strings_astype #1301

Merged
merged 3 commits into from
Feb 24, 2022
Merged

C++ refactoring: ak.strings_astype #1301

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
004657a
ak.strings_astype and testing
ioanaif Feb 21, 2022
8c5a6ba
Fixed test for int32 vs int64
ioanaif Feb 24, 2022
63587ae
[pre-commit.ci] auto fixes from pre-commit.com hooks
pre-commit-ci[bot] Feb 24, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 4 additions & 2 deletions src/awkward/_v2/operations/structure/ak_full_like.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -165,7 +165,9 @@ def action(layout, **kwargs):

out = layout.recursively_apply(action)
if dtype is not None:
out = ak._v2.operations.structure.strings_astype(out, dtype)
out = ak._v2.operations.structure.values_astype(out, dtype)
out = ak._v2.operations.structure.strings_astype(
out, dtype, highlevel, behavior
)
out = ak._v2.operations.structure.values_astype(out, dtype, highlevel, behavior)
return out
return ak._v2._util.wrap(out, behavior, highlevel)
134 changes: 66 additions & 68 deletions src/awkward/_v2/operations/structure/ak_strings_astype.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,76 +1,74 @@
# BSD 3-Clause License; see https://github.com/scikit-hep/awkward-1.0/blob/main/LICENSE


import awkward as ak

np = ak.nplike.NumpyMetadata.instance()


def strings_astype(array, to, highlevel=True, behavior=None):
raise NotImplementedError


# """
# Args:
# array: Array whose strings should be converted to a new numeric type.
# to (dtype or dtype specifier): Type to convert the strings into.
# highlevel (bool): If True, return an #ak.Array; otherwise, return
# a low-level #ak.layout.Content subclass.
# behavior (None or dict): Custom #ak.behavior for the output array, if
# high-level.

# Converts all strings in the array to a new type, leaving the structure
# untouched.

# For example,

# >>> array = ak.Array(["1", "2", " 3 ", "00004", "-5"])
# >>> ak.strings_astype(array, np.int32)
# <Array [1, 2, 3, 4, -5] type='5 * int32'>

# and

# >>> array = ak.Array(["1.1", "2.2", " 3.3 ", "00004.4", "-5.5"])
# >>> ak.strings_astype(array, np.float64)
# <Array [1.1, 2.2, 3.3, 4.4, -5.5] type='5 * float64'>

# and finally,

# >>> array = ak.Array([["1.1", "2.2", " 3.3 "], [], ["00004.4", "-5.5"]])
# >>> ak.strings_astype(array, np.float64)
# <Array [[1.1, 2.2, 3.3], [], [4.4, -5.5]] type='3 * var * float64'>

# See also #ak.numbers_astype.
# """
# to_dtype = np.dtype(to)

# def getfunction(layout):
# if isinstance(layout, ak._v2._util.listtypes) and (
# layout.parameter("__array__") == "string"
# or layout.parameter("__array__") == "bytestring"
# ):
# layout = without_parameters(layout, highlevel=False)
# max_length = ak.max(num(layout))
# regulararray = layout.rpad_and_clip(max_length, 1)
# maskedarray = ak._v2.operations.convert.to_numpy(
# regulararray, allow_missing=True
# )
# npstrings = maskedarray.data
# if maskedarray.mask is not False:
# npstrings[maskedarray.mask] = 0
# npnumbers = (
# npstrings.reshape(-1).view("<S" + str(max_length)).astype(to_dtype)
# )
# return lambda: ak._v2.contents.NumpyArray(npnumbers)
# else:
# return None

# layout = ak._v2.operations.convert.to_layout(
# array, allow_record=False, allow_other=False
# )
# out = ak._v2._util.recursively_apply(
# layout,
# getfunction,
# pass_depth=False,
# pass_user=False,
# )
# return ak._v2._util.maybe_wrap_like(out, array, behavior, highlevel)

"""
Args:
array: Array whose strings should be converted to a new numeric type.
to (dtype or dtype specifier): Type to convert the strings into.
highlevel (bool): If True, return an #ak.Array; otherwise, return
a low-level #ak.layout.Content subclass.
behavior (None or dict): Custom #ak.behavior for the output array, if
high-level.

Converts all strings in the array to a new type, leaving the structure
untouched.

For example,

>>> array = ak.Array(["1", "2", " 3 ", "00004", "-5"])
>>> ak.strings_astype(array, np.int32)
<Array [1, 2, 3, 4, -5] type='5 * int32'>

and

>>> array = ak.Array(["1.1", "2.2", " 3.3 ", "00004.4", "-5.5"])
>>> ak.strings_astype(array, np.float64)
<Array [1.1, 2.2, 3.3, 4.4, -5.5] type='5 * float64'>

and finally,

>>> array = ak.Array([["1.1", "2.2", " 3.3 "], [], ["00004.4", "-5.5"]])
>>> ak.strings_astype(array, np.float64)
<Array [[1.1, 2.2, 3.3], [], [4.4, -5.5]] type='3 * var * float64'>

See also #ak.numbers_astype.
"""
to_dtype = np.dtype(to)

def action(layout, **kwargs):
if layout.is_ListType and (
layout.parameter("__array__") == "string"
or layout.parameter("__array__") == "bytestring"
):
layout = ak._v2.operations.structure.without_parameters(
layout, highlevel=False
)
max_length = ak._v2.operations.reducers.max(
ak._v2.operations.structure.num(layout)
)
regulararray = layout.rpad(max_length, 1)
maskedarray = ak._v2.operations.convert.to_numpy(
regulararray, allow_missing=True
)
npstrings = maskedarray.data
if maskedarray.mask is not False:
npstrings[maskedarray.mask] = 0
npnumbers = (
npstrings.reshape(-1).view("<S" + str(max_length)).astype(to_dtype)
)
return ak._v2.contents.NumpyArray(npnumbers)
else:
return None

layout = ak._v2.operations.convert.to_layout(
array, allow_record=False, allow_other=False
)
out = layout.recursively_apply(action)
return ak._v2._util.wrap(out, behavior, highlevel)
1 change: 0 additions & 1 deletion tests/v2/test_0493-zeros-ones-full-like.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -112,7 +112,6 @@ def test():
]


@pytest.mark.skip(reason="Tests passing, will be enabled in the strings_astype PR.")
def test_full_like_types():

array = ak._v2.highlevel.Array(
Expand Down
92 changes: 57 additions & 35 deletions tests/v2/test_0813-full-like-dtype-arg.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,7 +6,6 @@
import awkward as ak # noqa: F401


@pytest.mark.skip(reason="FIXME: ak.strings_astype not implemented")
def test():
array = ak._v2.Array(
[
Expand Down Expand Up @@ -43,39 +42,51 @@ def assert_array_type(new_array, intended_type):
assert isinstance(new_array[2][4]["y"][3], intended_type)
assert isinstance(new_array[2][4]["y"][4], intended_type)

int_type = ak._v2.operations.structure.full_like(array, 12, dtype=int)
int_type32 = ak._v2.operations.structure.full_like(array, 12, dtype="int32")
int_type64 = ak._v2.operations.structure.full_like(array, 12, dtype="int64")
float_type = ak._v2.operations.structure.full_like(array, 12, dtype=float)
assert int_type.tolist() == float_type.tolist()
assert_array_type(int_type, int)

assert int_type64.tolist() == float_type.tolist()
assert_array_type(int_type32, np.int32)
assert_array_type(int_type64, np.int64)
assert_array_type(float_type, float)

bool_type = ak._v2.operations.structure.full_like(array, 12, dtype=bool)
assert_array_type(bool_type, bool)
assert_array_type(bool_type, np.bool_)

int_type = ak._v2.operations.structure.full_like(array, -1.2, dtype=int)
int_type32 = ak._v2.operations.structure.full_like(array, -1.2, dtype="int32")
int_type64 = ak._v2.operations.structure.full_like(array, -1.2, dtype="int64")
float_type = ak._v2.operations.structure.full_like(array, -1.2, dtype=float)
bool_type = ak._v2.operations.structure.full_like(array, -1.2, dtype=bool)
assert_array_type(int_type, int)

assert_array_type(int_type32, np.int32)
assert_array_type(int_type64, np.int64)
assert_array_type(float_type, float)
assert_array_type(bool_type, bool)
assert_array_type(bool_type, np.bool_)

int_type = ak._v2.operations.structure.zeros_like(array, dtype=int)
int_type32 = ak._v2.operations.structure.zeros_like(array, dtype="int32")
int_type64 = ak._v2.operations.structure.zeros_like(array, dtype="int64")
float_type = ak._v2.operations.structure.zeros_like(array, dtype=float)
bool_type = ak._v2.operations.structure.zeros_like(array, dtype=bool)
assert int_type.tolist() == float_type.tolist()
assert int_type.tolist() == bool_type.tolist()
assert_array_type(int_type, int)

assert int_type64.tolist() == float_type.tolist()
assert int_type64.tolist() == bool_type.tolist()
assert_array_type(int_type32, np.int32)
assert_array_type(int_type64, np.int64)
assert_array_type(float_type, float)
assert_array_type(bool_type, bool)
assert_array_type(bool_type, np.bool_)

int_type = ak._v2.operations.structure.ones_like(array, dtype=int)
int_type32 = ak._v2.operations.structure.ones_like(array, dtype="int32")
int_type64 = ak._v2.operations.structure.ones_like(array, dtype="int64")
float_type = ak._v2.operations.structure.ones_like(array, dtype=float)
bool_type = ak._v2.operations.structure.ones_like(array, dtype=bool)
assert int_type.tolist() == float_type.tolist()
assert int_type.tolist() == bool_type.tolist()
assert_array_type(int_type, int)

assert int_type64.tolist() == float_type.tolist()
assert int_type64.tolist() == bool_type.tolist()
assert_array_type(int_type32, np.int32)
assert_array_type(int_type64, np.int64)
assert_array_type(float_type, float)
assert_array_type(bool_type, bool)
assert_array_type(bool_type, np.bool_)

array = ak.Array([["one", "two", "three"], [], ["four", "five"]])

Expand All @@ -87,36 +98,47 @@ def assert_array_type(new_array, intended_type):
assert isinstance(new_array[2][0], intended_type)
assert isinstance(new_array[2][1], intended_type)

int_type = ak._v2.operations.structure.full_like(array, 12, dtype=int)
int_type32 = ak._v2.operations.structure.full_like(array, 12, dtype="int32")
int_type64 = ak._v2.operations.structure.full_like(array, 12, dtype="int64")
float_type = ak._v2.operations.structure.full_like(array, 12, dtype=float)
assert int_type.tolist() == float_type.tolist()
assert_array_type(int_type, int)

assert int_type64.tolist() == float_type.tolist()
assert_array_type(int_type32, np.int32)
assert_array_type(int_type64, np.int64)
assert_array_type(float_type, float)

bool_type = ak._v2.operations.structure.full_like(array, 12, dtype=bool)
assert_array_type(bool_type, bool)
assert_array_type(bool_type, np.bool_)

int_type = ak._v2.operations.structure.full_like(array, -1.2, dtype=int)
int_type32 = ak._v2.operations.structure.full_like(array, -1.2, dtype="int32")
int_type64 = ak._v2.operations.structure.full_like(array, -1.2, dtype="int64")
float_type = ak._v2.operations.structure.full_like(array, -1.2, dtype=float)
bool_type = ak._v2.operations.structure.full_like(array, -1.2, dtype=bool)
assert_array_type(int_type, int)

assert_array_type(int_type32, np.int32)
assert_array_type(int_type64, np.int64)
assert_array_type(float_type, float)
assert_array_type(bool_type, bool)
assert_array_type(bool_type, np.bool_)

int_type = ak._v2.operations.structure.zeros_like(array, dtype=int)
int_type32 = ak._v2.operations.structure.zeros_like(array, dtype="int32")
int_type64 = ak._v2.operations.structure.zeros_like(array, dtype="int64")
float_type = ak._v2.operations.structure.zeros_like(array, dtype=float)
bool_type = ak._v2.operations.structure.zeros_like(array, dtype=bool)
assert int_type.tolist() == float_type.tolist()
assert int_type.tolist() == bool_type.tolist()
assert_array_type(int_type, int)

assert int_type64.tolist() == float_type.tolist()
assert int_type64.tolist() == bool_type.tolist()
assert_array_type(int_type32, np.int32)
assert_array_type(int_type64, np.int64)
assert_array_type(float_type, float)
assert_array_type(bool_type, bool)
assert_array_type(bool_type, np.bool_)

int_type = ak._v2.operations.structure.ones_like(array, dtype=int)
int_type32 = ak._v2.operations.structure.ones_like(array, dtype="int32")
int_type64 = ak._v2.operations.structure.ones_like(array, dtype="int64")
float_type = ak._v2.operations.structure.ones_like(array, dtype=float)
bool_type = ak._v2.operations.structure.ones_like(array, dtype=bool)
assert int_type.tolist() == float_type.tolist()
assert int_type.tolist() == bool_type.tolist()
assert_array_type(int_type, int)
assert int_type64.tolist() == float_type.tolist()
assert int_type64.tolist() == bool_type.tolist()
assert_array_type(int_type32, np.int32)
assert_array_type(int_type64, np.int64)
assert_array_type(float_type, float)
assert_array_type(bool_type, bool)
assert_array_type(bool_type, np.bool_)