Skip to content

STY: Boolean values for bint variables #33009

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

Merged
merged 2 commits into from
Mar 26, 2020
Merged

STY: Boolean values for bint variables #33009

Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
ef0bb91
STY: Boolean values for bint variables
Mar 25, 2020
d5c70bb
Merge remote-tracking branch 'upstream/master' into STY-bint-boolean-…
Mar 25, 2020
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
132 changes: 66 additions & 66 deletions pandas/_libs/lib.pyx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -530,22 +530,22 @@ def maybe_booleans_to_slice(ndarray[uint8_t] mask):
cdef:
Py_ssize_t i, n = len(mask)
Py_ssize_t start = 0, end = 0
bint started = 0, finished = 0
bint started = False, finished = False

for i in range(n):
if mask[i]:
if finished:
return mask.view(np.bool_)
if not started:
started = 1
started = True
start = i
else:
if finished:
continue

if started:
end = i
finished = 1
finished = True

if not started:
return slice(0, 0)
Expand Down Expand Up @@ -657,13 +657,13 @@ def clean_index_list(obj: list):
cdef:
Py_ssize_t i, n = len(obj)
object val
bint all_arrays = 1
bint all_arrays = True

for i in range(n):
val = obj[i]
if not (isinstance(val, list) or
util.is_array(val) or hasattr(val, '_data')):
all_arrays = 0
all_arrays = False
break

if all_arrays:
Expand Down Expand Up @@ -692,7 +692,7 @@ def clean_index_list(obj: list):
@cython.boundscheck(False)
@cython.wraparound(False)
def generate_bins_dt64(ndarray[int64_t] values, const int64_t[:] binner,
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

can values here be `const int64_t[:]``

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

No, cython raises errors

[1/1] Cythonizing pandas/_libs/lib.pyx

Error compiling Cython file:
------------------------------------------------------------
...
        int64_t l_bin, r_bin, nat_count
        bint right_closed = closed == 'right'

    nat_count = 0
    if hasnans:
        mask = values == NPY_NAT
                     ^
------------------------------------------------------------

pandas/_libs/lib.pyx:707:22: Invalid types for '==' (const int64_t[:], int64_t)
warning: pandas/_libs/lib.pyx:709:24: Index should be typed for more efficient access

Error compiling Cython file:
------------------------------------------------------------
...

    nat_count = 0
    if hasnans:
        mask = values == NPY_NAT
        nat_count = np.sum(mask)
        values = values[~mask]
                      ^
------------------------------------------------------------

pandas/_libs/lib.pyx:709:23: Cannot convert 'int64_t' to memoryviewslice
Traceback (most recent call last):
  File "setup.py", line 791, in <module>
    setup_package()
  File "setup.py", line 761, in setup_package
    ext_modules=maybe_cythonize(extensions, compiler_directives=directives),
  File "setup.py", line 534, in maybe_cythonize
    return cythonize(extensions, *args, **kwargs)
  File "/home/bummy/miniconda3/envs/pandas-dev/lib/python3.7/site-packages/Cython/Build/Dependencies.py", line 1102, in cythonize
    cythonize_one(*args)
  File "/home/bummy/miniconda3/envs/pandas-dev/lib/python3.7/site-packages/Cython/Build/Dependencies.py", line 1225, in cythonize_one
    raise CompileError(None, pyx_file)
Cython.Compiler.Errors.CompileError: pandas/_libs/lib.pyx

object closed='left', bint hasnans=0):
object closed='left', bint hasnans=False):
"""
Int64 (datetime64) version of generic python version in ``groupby.py``.
"""
Expand Down Expand Up @@ -1064,29 +1064,29 @@ cdef class Seen:
bint timedelta_ # seen_timedelta
bint datetimetz_ # seen_datetimetz

def __cinit__(self, bint coerce_numeric=0):
def __cinit__(self, bint coerce_numeric=False):
"""
Initialize a Seen instance.

Parameters
----------
coerce_numeric : bint, default 0
coerce_numeric : bool, default False
Whether or not to force conversion to a numeric data type if
initial methods to convert to numeric fail.
"""
self.int_ = 0
self.nat_ = 0
self.bool_ = 0
self.null_ = 0
self.nan_ = 0
self.uint_ = 0
self.sint_ = 0
self.float_ = 0
self.object_ = 0
self.complex_ = 0
self.datetime_ = 0
self.timedelta_ = 0
self.datetimetz_ = 0
self.int_ = False
self.nat_ = False
self.bool_ = False
self.null_ = False
self.nan_ = False
self.uint_ = False
self.sint_ = False
self.float_ = False
self.object_ = False
self.complex_ = False
self.datetime_ = False
self.timedelta_ = False
self.datetimetz_ = False
self.coerce_numeric = coerce_numeric

cdef inline bint check_uint64_conflict(self) except -1:
Expand Down Expand Up @@ -1127,8 +1127,8 @@ cdef class Seen:
"""
Set flags indicating that a null value was encountered.
"""
self.null_ = 1
self.float_ = 1
self.null_ = True
self.float_ = True

cdef saw_int(self, object val):
"""
Expand All @@ -1147,7 +1147,7 @@ cdef class Seen:
val : Python int
Value with which to set the flags.
"""
self.int_ = 1
self.int_ = True
self.sint_ = self.sint_ or (oINT64_MIN <= val < 0)
self.uint_ = self.uint_ or (oINT64_MAX < val <= oUINT64_MAX)

Expand Down Expand Up @@ -1445,9 +1445,9 @@ def infer_datetimelike_array(arr: object) -> object:
"""
cdef:
Py_ssize_t i, n = len(arr)
bint seen_timedelta = 0, seen_date = 0, seen_datetime = 0
bint seen_tz_aware = 0, seen_tz_naive = 0
bint seen_nat = 0
bint seen_timedelta = False, seen_date = False, seen_datetime = False
bint seen_tz_aware = False, seen_tz_naive = False
bint seen_nat = False
list objs = []
object v

Expand All @@ -1463,27 +1463,27 @@ def infer_datetimelike_array(arr: object) -> object:
# nan or None
pass
elif v is NaT:
seen_nat = 1
seen_nat = True
elif PyDateTime_Check(v):
# datetime
seen_datetime = 1
seen_datetime = True

# disambiguate between tz-naive and tz-aware
if v.tzinfo is None:
seen_tz_naive = 1
seen_tz_naive = True
else:
seen_tz_aware = 1
seen_tz_aware = True

if seen_tz_naive and seen_tz_aware:
return 'mixed'
elif util.is_datetime64_object(v):
# np.datetime64
seen_datetime = 1
seen_datetime = True
elif PyDate_Check(v):
seen_date = 1
seen_date = True
elif is_timedelta(v):
# timedelta, or timedelta64
seen_timedelta = 1
seen_timedelta = True
else:
return "mixed"

Expand Down Expand Up @@ -2035,10 +2035,10 @@ def maybe_convert_numeric(ndarray[object] values, set na_values,

@cython.boundscheck(False)
@cython.wraparound(False)
def maybe_convert_objects(ndarray[object] objects, bint try_float=0,
bint safe=0, bint convert_datetime=0,
bint convert_timedelta=0,
bint convert_to_nullable_integer=0):
def maybe_convert_objects(ndarray[object] objects, bint try_float=False,
bint safe=False, bint convert_datetime=False,
bint convert_timedelta=False,
bint convert_to_nullable_integer=False):
"""
Type inference function-- convert object array to proper dtype

Expand Down Expand Up @@ -2102,45 +2102,45 @@ def maybe_convert_objects(ndarray[object] objects, bint try_float=0,
val = objects[i]

if val is None:
seen.null_ = 1
seen.null_ = True
floats[i] = complexes[i] = fnan
mask[i] = True
elif val is NaT:
seen.nat_ = 1
seen.nat_ = True
if convert_datetime:
idatetimes[i] = NPY_NAT
if convert_timedelta:
itimedeltas[i] = NPY_NAT
if not (convert_datetime or convert_timedelta):
seen.object_ = 1
seen.object_ = True
break
elif val is np.nan:
seen.nan_ = 1
seen.nan_ = True
mask[i] = True
floats[i] = complexes[i] = val
elif util.is_bool_object(val):
seen.bool_ = 1
seen.bool_ = True
bools[i] = val
elif util.is_float_object(val):
floats[i] = complexes[i] = val
seen.float_ = 1
seen.float_ = True
elif util.is_datetime64_object(val):
if convert_datetime:
idatetimes[i] = convert_to_tsobject(
val, None, None, 0, 0).value
seen.datetime_ = 1
seen.datetime_ = True
else:
seen.object_ = 1
seen.object_ = True
break
elif is_timedelta(val):
if convert_timedelta:
itimedeltas[i] = convert_to_timedelta64(val, 'ns')
seen.timedelta_ = 1
seen.timedelta_ = True
else:
seen.object_ = 1
seen.object_ = True
break
elif util.is_integer_object(val):
seen.int_ = 1
seen.int_ = True
floats[i] = <float64_t>val
complexes[i] = <double complex>val
if not seen.null_:
Expand All @@ -2149,7 +2149,7 @@ def maybe_convert_objects(ndarray[object] objects, bint try_float=0,

if ((seen.uint_ and seen.sint_) or
val > oUINT64_MAX or val < oINT64_MIN):
seen.object_ = 1
seen.object_ = True
break

if seen.uint_:
Expand All @@ -2162,40 +2162,40 @@ def maybe_convert_objects(ndarray[object] objects, bint try_float=0,

elif util.is_complex_object(val):
complexes[i] = val
seen.complex_ = 1
seen.complex_ = True
elif PyDateTime_Check(val) or util.is_datetime64_object(val):

# if we have an tz's attached then return the objects
if convert_datetime:
if getattr(val, 'tzinfo', None) is not None:
seen.datetimetz_ = 1
seen.datetimetz_ = True
break
else:
seen.datetime_ = 1
seen.datetime_ = True
idatetimes[i] = convert_to_tsobject(
val, None, None, 0, 0).value
else:
seen.object_ = 1
seen.object_ = True
break
elif try_float and not isinstance(val, str):
# this will convert Decimal objects
try:
floats[i] = float(val)
complexes[i] = complex(val)
seen.float_ = 1
seen.float_ = True
except (ValueError, TypeError):
seen.object_ = 1
seen.object_ = True
break
else:
seen.object_ = 1
seen.object_ = True
break

# we try to coerce datetime w/tz but must all have the same tz
if seen.datetimetz_:
if is_datetime_with_singletz_array(objects):
from pandas import DatetimeIndex
return DatetimeIndex(objects)
seen.object_ = 1
seen.object_ = True

if not seen.object_:
if not safe:
Expand Down Expand Up @@ -2294,7 +2294,7 @@ no_default = object() #: Sentinel indicating the default value.

@cython.boundscheck(False)
@cython.wraparound(False)
def map_infer_mask(ndarray arr, object f, const uint8_t[:] mask, bint convert=1,
def map_infer_mask(ndarray arr, object f, const uint8_t[:] mask, bint convert=True,
object na_value=no_default, object dtype=object):
"""
Substitute for np.vectorize with pandas-friendly dtype inference.
Expand Down Expand Up @@ -2343,16 +2343,16 @@ def map_infer_mask(ndarray arr, object f, const uint8_t[:] mask, bint convert=1,

if convert:
return maybe_convert_objects(result,
try_float=0,
convert_datetime=0,
convert_timedelta=0)
try_float=False,
convert_datetime=False,
convert_timedelta=False)

return result


@cython.boundscheck(False)
@cython.wraparound(False)
def map_infer(ndarray arr, object f, bint convert=1):
def map_infer(ndarray arr, object f, bint convert=True):
"""
Substitute for np.vectorize with pandas-friendly dtype inference.

Expand Down Expand Up @@ -2385,9 +2385,9 @@ def map_infer(ndarray arr, object f, bint convert=1):

if convert:
return maybe_convert_objects(result,
try_float=0,
convert_datetime=0,
convert_timedelta=0)
try_float=False,
convert_datetime=False,
convert_timedelta=False)

return result

Expand Down