def _value_with_fmt(self, val):
"""Convert numpy types to Python types for the Excel writers.
Parameters
----------
val : object
Value to be written into cells
Returns
-------
Tuple with the first element being the converted value and the second
being an optional format
"""
fmt = None
if is_integer(val):
val = int(val)
elif is_float(val):
val = float(val)
elif is_bool(val):
val = bool(val)
elif isinstance(val, datetime):
fmt = self.datetime_format
elif isinstance(val, date):
fmt = self.date_format
elif isinstance(val, timedelta):
val = val.total_seconds() / float(86400)
fmt = '0'
else:
val = compat.to_str(val)
return val, fmt
def validate_bool_kwarg(value, arg_name):
""" Ensures that argument passed in arg_name is of type bool. """
if not (is_bool(value) or value is None):
raise ValueError('For argument "%s" expected type bool, '
'received type %s.' %
(arg_name, type(value).__name__))
return value
def validate_bool_kwarg(value, arg_name):
""" Ensures that argument passed in arg_name is of type bool. """
if not (is_bool(value) or value is None):
raise ValueError('For argument "{arg}" expected type bool, received '
'type {typ}.'.format(arg=arg_name,
typ=type(value).__name__))
return value
def _convert_for_op(self, value):
""" Convert value to be insertable to ndarray """
if is_bool(value) or is_bool_dtype(value):
# force conversion to object
# so we don't lose the bools
raise TypeError
return value
def validate_cum_func_with_skipna(skipna, args, kwargs, name):
"""
If this function is called via the 'numpy' library, the third
parameter in its signature is 'dtype', which takes either a
'numpy' dtype or 'None', so check if the 'skipna' parameter is
a boolean or not
"""
if not is_bool(skipna):
args = (skipna,) + args
skipna = True
validate_cum_func(args, kwargs, fname=name)
return skipna
def get_loc(self, key, method=None, tolerance=None):
try:
if np.all(np.isnan(key)) or is_bool(key):
nan_idxs = self._nan_idxs
try:
return nan_idxs.item()
except (ValueError, IndexError):
# should only need to catch ValueError here but on numpy
# 1.7 .item() can raise IndexError when NaNs are present
if not len(nan_idxs):
raise KeyError(key)
return nan_idxs
except (TypeError, NotImplementedError):
pass
return super().get_loc(key, method=method, tolerance=tolerance)
def validate_ordered(ordered):
"""
Validates that we have a valid ordered parameter. If
it is not a boolean, a TypeError will be raised.
Parameters
----------
ordered : object
The parameter to be verified.
Raises
------
TypeError
If 'ordered' is not a boolean.
"""
from pandas.core.dtypes.common import is_bool
if not is_bool(ordered):
raise TypeError("'ordered' must either be 'True' or 'False'")
def _check_for_default_values(fname, arg_val_dict, compat_args):
"""
Check that the keys in `arg_val_dict` are mapped to their
default values as specified in `compat_args`.
Note that this function is to be called only when it has been
checked that arg_val_dict.keys() is a subset of compat_args
"""
for key in arg_val_dict:
# try checking equality directly with '=' operator,
# as comparison may have been overriden for the left
# hand object
try:
v1 = arg_val_dict[key]
v2 = compat_args[key]
# check for None-ness otherwise we could end up
# comparing a numpy array vs None
if (v1 is not None and v2 is None) or \
(v1 is None and v2 is not None):
match = False
else:
match = (v1 == v2)
if not is_bool(match):
raise ValueError("'match' is not a boolean")
# could not compare them directly, so try comparison
# using the 'is' operator
except:
match = (arg_val_dict[key] is compat_args[key])
if not match:
raise ValueError(("the '{arg}' parameter is not "
"supported in the pandas "
"implementation of {fname}()".
format(fname=fname, arg=key)))
def test_is_bool(self):
assert is_bool(True)
assert is_bool(np.bool(False))
assert is_bool(np.bool_(False))
assert not is_bool(1)
assert not is_bool(1.1)
assert not is_bool(1 + 3j)
assert not is_bool(np.int64(1))
assert not is_bool(np.float64(1.1))
assert not is_bool(np.complex128(1 + 3j))
assert not is_bool(np.nan)
assert not is_bool(None)
assert not is_bool('x')
assert not is_bool(datetime(2011, 1, 1))
assert not is_bool(np.datetime64('2011-01-01'))
assert not is_bool(Timestamp('2011-01-01'))
assert not is_bool(Timestamp('2011-01-01', tz='US/Eastern'))
assert not is_bool(timedelta(1000))
assert not is_bool(np.timedelta64(1, 'D'))
assert not is_bool(Timedelta('1 days'))
def test_is_bool(self):
assert is_bool(True)
assert is_bool(np.bool(False))
assert is_bool(np.bool_(False))
assert not is_bool(1)
assert not is_bool(1.1)
assert not is_bool(1 + 3j)
assert not is_bool(np.int64(1))
assert not is_bool(np.float64(1.1))
assert not is_bool(np.complex128(1 + 3j))
assert not is_bool(np.nan)
assert not is_bool(None)
assert not is_bool('x')
assert not is_bool(datetime(2011, 1, 1))
assert not is_bool(np.datetime64('2011-01-01'))
assert not is_bool(Timestamp('2011-01-01'))
assert not is_bool(Timestamp('2011-01-01', tz='US/Eastern'))
assert not is_bool(timedelta(1000))
assert not is_bool(np.timedelta64(1, 'D'))
assert not is_bool(Timedelta('1 days'))
def assert_almost_equal(
left,
right,
check_dtype: bool | str = "equiv",
check_less_precise: bool | int | NoDefault = no_default,
rtol: float = 1.0e-5,
atol: float = 1.0e-8,
**kwargs,
):
"""
Check that the left and right objects are approximately equal.
By approximately equal, we refer to objects that are numbers or that
contain numbers which may be equivalent to specific levels of precision.
Parameters
----------
left : object
right : object
check_dtype : bool or {'equiv'}, default 'equiv'
Check dtype if both a and b are the same type. If 'equiv' is passed in,
then `RangeIndex` and `Int64Index` are also considered equivalent
when doing type checking.
check_less_precise : bool or int, default False
Specify comparison precision. 5 digits (False) or 3 digits (True)
after decimal points are compared. If int, then specify the number
of digits to compare.
When comparing two numbers, if the first number has magnitude less
than 1e-5, we compare the two numbers directly and check whether
they are equivalent within the specified precision. Otherwise, we
compare the **ratio** of the second number to the first number and
check whether it is equivalent to 1 within the specified precision.
.. deprecated:: 1.1.0
Use `rtol` and `atol` instead to define relative/absolute
tolerance, respectively. Similar to :func:`math.isclose`.
rtol : float, default 1e-5
Relative tolerance.
.. versionadded:: 1.1.0
atol : float, default 1e-8
Absolute tolerance.
.. versionadded:: 1.1.0
"""
if check_less_precise is not no_default:
warnings.warn(
"The 'check_less_precise' keyword in testing.assert_*_equal "
"is deprecated and will be removed in a future version. "
"You can stop passing 'check_less_precise' to silence this warning.",
FutureWarning,
stacklevel=2,
)
# error: Argument 1 to "_get_tol_from_less_precise" has incompatible
# type "Union[bool, int, NoDefault]"; expected "Union[bool, int]"
rtol = atol = _get_tol_from_less_precise(
check_less_precise # type: ignore[arg-type]
)
if isinstance(left, Index):
assert_index_equal(
left,
right,
check_exact=False,
exact=check_dtype,
rtol=rtol,
atol=atol,
**kwargs,
)
elif isinstance(left, Series):
assert_series_equal(
left,
right,
check_exact=False,
check_dtype=check_dtype,
rtol=rtol,
atol=atol,
**kwargs,
)
elif isinstance(left, DataFrame):
assert_frame_equal(
left,
right,
check_exact=False,
check_dtype=check_dtype,
rtol=rtol,
atol=atol,
**kwargs,
)
else:
# Other sequences.
if check_dtype:
if is_number(left) and is_number(right):
# Do not compare numeric classes, like np.float64 and float.
pass
elif is_bool(left) and is_bool(right):
# Do not compare bool classes, like np.bool_ and bool.
pass
else:
if isinstance(left, np.ndarray) or isinstance(right, np.ndarray):
obj = "numpy array"
else:
obj = "Input"
assert_class_equal(left, right, obj=obj)
# if we have "equiv", this becomes True
check_dtype = bool(check_dtype)
_testing.assert_almost_equal(
left, right, check_dtype=check_dtype, rtol=rtol, atol=atol, **kwargs
)
def infer_dtype_from_scalar(val, pandas_dtype: bool = False):
"""
Interpret the dtype from a scalar.
Parameters
----------
pandas_dtype : bool, default False
whether to infer dtype including pandas extension types.
If False, scalar belongs to pandas extension types is inferred as
object
"""
dtype = np.object_
# a 1-element ndarray
if isinstance(val, np.ndarray):
msg = "invalid ndarray passed to infer_dtype_from_scalar"
if val.ndim != 0:
raise ValueError(msg)
dtype = val.dtype
val = val.item()
elif isinstance(val, str):
# If we create an empty array using a string to infer
# the dtype, NumPy will only allocate one character per entry
# so this is kind of bad. Alternately we could use np.repeat
# instead of np.empty (but then you still don't want things
# coming out as np.str_!
dtype = np.object_
elif isinstance(val, (np.datetime64, datetime)):
val = tslibs.Timestamp(val)
if val is tslibs.NaT or val.tz is None:
dtype = np.dtype("M8[ns]")
else:
if pandas_dtype:
dtype = DatetimeTZDtype(unit="ns", tz=val.tz)
else:
# return datetimetz as object
return np.object_, val
val = val.value
elif isinstance(val, (np.timedelta64, timedelta)):
val = tslibs.Timedelta(val).value
dtype = np.dtype("m8[ns]")
elif is_bool(val):
dtype = np.bool_
elif is_integer(val):
if isinstance(val, np.integer):
dtype = type(val)
else:
dtype = np.int64
elif is_float(val):
if isinstance(val, np.floating):
dtype = type(val)
else:
dtype = np.float64
elif is_complex(val):
dtype = np.complex_
elif pandas_dtype:
if lib.is_period(val):
dtype = PeriodDtype(freq=val.freq)
val = val.ordinal
elif lib.is_interval(val):
subtype = infer_dtype_from_scalar(val.left, pandas_dtype=True)[0]
dtype = IntervalDtype(subtype=subtype)
return dtype, val
def maybe_promote(dtype, fill_value=np.nan):
"""
Find the minimal dtype that can hold both the given dtype and fill_value.
Parameters
----------
dtype : np.dtype or ExtensionDtype
fill_value : scalar, default np.nan
Returns
-------
dtype
Upcasted from dtype argument if necessary.
fill_value
Upcasted from fill_value argument if necessary.
"""
if not is_scalar(fill_value) and not is_object_dtype(dtype):
# with object dtype there is nothing to promote, and the user can
# pass pretty much any weird fill_value they like
raise ValueError("fill_value must be a scalar")
# if we passed an array here, determine the fill value by dtype
if isinstance(fill_value, np.ndarray):
if issubclass(fill_value.dtype.type, (np.datetime64, np.timedelta64)):
fill_value = fill_value.dtype.type("NaT", "ns")
else:
# we need to change to object type as our
# fill_value is of object type
if fill_value.dtype == np.object_:
dtype = np.dtype(np.object_)
fill_value = np.nan
if dtype == np.object_ or dtype.kind in ["U", "S"]:
# We treat string-like dtypes as object, and _always_ fill
# with np.nan
fill_value = np.nan
dtype = np.dtype(np.object_)
# returns tuple of (dtype, fill_value)
if issubclass(dtype.type, np.datetime64):
if isinstance(fill_value, datetime) and fill_value.tzinfo is not None:
# Trying to insert tzaware into tznaive, have to cast to object
dtype = np.dtype(np.object_)
elif is_integer(fill_value) or (is_float(fill_value)
and not isna(fill_value)):
dtype = np.dtype(np.object_)
else:
try:
fill_value = tslibs.Timestamp(fill_value).to_datetime64()
except (TypeError, ValueError):
dtype = np.dtype(np.object_)
elif issubclass(dtype.type, np.timedelta64):
if (is_integer(fill_value)
or (is_float(fill_value) and not np.isnan(fill_value))
or isinstance(fill_value, str)):
# TODO: What about str that can be a timedelta?
dtype = np.dtype(np.object_)
else:
try:
fv = tslibs.Timedelta(fill_value)
except ValueError:
dtype = np.dtype(np.object_)
else:
if fv is NaT:
# NaT has no `to_timedelta64` method
fill_value = np.timedelta64("NaT", "ns")
else:
fill_value = fv.to_timedelta64()
elif is_datetime64tz_dtype(dtype):
if isna(fill_value):
fill_value = NaT
elif not isinstance(fill_value, datetime):
dtype = np.dtype(np.object_)
elif fill_value.tzinfo is None:
dtype = np.dtype(np.object_)
elif not tz_compare(fill_value.tzinfo, dtype.tz):
# TODO: sure we want to cast here?
dtype = np.dtype(np.object_)
elif is_extension_array_dtype(dtype) and isna(fill_value):
fill_value = dtype.na_value
elif is_float(fill_value):
if issubclass(dtype.type, np.bool_):
dtype = np.dtype(np.object_)
elif issubclass(dtype.type, np.integer):
dtype = np.dtype(np.float64)
elif dtype.kind == "f":
mst = np.min_scalar_type(fill_value)
if mst > dtype:
# e.g. mst is np.float64 and dtype is np.float32
dtype = mst
elif dtype.kind == "c":
mst = np.min_scalar_type(fill_value)
dtype = np.promote_types(dtype, mst)
elif is_bool(fill_value):
if not issubclass(dtype.type, np.bool_):
dtype = np.dtype(np.object_)
elif is_integer(fill_value):
if issubclass(dtype.type, np.bool_):
dtype = np.dtype(np.object_)
elif issubclass(dtype.type, np.integer):
if not np.can_cast(fill_value, dtype):
# upcast to prevent overflow
mst = np.min_scalar_type(fill_value)
dtype = np.promote_types(dtype, mst)
if dtype.kind == "f":
# Case where we disagree with numpy
dtype = np.dtype(np.object_)
elif is_complex(fill_value):
if issubclass(dtype.type, np.bool_):
dtype = np.dtype(np.object_)
elif issubclass(dtype.type, (np.integer, np.floating)):
mst = np.min_scalar_type(fill_value)
dtype = np.promote_types(dtype, mst)
elif dtype.kind == "c":
mst = np.min_scalar_type(fill_value)
if mst > dtype:
# e.g. mst is np.complex128 and dtype is np.complex64
dtype = mst
elif fill_value is None:
if is_float_dtype(dtype) or is_complex_dtype(dtype):
fill_value = np.nan
elif is_integer_dtype(dtype):
dtype = np.float64
fill_value = np.nan
elif is_datetime_or_timedelta_dtype(dtype):
fill_value = dtype.type("NaT", "ns")
else:
dtype = np.dtype(np.object_)
fill_value = np.nan
else:
dtype = np.dtype(np.object_)
# in case we have a string that looked like a number
if is_extension_array_dtype(dtype):
pass
elif issubclass(np.dtype(dtype).type, (bytes, str)):
dtype = np.dtype(np.object_)
fill_value = _ensure_dtype_type(fill_value, dtype)
return dtype, fill_value
def test_is_bool(self):
assert is_bool(True)
assert is_bool(np.bool(False))
assert is_bool(np.bool_(False))
assert not is_bool(1)
assert not is_bool(1.1)
assert not is_bool(1 + 3j)
assert not is_bool(np.int64(1))
assert not is_bool(np.float64(1.1))
assert not is_bool(np.complex128(1 + 3j))
assert not is_bool(np.nan)
assert not is_bool(None)
assert not is_bool("x")
assert not is_bool(datetime(2011, 1, 1))
assert not is_bool(np.datetime64("2011-01-01"))
assert not is_bool(Timestamp("2011-01-01"))
assert not is_bool(Timestamp("2011-01-01", tz="US/Eastern"))
assert not is_bool(timedelta(1000))
assert not is_bool(np.timedelta64(1, "D"))
assert not is_bool(Timedelta("1 days"))
def get_loc(self, key, method=None, tolerance=None):
if is_bool(key):
# Catch this to avoid accidentally casting to 1.0
raise KeyError(key)
return super().get_loc(key, method=method, tolerance=tolerance)
