def astype_array(values: ArrayLike, dtype: DtypeObj, copy: bool = False) -> ArrayLike:
"""
Cast array (ndarray or ExtensionArray) to the new dtype.
Parameters
----------
values : ndarray or ExtensionArray
dtype : dtype object
copy : bool, default False
copy if indicated
Returns
-------
ndarray or ExtensionArray
"""
if (
values.dtype.kind in ["m", "M"]
and dtype.kind in ["i", "u"]
and isinstance(dtype, np.dtype)
and dtype.itemsize != 8
):
# TODO(2.0) remove special case once deprecation on DTA/TDA is enforced
msg = rf"cannot astype a datetimelike from [{values.dtype}] to [{dtype}]"
raise TypeError(msg)
if is_datetime64tz_dtype(dtype) and is_datetime64_dtype(values.dtype):
return astype_dt64_to_dt64tz(values, dtype, copy, via_utc=True)
if is_dtype_equal(values.dtype, dtype):
if copy:
return values.copy()
return values
if not isinstance(values, np.ndarray):
# i.e. ExtensionArray
values = values.astype(dtype, copy=copy)
else:
values = astype_nansafe(values, dtype, copy=copy)
# in pandas we don't store numpy str dtypes, so convert to object
if isinstance(dtype, np.dtype) and issubclass(values.dtype.type, str):
values = np.array(values, dtype=object)
return values
def na_accum_func(values: ArrayLike, accum_func, skipna: bool) -> ArrayLike:
"""
Cumulative function with skipna support.
Parameters
----------
values : np.ndarray or ExtensionArray
accum_func : {np.cumprod, np.maximum.accumulate, np.cumsum, np.minimum.accumulate}
skipna : bool
Returns
-------
np.ndarray or ExtensionArray
"""
mask_a, mask_b = {
np.cumprod: (1.0, np.nan),
np.maximum.accumulate: (-np.inf, np.nan),
np.cumsum: (0.0, np.nan),
np.minimum.accumulate: (np.inf, np.nan),
}[accum_func]
# We will be applying this function to block values
if values.dtype.kind in ["m", "M"]:
# GH#30460, GH#29058
# numpy 1.18 started sorting NaTs at the end instead of beginning,
# so we need to work around to maintain backwards-consistency.
orig_dtype = values.dtype
# We need to define mask before masking NaTs
mask = isna(values)
if accum_func == np.minimum.accumulate:
# Note: the accum_func comparison fails as an "is" comparison
y = values.view("i8")
y[mask] = np.iinfo(np.int64).max
changed = True
else:
y = values
changed = False
result = accum_func(y.view("i8"), axis=0)
if skipna:
result[mask] = iNaT
elif accum_func == np.minimum.accumulate:
# Restore NaTs that we masked previously
nz = (~np.asarray(mask)).nonzero()[0]
if len(nz):
# everything up to the first non-na entry stays NaT
result[: nz[0]] = iNaT
if changed:
# restore NaT elements
y[mask] = iNaT # TODO: could try/finally for this?
if isinstance(values, np.ndarray):
result = result.view(orig_dtype)
else:
# DatetimeArray
result = type(values)._from_sequence(result, dtype=orig_dtype)
elif skipna and not issubclass(values.dtype.type, (np.integer, np.bool_)):
vals = values.copy()
mask = isna(vals)
vals[mask] = mask_a
result = accum_func(vals, axis=0)
result[mask] = mask_b
else:
result = accum_func(values, axis=0)
return result
def astype_dt64_to_dt64tz(
values: ArrayLike, dtype: DtypeObj, copy: bool, via_utc: bool = False
) -> DatetimeArray:
# GH#33401 we have inconsistent behaviors between
# Datetimeindex[naive].astype(tzaware)
# Series[dt64].astype(tzaware)
# This collects them in one place to prevent further fragmentation.
from pandas.core.construction import ensure_wrapped_if_datetimelike
values = ensure_wrapped_if_datetimelike(values)
values = cast("DatetimeArray", values)
aware = isinstance(dtype, DatetimeTZDtype)
if via_utc:
# Series.astype behavior
# caller is responsible for checking this
assert values.tz is None and aware
dtype = cast(DatetimeTZDtype, dtype)
if copy:
# this should be the only copy
values = values.copy()
warnings.warn(
"Using .astype to convert from timezone-naive dtype to "
"timezone-aware dtype is deprecated and will raise in a "
"future version. Use ser.dt.tz_localize instead.",
FutureWarning,
stacklevel=find_stack_level(),
)
# GH#33401 this doesn't match DatetimeArray.astype, which
# goes through the `not via_utc` path
return values.tz_localize("UTC").tz_convert(dtype.tz)
else:
# DatetimeArray/DatetimeIndex.astype behavior
if values.tz is None and aware:
dtype = cast(DatetimeTZDtype, dtype)
warnings.warn(
"Using .astype to convert from timezone-naive dtype to "
"timezone-aware dtype is deprecated and will raise in a "
"future version. Use obj.tz_localize instead.",
FutureWarning,
stacklevel=find_stack_level(),
)
return values.tz_localize(dtype.tz)
elif aware:
# GH#18951: datetime64_tz dtype but not equal means different tz
dtype = cast(DatetimeTZDtype, dtype)
result = values.tz_convert(dtype.tz)
if copy:
result = result.copy()
return result
elif values.tz is not None:
warnings.warn(
"Using .astype to convert from timezone-aware dtype to "
"timezone-naive dtype is deprecated and will raise in a "
"future version. Use obj.tz_localize(None) or "
"obj.tz_convert('UTC').tz_localize(None) instead",
FutureWarning,
stacklevel=find_stack_level(),
)
result = values.tz_convert("UTC").tz_localize(None)
if copy:
result = result.copy()
return result
raise NotImplementedError("dtype_equal case should be handled elsewhere")
def astype_array_safe(values: ArrayLike,
dtype,
copy: bool = False,
errors: IgnoreRaise = "raise") -> ArrayLike:
"""
Cast array (ndarray or ExtensionArray) to the new dtype.
This basically is the implementation for DataFrame/Series.astype and
includes all custom logic for pandas (NaN-safety, converting str to object,
not allowing )
Parameters
----------
values : ndarray or ExtensionArray
dtype : str, dtype convertible
copy : bool, default False
copy if indicated
errors : str, {'raise', 'ignore'}, default 'raise'
- ``raise`` : allow exceptions to be raised
- ``ignore`` : suppress exceptions. On error return original object
Returns
-------
ndarray or ExtensionArray
"""
errors_legal_values = ("raise", "ignore")
if errors not in errors_legal_values:
invalid_arg = (
"Expected value of kwarg 'errors' to be one of "
f"{list(errors_legal_values)}. Supplied value is '{errors}'")
raise ValueError(invalid_arg)
if inspect.isclass(dtype) and issubclass(dtype, ExtensionDtype):
msg = (f"Expected an instance of {dtype.__name__}, "
"but got the class instead. Try instantiating 'dtype'.")
raise TypeError(msg)
dtype = pandas_dtype(dtype)
if isinstance(dtype, PandasDtype):
# Ensure we don't end up with a PandasArray
dtype = dtype.numpy_dtype
if (is_datetime64_dtype(values.dtype)
# need to do np.dtype check instead of is_datetime64_dtype
# otherwise pyright complains
and isinstance(dtype, np.dtype) and dtype.kind == "M" and
not is_unitless(dtype) and
not is_dtype_equal(dtype, values.dtype)):
# unit conversion, we would re-cast to nanosecond, so this is
# effectively just a copy (regardless of copy kwd)
# TODO(2.0): remove special-case
return values.copy()
try:
new_values = astype_array(values, dtype, copy=copy)
except (ValueError, TypeError):
# e.g. astype_nansafe can fail on object-dtype of strings
# trying to convert to float
if errors == "ignore":
new_values = values
else:
raise
return new_values