def normalize_binop_value(self, other):
if isinstance(other, dt.datetime):
other = np.datetime64(other)
elif isinstance(other, dt.timedelta):
other = np.timedelta64(other)
elif isinstance(other, pd.Timestamp):
other = other.to_datetime64()
elif isinstance(other, pd.Timedelta):
other = other.to_timedelta64()
if isinstance(other, np.datetime64):
if np.isnat(other):
return as_scalar(val=None, dtype=self.dtype)
other = other.astype(self.dtype)
return as_scalar(other)
elif isinstance(other, np.timedelta64):
other_time_unit = cudf.utils.dtypes.get_time_unit(other)
if other_time_unit not in ("s", "ms", "ns", "us"):
other = other.astype("timedelta64[s]")
if np.isnat(other):
return as_scalar(val=None, dtype=other.dtype)
return as_scalar(other)
else:
raise TypeError("cannot normalize {}".format(type(other)))
def _binary_op_floordiv(self, rhs):
lhs, rhs = self, rhs
if pd.api.types.is_timedelta64_dtype(rhs.dtype):
common_dtype = determine_out_dtype(self.dtype, rhs.dtype)
lhs = lhs.astype(common_dtype).astype("float64")
if isinstance(rhs, Scalar):
if rhs.is_valid():
if isinstance(rhs, Scalar):
rhs = np.timedelta64(rhs.value)
rhs = rhs.astype(common_dtype).astype("float64")
else:
rhs = as_scalar(None, "float64")
else:
rhs = rhs.astype(common_dtype).astype("float64")
out_dtype = np.dtype("int64")
elif rhs.dtype.kind in ("f", "i", "u"):
out_dtype = self.dtype
else:
raise TypeError(
f"Floor Division of {self.dtype} with {rhs.dtype} "
f"cannot be performed."
)
return lhs, rhs, out_dtype
def _process_col(col, unit, dayfirst, infer_datetime_format, format):
if col.dtype.kind == "M":
return col
if col.dtype.kind in ("f"):
if unit not in (None, "ns"):
factor = as_scalar(
column.datetime._numpy_to_pandas_conversion[unit]
)
col = col.binary_operator(binop="mul", rhs=factor)
col = col.as_datetime_column(dtype="datetime64[ns]")
if col.dtype.kind in ("i"):
if unit in ("D", "h", "m"):
factor = as_scalar(
column.datetime._numpy_to_pandas_conversion[unit]
/ column.datetime._numpy_to_pandas_conversion["s"]
)
col = col.binary_operator(binop="mul", rhs=factor)
col = col.as_datetime_column(dtype=_unit_dtype_map[unit])
elif col.dtype.kind in ("O"):
if unit not in (None, "ns"):
try:
col = col.astype(dtype="int64")
except ValueError:
col = col.astype(dtype="float64")
return _process_col(
col=col,
unit=unit,
dayfirst=dayfirst,
infer_datetime_format=infer_datetime_format,
format=format,
)
else:
if infer_datetime_format and format is None:
format = column.datetime.infer_format(
element=col[0], dayfirst=dayfirst,
)
elif format is None:
format = column.datetime.infer_format(element=col[0])
col = col.as_datetime_column(
dtype=_unit_dtype_map[unit], format=format,
)
return col
def quantile(self, q, interpolation, exact):
result = self.as_numerical.quantile(q=q,
interpolation=interpolation,
exact=exact)
if isinstance(q, Number):
return pd.Timestamp(result, unit=self.time_unit)
result = result.binary_operator(
"mul", as_scalar(_numpy_to_pandas_conversion[self.time_unit]))
return result.astype("datetime64[ns]")
def seconds(self):
"""
Number of seconds (>= 0 and less than 1 day).
Returns
-------
NumericalColumn
"""
# This property must return the number of seconds (>= 0 and
# less than 1 day) for each element, hence first performing
# mod operation to remove the number of days and then performing
# division operation to extract the number of seconds.
return self.binary_operator(
"mod",
as_scalar(np.timedelta64(_numpy_to_pandas_conversion["D"], "ns")),
).binary_operator(
"floordiv",
as_scalar(np.timedelta64(_numpy_to_pandas_conversion["s"], "ns")),
)
def nanoseconds(self):
"""
Return the number of nanoseconds (n), where 0 <= n < 1 microsecond.
Returns
-------
NumericalColumn
"""
# This property must return the number of nanoseconds (>= 0 and
# less than 1 microsecond) for each element, hence first performing
# mod operation to remove the number of microseconds and then
# performing division operation to extract the number
# of nanoseconds.
return self.binary_operator(
"mod",
as_scalar(np.timedelta64(_numpy_to_pandas_conversion["us"], "ns")),
).binary_operator(
"floordiv",
as_scalar(np.timedelta64(_numpy_to_pandas_conversion["ns"], "ns")),
)
def days(self):
"""
Number of days for each element.
Returns
-------
NumericalColumn
"""
return self.binary_operator(
"floordiv",
as_scalar(np.timedelta64(_numpy_to_pandas_conversion["D"], "ns")),
)
def to_datetime(
arg,
errors="raise",
dayfirst=False,
yearfirst=False,
utc=None,
format=None,
exact=True,
unit="ns",
infer_datetime_format=False,
origin="unix",
cache=True,
):
"""
Convert argument to datetime.
Parameters
----------
arg : int, float, str, datetime, list, tuple, 1-d array,
Series DataFrame/dict-like
The object to convert to a datetime.
errors : {'ignore', 'raise', 'coerce', 'warn'}, default 'raise'
- If 'raise', then invalid parsing will raise an exception.
- If 'coerce', then invalid parsing will be set as NaT.
- If 'warn' : prints last exceptions as warnings and
return the input.
- If 'ignore', then invalid parsing will return the input.
dayfirst : bool, default False
Specify a date parse order if `arg` is str or its list-likes.
If True, parses dates with the day first, eg 10/11/12 is parsed as
2012-11-10.
Warning: dayfirst=True is not strict, but will prefer to parse
with day first (this is a known bug, based on dateutil behavior).
format : str, default None
The strftime to parse time, eg "%d/%m/%Y", note that "%f" will parse
all the way up to nanoseconds.
See strftime documentation for more information on choices:
https://docs.python.org/3/library/datetime.html#strftime-and-strptime-behavior.
unit : str, default 'ns'
The unit of the arg (D,s,ms,us,ns) denote the unit, which is an
integer or float number. This will be based off the
origin(unix epoch start).
Example, with unit='ms' and origin='unix' (the default), this
would calculate the number of milliseconds to the unix epoch start.
infer_datetime_format : bool, default False
If True and no `format` is given, attempt to infer the format of the
datetime strings, and if it can be inferred, switch to a faster
method of parsing them. In some cases this can increase the parsing
speed by ~5-10x.
Returns
-------
datetime
If parsing succeeded.
Return type depends on input:
- list-like: DatetimeIndex
- Series: Series of datetime64 dtype
- scalar: Timestamp
Examples
--------
Assembling a datetime from multiple columns of a DataFrame. The keys can be
common abbreviations like ['year', 'month', 'day', 'minute', 'second',
'ms', 'us', 'ns']) or plurals of the same
>>> df = cudf.DataFrame({'year': [2015, 2016],
... 'month': [2, 3],
... 'day': [4, 5]})
>>> cudf.to_datetime(df)
0 2015-02-04
1 2016-03-05
dtype: datetime64[ns]
>>> cudf.to_datetime(1490195805, unit='s')
numpy.datetime64('2017-03-22T15:16:45.000000000')
>>> cudf.to_datetime(1490195805433502912, unit='ns')
numpy.datetime64('1780-11-20T01:02:30.494253056')
"""
if arg is None:
return None
if exact is False:
raise NotImplementedError("exact support is not yet implemented")
if origin != "unix":
raise NotImplementedError("origin support is not yet implemented")
if yearfirst:
raise NotImplementedError("yearfirst support is not yet implemented")
try:
if isinstance(arg, cudf.DataFrame):
# we require at least Ymd
required = ["year", "month", "day"]
req = list(set(required) - set(arg._data.names))
if len(req):
req = ",".join(req)
raise ValueError(
"to assemble mappings requires at least that "
f"[year, month, day] be specified: [{req}] "
"is missing"
)
# replace passed column name with values in _unit_map
unit = {k: get_units(k) for k in arg._data.names}
unit_rev = {v: k for k, v in unit.items()}
# keys we don't recognize
excess = set(unit_rev.keys()) - set(_unit_map.values())
if len(excess):
excess = ",".join(excess)
raise ValueError(
f"extra keys have been passed to the \
datetime assemblage: [{excess}]"
)
new_series = (
arg[unit_rev["year"]].astype("str")
+ "-"
+ arg[unit_rev["month"]].astype("str").str.zfill(2)
+ "-"
+ arg[unit_rev["day"]].astype("str").str.zfill(2)
)
format = "%Y-%m-%d"
col = new_series._column.as_datetime_column(
"datetime64[s]", format=format
)
for u in ["h", "m", "s", "ms", "us", "ns"]:
value = unit_rev.get(u)
if value is not None and value in arg:
arg_col = arg._data[value]
if arg_col.dtype.kind in ("f"):
col = new_series._column.as_datetime_column(
"datetime64[ns]", format=format
)
break
elif arg_col.dtype.kind in ("O"):
if not cpp_is_integer(arg_col).all():
col = new_series._column.as_datetime_column(
"datetime64[ns]", format=format
)
break
times_column = None
for u in ["h", "m", "s", "ms", "us", "ns"]:
value = unit_rev.get(u)
if value is not None and value in arg:
current_col = arg._data[value]
# If the arg[value] is of int or
# float dtype we don't want to type-cast
if current_col.dtype.kind in ("O"):
try:
current_col = current_col.astype(dtype="int64")
except ValueError:
current_col = current_col.astype(dtype="float64")
factor = as_scalar(
column.datetime._numpy_to_pandas_conversion[u]
/ (
column.datetime._numpy_to_pandas_conversion["s"]
if np.datetime_data(col.dtype)[0] == "s"
else 1
)
)
if times_column is None:
times_column = current_col.binary_operator(
binop="mul", rhs=factor
)
else:
times_column = times_column.binary_operator(
binop="add",
rhs=current_col.binary_operator(
binop="mul", rhs=factor
),
)
if times_column is not None:
col = (
col.astype(dtype="int64")
.binary_operator(binop="add", rhs=times_column)
.astype(dtype=col.dtype)
)
return cudf.Series(col, index=arg.index)
elif isinstance(arg, cudf.Index):
col = arg._values
col = _process_col(
col=col,
unit=unit,
dayfirst=dayfirst,
infer_datetime_format=infer_datetime_format,
format=format,
)
return as_index(col, name=arg.name)
elif isinstance(arg, cudf.Series):
col = arg._column
col = _process_col(
col=col,
unit=unit,
dayfirst=dayfirst,
infer_datetime_format=infer_datetime_format,
format=format,
)
return cudf.Series(col, index=arg.index, name=arg.name)
else:
col = column.as_column(arg)
col = _process_col(
col=col,
unit=unit,
dayfirst=dayfirst,
infer_datetime_format=infer_datetime_format,
format=format,
)
if is_scalar(arg):
return col[0]
else:
return as_index(col)
except Exception as e:
if errors == "raise":
raise e
elif errors == "warn":
import traceback
tb = traceback.format_exc()
warnings.warn(tb)
elif errors == "ignore":
pass
elif errors == "coerce":
return np.datetime64("nat", "ns" if unit is None else unit)
return arg
def components(self, index=None):
"""
Return a Dataframe of the components of the Timedeltas.
Returns
-------
DataFrame
Examples
--------
>>> s = pd.Series(pd.to_timedelta(np.arange(5), unit='s'))
>>> s = cudf.Series([12231312123, 1231231231, 1123236768712, 2135656,
... 3244334234], dtype='timedelta64[ms]')
>>> s
0 141 days 13:35:12.123
1 14 days 06:00:31.231
2 13000 days 10:12:48.712
3 0 days 00:35:35.656
4 37 days 13:12:14.234
dtype: timedelta64[ms]
>>> s.dt.components
days hours minutes seconds milliseconds microseconds nanoseconds
0 141 13 35 12 123 0 0
1 14 6 0 31 231 0 0
2 13000 10 12 48 712 0 0
3 0 0 35 35 656 0 0
4 37 13 12 14 234 0 0
""" # noqa: E501
return cudf.DataFrame(
data={
"days": self.binary_operator(
"floordiv",
as_scalar(
np.timedelta64(_numpy_to_pandas_conversion["D"], "ns")
),
),
"hours": self.binary_operator(
"mod",
as_scalar(
np.timedelta64(_numpy_to_pandas_conversion["D"], "ns")
),
).binary_operator(
"floordiv",
as_scalar(
np.timedelta64(_numpy_to_pandas_conversion["h"], "ns")
),
),
"minutes": self.binary_operator(
"mod",
as_scalar(
np.timedelta64(_numpy_to_pandas_conversion["h"], "ns")
),
).binary_operator(
"floordiv",
as_scalar(
np.timedelta64(_numpy_to_pandas_conversion["m"], "ns")
),
),
"seconds": self.binary_operator(
"mod",
as_scalar(
np.timedelta64(_numpy_to_pandas_conversion["m"], "ns")
),
).binary_operator(
"floordiv",
as_scalar(
np.timedelta64(_numpy_to_pandas_conversion["s"], "ns")
),
),
"milliseconds": self.binary_operator(
"mod",
as_scalar(
np.timedelta64(_numpy_to_pandas_conversion["s"], "ns")
),
).binary_operator(
"floordiv",
as_scalar(
np.timedelta64(_numpy_to_pandas_conversion["ms"], "ns")
),
),
"microseconds": self.binary_operator(
"mod",
as_scalar(
np.timedelta64(_numpy_to_pandas_conversion["ms"], "ns")
),
).binary_operator(
"floordiv",
as_scalar(
np.timedelta64(_numpy_to_pandas_conversion["us"], "ns")
),
),
"nanoseconds": self.binary_operator(
"mod",
as_scalar(
np.timedelta64(_numpy_to_pandas_conversion["us"], "ns")
),
).binary_operator(
"floordiv",
as_scalar(
np.timedelta64(_numpy_to_pandas_conversion["ns"], "ns")
),
),
},
index=index,
)
def _process_col(col, unit, dayfirst, infer_datetime_format, format):
if col.dtype.kind == "M":
return col
elif col.dtype.kind == "m":
raise TypeError(
f"dtype {col.dtype} cannot be converted to {_unit_dtype_map[unit]}"
)
if col.dtype.kind in ("f"):
if unit not in (None, "ns"):
factor = as_scalar(
column.datetime._numpy_to_pandas_conversion[unit])
col = col.binary_operator(binop="mul", rhs=factor)
if format is not None:
# Converting to int because,
# pandas actually creates a datetime column
# out of float values and then creates an
# int column out of it to parse against `format`.
# Instead we directly cast to int and perform
# parsing against `format`.
col = (col.astype("int").astype("str").as_datetime_column(
dtype="datetime64[us]" if "%f" in format else "datetime64[s]",
format=format,
))
else:
col = col.as_datetime_column(dtype="datetime64[ns]")
if col.dtype.kind in ("i"):
if unit in ("D", "h", "m"):
factor = as_scalar(
column.datetime._numpy_to_pandas_conversion[unit] /
column.datetime._numpy_to_pandas_conversion["s"])
col = col.binary_operator(binop="mul", rhs=factor)
if format is not None:
col = col.astype("str").as_datetime_column(
dtype=_unit_dtype_map[unit], format=format)
else:
col = col.as_datetime_column(dtype=_unit_dtype_map[unit])
elif col.dtype.kind in ("O"):
if unit not in (None, "ns"):
try:
col = col.astype(dtype="int64")
except ValueError:
col = col.astype(dtype="float64")
return _process_col(
col=col,
unit=unit,
dayfirst=dayfirst,
infer_datetime_format=infer_datetime_format,
format=format,
)
else:
if infer_datetime_format and format is None:
format = column.datetime.infer_format(
element=col[0],
dayfirst=dayfirst,
)
elif format is None:
format = column.datetime.infer_format(element=col[0])
col = col.as_datetime_column(
dtype=_unit_dtype_map[unit],
format=format,
)
return col
