def linspace(start: Union[float, np.float64, int, np.int64],
stop: Union[float, np.float64, int,
np.int64], length: Union[int, np.int64]) -> pdarray:
"""
Create a pdarray of linearly-spaced floats in a closed interval.
Parameters
----------
start : Union[float,np.float64, int, np.int64]
Start of interval (inclusive)
stop : Union[float,np.float64, int, np.int64]
End of interval (inclusive)
length : Union[int,np.int64]
Number of points
Returns
-------
pdarray, float64
Array of evenly spaced float values along the interval
Raises
------
TypeError
Raised if start or stop is not a float or int or if length is not an int
See Also
--------
arange
Notes
-----
If that start is greater than stop, the pdarray values are generated
in descending order.
Examples
--------
>>> ak.linspace(0, 1, 5)
array([0, 0.25, 0.5, 0.75, 1])
>>> ak.linspace(start=1, stop=0, length=5)
array([1, 0.75, 0.5, 0.25, 0])
>>> ak.linspace(start=-5, stop=0, length=5)
array([-5, -3.75, -2.5, -1.25, 0])
"""
if not isSupportedNumber(start) or not isSupportedNumber(stop):
raise TypeError(
'both start and stop must be an int, np.int64, float, or np.float64'
)
if not isSupportedNumber(length):
raise TypeError('length must be an int or int64')
repMsg = generic_msg(cmd='linspace',
args="{} {} {}".format(start, stop, length))
return create_pdarray(repMsg)
def where(condition: pdarray, A: Union[numeric_scalars, pdarray],
B: Union[numeric_scalars, pdarray]) -> pdarray:
"""
Returns an array with elements chosen from A and B based upon a
conditioning array. As is the case with numpy.where, the return array
consists of values from the first array (A) where the conditioning array
elements are True and from the second array (B) where the conditioning
array elements are False.
Parameters
----------
condition : pdarray
Used to choose values from A or B
A : Union[numeric_scalars, pdarray]
Value(s) used when condition is True
B : Union[numeric_scalars, pdarray]
Value(s) used when condition is False
Returns
-------
pdarray
Values chosen from A where the condition is True and B where
the condition is False
Raises
------
TypeError
Raised if the condition object is not a pdarray, if A or B is not
an int, np.int64, float, np.float64, or pdarray, if pdarray dtypes
are not supported or do not match, or multiple condition clauses (see
Notes section) are applied
ValueError
Raised if the shapes of the condition, A, and B pdarrays are unequal
Examples
--------
>>> a1 = ak.arange(1,10)
>>> a2 = ak.ones(9, dtype=np.int64)
>>> cond = a1 < 5
>>> ak.where(cond,a1,a2)
array([1, 2, 3, 4, 1, 1, 1, 1, 1])
>>> a1 = ak.arange(1,10)
>>> a2 = ak.ones(9, dtype=np.int64)
>>> cond = a1 == 5
>>> ak.where(cond,a1,a2)
array([1, 1, 1, 1, 5, 1, 1, 1, 1])
>>> a1 = ak.arange(1,10)
>>> a2 = 10
>>> cond = a1 < 5
>>> ak.where(cond,a1,a2)
array([1, 2, 3, 4, 10, 10, 10, 10, 10])
Notes
-----
A and B must have the same dtype and only one conditional clause
is supported e.g., n < 5, n > 1, which is supported in numpy
is not currently supported in Arkouda
"""
if (not isSupportedNumber(A) and not isinstance(A,pdarray)) or \
(not isSupportedNumber(B) and not isinstance(B,pdarray)):
raise TypeError(
'both A and B must be an int, np.int64, float, np.float64, or pdarray'
)
if isinstance(A, pdarray) and isinstance(B, pdarray):
repMsg = generic_msg(cmd="efunc3vv", args="{} {} {} {}".\
format("where",
condition.name,
A.name,
B.name))
# For scalars, try to convert it to the array's dtype
elif isinstance(A, pdarray) and np.isscalar(B):
repMsg = generic_msg(cmd="efunc3vs", args="{} {} {} {} {}".\
format("where",
condition.name,
A.name,
A.dtype.name,
A.format_other(B)))
elif isinstance(B, pdarray) and np.isscalar(A):
repMsg = generic_msg(cmd="efunc3sv", args="{} {} {} {} {}".\
format("where",
condition.name,
B.dtype.name,
B.format_other(A),
B.name))
elif np.isscalar(A) and np.isscalar(B):
# Scalars must share a common dtype (or be cast)
dtA = resolve_scalar_dtype(A)
dtB = resolve_scalar_dtype(B)
# Make sure at least one of the dtypes is supported
if not (dtA in DTypes or dtB in DTypes):
raise TypeError(
("Not implemented for scalar types {} " + "and {}").format(
dtA, dtB))
# If the dtypes are the same, do not cast
if dtA == dtB: # type: ignore
dt = dtA
# If the dtypes are different, try casting one direction then the other
elif dtB in DTypes and np.can_cast(A, dtB):
A = np.dtype(dtB).type(A)
dt = dtB
elif dtA in DTypes and np.can_cast(B, dtA):
B = np.dtype(dtA).type(B)
dt = dtA
# Cannot safely cast
else:
raise TypeError(("Cannot cast between scalars {} and {} to " +
"supported dtype").format(A, B))
repMsg = generic_msg(cmd="efunc3ss", args="{} {} {} {} {} {}".\
format("where",
condition.name,
dt,
A,
dt,
B))
return create_pdarray(type_cast(str, repMsg))
def random_strings_lognormal(logmean : numeric_scalars, logstd : numeric_scalars,
size : int_scalars, characters : str='uppercase',
seed : Optional[int_scalars]=None) -> Strings:
"""
Generate random strings with log-normally distributed lengths and
with characters drawn from a specified set.
Parameters
----------
logmean : numeric_scalars
The log-mean of the length distribution
logstd : numeric_scalars
The log-standard-deviation of the length distribution
size : int_scalars
The number of strings to generate
characters : (uppercase, lowercase, numeric, printable, binary)
The set of characters to draw from
seed : int_scalars, optional
Value used to initialize the random number generator
Returns
-------
Strings
The Strings object encapsulating a pdarray of random strings
Raises
------
TypeError
Raised if logmean is neither a float nor a int, logstd is not a float,
size is not an int, or if characters is not a str
ValueError
Raised if logstd <= 0 or size < 0
See Also
--------
random_strings_lognormal, randint
Notes
-----
The lengths of the generated strings are distributed $Lognormal(\\mu, \\sigma^2)$,
with :math:`\\mu = logmean` and :math:`\\sigma = logstd`. Thus, the strings will
have an average length of :math:`exp(\\mu + 0.5*\\sigma^2)`, a minimum length of
zero, and a heavy tail towards longer strings.
Examples
--------
>>> ak.random_strings_lognormal(2, 0.25, 5, seed=1)
array(['TVKJTE', 'ABOCORHFM', 'LUDMMGTB', 'KWOQNPHZ', 'VSXRRL'])
>>> ak.random_strings_lognormal(2, 0.25, 5, seed=1, characters='printable')
array(['+5"fp-', ']3Q4kC~HF', '=F=`,IE!', 'DjkBa'9(', '5oZ1)='])
"""
if not isSupportedNumber(logmean) or not isSupportedNumber(logstd):
raise TypeError('both logmean and logstd must be an int, np.int64, float, or np.float64')
if logstd <= 0 or size < 0:
raise ValueError("Incompatible arguments: logstd <= 0 or size < 0")
repMsg = generic_msg(cmd="randomStrings", args="{} {} {} {} {} {}".\
format(NUMBER_FORMAT_STRINGS['int64'].format(size),
"lognormal", characters,
NUMBER_FORMAT_STRINGS['float64'].format(logmean),
NUMBER_FORMAT_STRINGS['float64'].format(logstd),
seed))
return Strings(*(cast(str,repMsg).split('+')))
