def test_unique_masked(self):
# issue 8664
x = np.array([64, 0, 1, 2, 3, 63, 63, 0, 0, 0, 1, 2, 0, 63, 0],
dtype='uint8')
y = np.ma.masked_equal(x, 0)
v = np.unique(y)
v2, i, c = np.unique(y, return_index=True, return_counts=True)
msg = 'Unique returned different results when asked for index'
assert_array_equal(v.data, v2.data, msg)
assert_array_equal(v.mask, v2.mask, msg)
def test_unique_sort_order_with_axis(self):
# These tests fail if sorting along axis is done by treating subarrays
# as unsigned byte strings. See gh-10495.
fmt = "sort order incorrect for integer type '%s'"
for dt in 'bhilq':
a = np.array([[-1], [0]], dt)
b = np.unique(a, axis=0)
assert_array_equal(a, b, fmt % dt)
def in1d(ar1, ar2, assume_unique=False, invert=False):
"""
Test whether each element of a 1-D array is also present in a second array.
Returns a boolean array the same length as `ar1` that is True
where an element of `ar1` is in `ar2` and False otherwise.
We recommend using :func:`isin` instead of `in1d` for new code.
Parameters
----------
ar1 : (M,) array_like
Input array.
ar2 : array_like
The values against which to test each value of `ar1`.
assume_unique : bool, optional
If True, the input arrays are both assumed to be unique, which
can speed up the calculation. Default is False.
invert : bool, optional
If True, the values in the returned array are inverted (that is,
False where an element of `ar1` is in `ar2` and True otherwise).
Default is False. ``np.in1d(a, b, invert=True)`` is equivalent
to (but is faster than) ``np.invert(in1d(a, b))``.
.. versionadded:: 1.8.0
Returns
-------
in1d : (M,) ndarray, bool
The values `ar1[in1d]` are in `ar2`.
See Also
--------
isin : Version of this function that preserves the
shape of ar1.
numpy.lib.arraysetops : Module with a number of other functions for
performing set operations on arrays.
Notes
-----
`in1d` can be considered as an element-wise function version of the
python keyword `in`, for 1-D sequences. ``in1d(a, b)`` is roughly
equivalent to ``np.array([item in b for item in a])``.
However, this idea fails if `ar2` is a set, or similar (non-sequence)
container: As ``ar2`` is converted to an array, in those cases
``asarray(ar2)`` is an object array rather than the expected array of
contained values.
.. versionadded:: 1.4.0
Examples
--------
>>> test = np.array([0, 1, 2, 5, 0])
>>> states = [0, 2]
>>> mask = np.in1d(test, states)
>>> mask
array([ True, False, True, False, True])
>>> test[mask]
array([0, 2, 0])
>>> mask = np.in1d(test, states, invert=True)
>>> mask
array([False, True, False, True, False])
>>> test[mask]
array([1, 5])
"""
# Ravel both arrays, behavior for the first array could be different
ar1 = np.asarray(ar1).ravel()
ar2 = np.asarray(ar2).ravel()
# Check if one of the arrays may contain arbitrary objects
contains_object = ar1.dtype.hasobject or ar2.dtype.hasobject
# This code is run when
# a) the first condition is true, making the code significantly faster
# b) the second condition is true (i.e. `ar1` or `ar2` may contain
# arbitrary objects), since then sorting is not guaranteed to work
if len(ar2) < 10 * len(ar1)**0.145 or contains_object:
if invert:
mask = np.ones(len(ar1), dtype=bool)
for a in ar2:
mask &= (ar1 != a)
else:
mask = np.zeros(len(ar1), dtype=bool)
for a in ar2:
mask |= (ar1 == a)
return mask
# Otherwise use sorting
if not assume_unique:
ar1, rev_idx = np.unique(ar1, return_inverse=True)
ar2 = np.unique(ar2)
ar = np.concatenate((ar1, ar2))
# We need this to be a stable sort, so always use 'mergesort'
# here. The values from the first array should always come before
# the values from the second array.
order = ar.argsort(kind='mergesort')
sar = ar[order]
if invert:
bool_ar = (sar[1:] != sar[:-1])
else:
bool_ar = (sar[1:] == sar[:-1])
flag = np.concatenate((bool_ar, [invert]))
ret = np.empty(ar.shape, dtype=bool)
ret[order] = flag
if assume_unique:
return ret[:len(ar1)]
else:
return ret[rev_idx]
def test_unique_1d(self):
def check_all(a, b, i1, i2, c, dt):
base_msg = 'check {0} failed for type {1}'
msg = base_msg.format('values', dt)
v = unique(a)
assert_array_equal(v, b, msg)
msg = base_msg.format('return_index', dt)
v, j = unique(a, 1, 0, 0)
assert_array_equal(v, b, msg)
assert_array_equal(j, i1, msg)
msg = base_msg.format('return_inverse', dt)
v, j = unique(a, 0, 1, 0)
assert_array_equal(v, b, msg)
assert_array_equal(j, i2, msg)
msg = base_msg.format('return_counts', dt)
v, j = unique(a, 0, 0, 1)
assert_array_equal(v, b, msg)
assert_array_equal(j, c, msg)
msg = base_msg.format('return_index and return_inverse', dt)
v, j1, j2 = unique(a, 1, 1, 0)
assert_array_equal(v, b, msg)
assert_array_equal(j1, i1, msg)
assert_array_equal(j2, i2, msg)
msg = base_msg.format('return_index and return_counts', dt)
v, j1, j2 = unique(a, 1, 0, 1)
assert_array_equal(v, b, msg)
assert_array_equal(j1, i1, msg)
assert_array_equal(j2, c, msg)
msg = base_msg.format('return_inverse and return_counts', dt)
v, j1, j2 = unique(a, 0, 1, 1)
assert_array_equal(v, b, msg)
assert_array_equal(j1, i2, msg)
assert_array_equal(j2, c, msg)
msg = base_msg.format(('return_index, return_inverse '
'and return_counts'), dt)
v, j1, j2, j3 = unique(a, 1, 1, 1)
assert_array_equal(v, b, msg)
assert_array_equal(j1, i1, msg)
assert_array_equal(j2, i2, msg)
assert_array_equal(j3, c, msg)
a = [5, 7, 1, 2, 1, 5, 7] * 10
b = [1, 2, 5, 7]
i1 = [2, 3, 0, 1]
i2 = [2, 3, 0, 1, 0, 2, 3] * 10
c = np.multiply([2, 1, 2, 2], 10)
# test for numeric arrays
types = []
types.extend(np.typecodes['AllInteger'])
types.extend(np.typecodes['AllFloat'])
types.append('datetime64[D]')
types.append('timedelta64[D]')
for dt in types:
aa = np.array(a, dt)
bb = np.array(b, dt)
check_all(aa, bb, i1, i2, c, dt)
# test for object arrays
dt = 'O'
aa = np.empty(len(a), dt)
aa[:] = a
bb = np.empty(len(b), dt)
bb[:] = b
check_all(aa, bb, i1, i2, c, dt)
# test for structured arrays
dt = [('', 'i'), ('', 'i')]
aa = np.array(list(zip(a, a)), dt)
bb = np.array(list(zip(b, b)), dt)
check_all(aa, bb, i1, i2, c, dt)
# test for ticket #2799
aa = [1. + 0.j, 1 - 1.j, 1]
assert_array_equal(np.unique(aa), [1. - 1.j, 1. + 0.j])
# test for ticket #4785
a = [(1, 2), (1, 2), (2, 3)]
unq = [1, 2, 3]
inv = [0, 1, 0, 1, 1, 2]
a1 = unique(a)
assert_array_equal(a1, unq)
a2, a2_inv = unique(a, return_inverse=True)
assert_array_equal(a2, unq)
assert_array_equal(a2_inv, inv)
# test for chararrays with return_inverse (gh-5099)
a = np.chararray(5)
a[...] = ''
a2, a2_inv = np.unique(a, return_inverse=True)
assert_array_equal(a2_inv, np.zeros(5))
# test for ticket #9137
a = []
a1_idx = np.unique(a, return_index=True)[1]
a2_inv = np.unique(a, return_inverse=True)[1]
a3_idx, a3_inv = np.unique(a, return_index=True,
return_inverse=True)[1:]
assert_equal(a1_idx.dtype, np.intp)
assert_equal(a2_inv.dtype, np.intp)
assert_equal(a3_idx.dtype, np.intp)
assert_equal(a3_inv.dtype, np.intp)
def test_unique_zero_sized(self):
# Ticket #205
assert_array_equal([], np.unique(np.array([])))