def argsort(self, ascending=True, kind="quicksort", *args, **kwargs):
"""
Return the indices that would sort this array.
Parameters
----------
ascending : bool, default True
Whether the indices should result in an ascending
or descending sort.
kind : {'quicksort', 'mergesort', 'heapsort'}, optional
Sorting algorithm.
*args, **kwargs:
passed through to :func:`numpy.argsort`.
Returns
-------
index_array : ndarray
Array of indices that sort ``self``. If NaN values are contained,
NaN values are placed at the end.
See Also
--------
numpy.argsort : Sorting implementation used internally.
"""
# Implementor note: You have two places to override the behavior of
# argsort.
# 1. _values_for_argsort : construct the values passed to np.argsort
# 2. argsort : total control over sorting.
ascending = nv.validate_argsort_with_ascending(ascending, args, kwargs)
result = nargsort(self,
kind=kind,
ascending=ascending,
na_position="last")
return result
def test_nargsort(self):
# np.argsort(items) places NaNs last
items = [np.nan] * 5 + list(range(100)) + [np.nan] * 5
# np.argsort(items2) may not place NaNs first
items2 = np.array(items, dtype="O")
# mergesort is the most difficult to get right because we want it to be
# stable.
# According to numpy/core/tests/test_multiarray, """The number of
# sorted items must be greater than ~50 to check the actual algorithm
# because quick and merge sort fall over to insertion sort for small
# arrays."""
# mergesort, ascending=True, na_position='last'
result = nargsort(items, kind="mergesort", ascending=True, na_position="last")
exp = list(range(5, 105)) + list(range(5)) + list(range(105, 110))
tm.assert_numpy_array_equal(result, np.array(exp), check_dtype=False)
# mergesort, ascending=True, na_position='first'
result = nargsort(items, kind="mergesort", ascending=True, na_position="first")
exp = list(range(5)) + list(range(105, 110)) + list(range(5, 105))
tm.assert_numpy_array_equal(result, np.array(exp), check_dtype=False)
# mergesort, ascending=False, na_position='last'
result = nargsort(items, kind="mergesort", ascending=False, na_position="last")
exp = list(range(104, 4, -1)) + list(range(5)) + list(range(105, 110))
tm.assert_numpy_array_equal(result, np.array(exp), check_dtype=False)
# mergesort, ascending=False, na_position='first'
result = nargsort(items, kind="mergesort", ascending=False, na_position="first")
exp = list(range(5)) + list(range(105, 110)) + list(range(104, 4, -1))
tm.assert_numpy_array_equal(result, np.array(exp), check_dtype=False)
# mergesort, ascending=True, na_position='last'
result = nargsort(items2, kind="mergesort", ascending=True, na_position="last")
exp = list(range(5, 105)) + list(range(5)) + list(range(105, 110))
tm.assert_numpy_array_equal(result, np.array(exp), check_dtype=False)
# mergesort, ascending=True, na_position='first'
result = nargsort(items2, kind="mergesort", ascending=True, na_position="first")
exp = list(range(5)) + list(range(105, 110)) + list(range(5, 105))
tm.assert_numpy_array_equal(result, np.array(exp), check_dtype=False)
# mergesort, ascending=False, na_position='last'
result = nargsort(items2, kind="mergesort", ascending=False, na_position="last")
exp = list(range(104, 4, -1)) + list(range(5)) + list(range(105, 110))
tm.assert_numpy_array_equal(result, np.array(exp), check_dtype=False)
# mergesort, ascending=False, na_position='first'
result = nargsort(
items2, kind="mergesort", ascending=False, na_position="first"
)
exp = list(range(5)) + list(range(105, 110)) + list(range(104, 4, -1))
tm.assert_numpy_array_equal(result, np.array(exp), check_dtype=False)
def _stable_series_sort(ser, ascending):
"""
Stable sort for pandas series
Temporary Solution until
https://github.com/pandas-dev/pandas/issues/28697
https://github.com/pandas-dev/pandas/pull/28698
are resolved
"""
from pandas.core.sorting import nargsort
values = ser._values
indexer = nargsort(
values, kind='mergesort', ascending=ascending, na_position='last')
return pd.Series(values[indexer], index=ser.index[indexer])
def test_nargsort(self, ascending, na_position, exp, box):
# list places NaNs last, np.array(..., dtype="O") may not place NaNs first
items = box([np.nan] * 5 + list(range(100)) + [np.nan] * 5)
# mergesort is the most difficult to get right because we want it to be
# stable.
# According to numpy/core/tests/test_multiarray, """The number of
# sorted items must be greater than ~50 to check the actual algorithm
# because quick and merge sort fall over to insertion sort for small
# arrays."""
result = nargsort(items,
kind="mergesort",
ascending=ascending,
na_position=na_position)
tm.assert_numpy_array_equal(result, np.array(exp), check_dtype=False)
def test_nargsort(self, data_missing_for_sorting, na_position, expected):
# GH 25439
result = nargsort(data_missing_for_sorting, na_position=na_position)
tm.assert_numpy_array_equal(result, expected)
def test_nargsort_datetimearray_warning(self):
# https://github.com/pandas-dev/pandas/issues/25439
# can be removed once the FutureWarning for np.array(DTA) is removed
data = to_datetime([0, 2, 0, 1]).tz_localize('Europe/Brussels')
with tm.assert_produces_warning(None):
nargsort(data)
def test_nargsort(self):
# np.argsort(items) places NaNs last
items = [nan] * 5 + list(range(100)) + [nan] * 5
# np.argsort(items2) may not place NaNs first
items2 = np.array(items, dtype='O')
try:
# GH 2785; due to a regression in NumPy1.6.2
np.argsort(np.array([[1, 2], [1, 3], [1, 2]], dtype='i'))
np.argsort(items2, kind='mergesort')
except TypeError:
pytest.skip('requested sort not available for type')
# mergesort is the most difficult to get right because we want it to be
# stable.
# According to numpy/core/tests/test_multiarray, """The number of
# sorted items must be greater than ~50 to check the actual algorithm
# because quick and merge sort fall over to insertion sort for small
# arrays."""
# mergesort, ascending=True, na_position='last'
result = nargsort(items,
kind='mergesort',
ascending=True,
na_position='last')
exp = list(range(5, 105)) + list(range(5)) + list(range(105, 110))
tm.assert_numpy_array_equal(result, np.array(exp), check_dtype=False)
# mergesort, ascending=True, na_position='first'
result = nargsort(items,
kind='mergesort',
ascending=True,
na_position='first')
exp = list(range(5)) + list(range(105, 110)) + list(range(5, 105))
tm.assert_numpy_array_equal(result, np.array(exp), check_dtype=False)
# mergesort, ascending=False, na_position='last'
result = nargsort(items,
kind='mergesort',
ascending=False,
na_position='last')
exp = list(range(104, 4, -1)) + list(range(5)) + list(range(105, 110))
tm.assert_numpy_array_equal(result, np.array(exp), check_dtype=False)
# mergesort, ascending=False, na_position='first'
result = nargsort(items,
kind='mergesort',
ascending=False,
na_position='first')
exp = list(range(5)) + list(range(105, 110)) + list(range(104, 4, -1))
tm.assert_numpy_array_equal(result, np.array(exp), check_dtype=False)
# mergesort, ascending=True, na_position='last'
result = nargsort(items2,
kind='mergesort',
ascending=True,
na_position='last')
exp = list(range(5, 105)) + list(range(5)) + list(range(105, 110))
tm.assert_numpy_array_equal(result, np.array(exp), check_dtype=False)
# mergesort, ascending=True, na_position='first'
result = nargsort(items2,
kind='mergesort',
ascending=True,
na_position='first')
exp = list(range(5)) + list(range(105, 110)) + list(range(5, 105))
tm.assert_numpy_array_equal(result, np.array(exp), check_dtype=False)
# mergesort, ascending=False, na_position='last'
result = nargsort(items2,
kind='mergesort',
ascending=False,
na_position='last')
exp = list(range(104, 4, -1)) + list(range(5)) + list(range(105, 110))
tm.assert_numpy_array_equal(result, np.array(exp), check_dtype=False)
# mergesort, ascending=False, na_position='first'
result = nargsort(items2,
kind='mergesort',
ascending=False,
na_position='first')
exp = list(range(5)) + list(range(105, 110)) + list(range(104, 4, -1))
tm.assert_numpy_array_equal(result, np.array(exp), check_dtype=False)
def test_nargsort_datetimearray_warning(self):
# https://github.com/pandas-dev/pandas/issues/25439
# can be removed once the FutureWarning for np.array(DTA) is removed
data = to_datetime([0, 2, 0, 1]).tz_localize('Europe/Brussels')
with tm.assert_produces_warning(None):
nargsort(data)
def test_nargsort(self):
# np.argsort(items) places NaNs last
items = [nan] * 5 + list(range(100)) + [nan] * 5
# np.argsort(items2) may not place NaNs first
items2 = np.array(items, dtype='O')
# mergesort is the most difficult to get right because we want it to be
# stable.
# According to numpy/core/tests/test_multiarray, """The number of
# sorted items must be greater than ~50 to check the actual algorithm
# because quick and merge sort fall over to insertion sort for small
# arrays."""
# mergesort, ascending=True, na_position='last'
result = nargsort(items, kind='mergesort', ascending=True,
na_position='last')
exp = list(range(5, 105)) + list(range(5)) + list(range(105, 110))
tm.assert_numpy_array_equal(result, np.array(exp), check_dtype=False)
# mergesort, ascending=True, na_position='first'
result = nargsort(items, kind='mergesort', ascending=True,
na_position='first')
exp = list(range(5)) + list(range(105, 110)) + list(range(5, 105))
tm.assert_numpy_array_equal(result, np.array(exp), check_dtype=False)
# mergesort, ascending=False, na_position='last'
result = nargsort(items, kind='mergesort', ascending=False,
na_position='last')
exp = list(range(104, 4, -1)) + list(range(5)) + list(range(105, 110))
tm.assert_numpy_array_equal(result, np.array(exp), check_dtype=False)
# mergesort, ascending=False, na_position='first'
result = nargsort(items, kind='mergesort', ascending=False,
na_position='first')
exp = list(range(5)) + list(range(105, 110)) + list(range(104, 4, -1))
tm.assert_numpy_array_equal(result, np.array(exp), check_dtype=False)
# mergesort, ascending=True, na_position='last'
result = nargsort(items2, kind='mergesort', ascending=True,
na_position='last')
exp = list(range(5, 105)) + list(range(5)) + list(range(105, 110))
tm.assert_numpy_array_equal(result, np.array(exp), check_dtype=False)
# mergesort, ascending=True, na_position='first'
result = nargsort(items2, kind='mergesort', ascending=True,
na_position='first')
exp = list(range(5)) + list(range(105, 110)) + list(range(5, 105))
tm.assert_numpy_array_equal(result, np.array(exp), check_dtype=False)
# mergesort, ascending=False, na_position='last'
result = nargsort(items2, kind='mergesort', ascending=False,
na_position='last')
exp = list(range(104, 4, -1)) + list(range(5)) + list(range(105, 110))
tm.assert_numpy_array_equal(result, np.array(exp), check_dtype=False)
# mergesort, ascending=False, na_position='first'
result = nargsort(items2, kind='mergesort', ascending=False,
na_position='first')
exp = list(range(5)) + list(range(105, 110)) + list(range(104, 4, -1))
tm.assert_numpy_array_equal(result, np.array(exp), check_dtype=False)