numpy/lib/tests/test_nanfunctions.py

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562563564565566567568569570571572573574575576577578579580581582583584585586587588589590591592593594595596597598599600601602603604605606607608609610611612613614615616617618619620621622623624625626627628629630631632633634635636637638639640641642643644645646647648649650651652653654655656657658659660661662663664665666667668669670671672673674675676677678679680681682683684685686687688689690691692693694695696697698699700701702703704705706707708709710711712713714715716717718719720721722723724725726727728729730731732733734735736737738739740741742743744745746747748749750751752753754755756757758759760761762763764765766767768769770771772773774775776777778779780781782783784785786787788789790791792793794795796797798799800801802803804805806807808809810811812813814815816817818819820821822823824825826827828829830831832833834835836837838839840841842843844845846847848849850851852853854855856857858859860861862863864865866867868869870871872873874875876877878879880881882883884885886887888889890891892893894895896897898899900901902903904905906907908909910911912913914915916917918919920921922923924925926927
from __future__ import division, absolute_import, print_function

import warnings

import numpy as np
from numpy.testing import (
    assert_, assert_equal, assert_almost_equal, assert_no_warnings,
    assert_raises, assert_array_equal, suppress_warnings
    )


# Test data
_ndat = np.array([[0.6244, np.nan, 0.2692, 0.0116, np.nan, 0.1170],
                  [0.5351, -0.9403, np.nan, 0.2100, 0.4759, 0.2833],
                  [np.nan, np.nan, np.nan, 0.1042, np.nan, -0.5954],
                  [0.1610, np.nan, np.nan, 0.1859, 0.3146, np.nan]])


# Rows of _ndat with nans removed
_rdat = [np.array([0.6244, 0.2692, 0.0116, 0.1170]),
         np.array([0.5351, -0.9403, 0.2100, 0.4759, 0.2833]),
         np.array([0.1042, -0.5954]),
         np.array([0.1610, 0.1859, 0.3146])]

# Rows of _ndat with nans converted to ones
_ndat_ones = np.array([[0.6244, 1.0, 0.2692, 0.0116, 1.0, 0.1170],
                       [0.5351, -0.9403, 1.0, 0.2100, 0.4759, 0.2833],
                       [1.0, 1.0, 1.0, 0.1042, 1.0, -0.5954],
                       [0.1610, 1.0, 1.0, 0.1859, 0.3146, 1.0]])

# Rows of _ndat with nans converted to zeros
_ndat_zeros = np.array([[0.6244, 0.0, 0.2692, 0.0116, 0.0, 0.1170],
                        [0.5351, -0.9403, 0.0, 0.2100, 0.4759, 0.2833],
                        [0.0, 0.0, 0.0, 0.1042, 0.0, -0.5954],
                        [0.1610, 0.0, 0.0, 0.1859, 0.3146, 0.0]])


class TestNanFunctions_MinMax(object):

    nanfuncs = [np.nanmin, np.nanmax]
    stdfuncs = [np.min, np.max]

    def test_mutation(self):
        # Check that passed array is not modified.
        ndat = _ndat.copy()
        for f in self.nanfuncs:
            f(ndat)
            assert_equal(ndat, _ndat)

    def test_keepdims(self):
        mat = np.eye(3)
        for nf, rf in zip(self.nanfuncs, self.stdfuncs):
            for axis in [None, 0, 1]:
                tgt = rf(mat, axis=axis, keepdims=True)
                res = nf(mat, axis=axis, keepdims=True)
                assert_(res.ndim == tgt.ndim)

    def test_out(self):
        mat = np.eye(3)
        for nf, rf in zip(self.nanfuncs, self.stdfuncs):
            resout = np.zeros(3)
            tgt = rf(mat, axis=1)
            res = nf(mat, axis=1, out=resout)
            assert_almost_equal(res, resout)
            assert_almost_equal(res, tgt)

    def test_dtype_from_input(self):
        codes = 'efdgFDG'
        for nf, rf in zip(self.nanfuncs, self.stdfuncs):
            for c in codes:
                mat = np.eye(3, dtype=c)
                tgt = rf(mat, axis=1).dtype.type
                res = nf(mat, axis=1).dtype.type
                assert_(res is tgt)
                # scalar case
                tgt = rf(mat, axis=None).dtype.type
                res = nf(mat, axis=None).dtype.type
                assert_(res is tgt)

    def test_result_values(self):
        for nf, rf in zip(self.nanfuncs, self.stdfuncs):
            tgt = [rf(d) for d in _rdat]
            res = nf(_ndat, axis=1)
            assert_almost_equal(res, tgt)

    def test_allnans(self):
        mat = np.array([np.nan]*9).reshape(3, 3)
        for f in self.nanfuncs:
            for axis in [None, 0, 1]:
                with warnings.catch_warnings(record=True) as w:
                    warnings.simplefilter('always')
                    assert_(np.isnan(f(mat, axis=axis)).all())
                    assert_(len(w) == 1, 'no warning raised')
                    assert_(issubclass(w[0].category, RuntimeWarning))
            # Check scalars
            with warnings.catch_warnings(record=True) as w:
                warnings.simplefilter('always')
                assert_(np.isnan(f(np.nan)))
                assert_(len(w) == 1, 'no warning raised')
                assert_(issubclass(w[0].category, RuntimeWarning))

    def test_masked(self):
        mat = np.ma.fix_invalid(_ndat)
        msk = mat._mask.copy()
        for f in [np.nanmin]:
            res = f(mat, axis=1)
            tgt = f(_ndat, axis=1)
            assert_equal(res, tgt)
            assert_equal(mat._mask, msk)
            assert_(not np.isinf(mat).any())

    def test_scalar(self):
        for f in self.nanfuncs:
            assert_(f(0.) == 0.)

    def test_subclass(self):
        class MyNDArray(np.ndarray):
            pass

        # Check that it works and that type and
        # shape are preserved
        mine = np.eye(3).view(MyNDArray)
        for f in self.nanfuncs:
            res = f(mine, axis=0)
            assert_(isinstance(res, MyNDArray))
            assert_(res.shape == (3,))
            res = f(mine, axis=1)
            assert_(isinstance(res, MyNDArray))
            assert_(res.shape == (3,))
            res = f(mine)
            assert_(res.shape == ())

        # check that rows of nan are dealt with for subclasses (#4628)
        mine[1] = np.nan
        for f in self.nanfuncs:
            with warnings.catch_warnings(record=True) as w:
                warnings.simplefilter('always')
                res = f(mine, axis=0)
                assert_(isinstance(res, MyNDArray))
                assert_(not np.any(np.isnan(res)))
                assert_(len(w) == 0)

            with warnings.catch_warnings(record=True) as w:
                warnings.simplefilter('always')
                res = f(mine, axis=1)
                assert_(isinstance(res, MyNDArray))
                assert_(np.isnan(res[1]) and not np.isnan(res[0])
                        and not np.isnan(res[2]))
                assert_(len(w) == 1, 'no warning raised')
                assert_(issubclass(w[0].category, RuntimeWarning))

            with warnings.catch_warnings(record=True) as w:
                warnings.simplefilter('always')
                res = f(mine)
                assert_(res.shape == ())
                assert_(res != np.nan)
                assert_(len(w) == 0)

    def test_object_array(self):
        arr = np.array([[1.0, 2.0], [np.nan, 4.0], [np.nan, np.nan]], dtype=object)
        assert_equal(np.nanmin(arr), 1.0)
        assert_equal(np.nanmin(arr, axis=0), [1.0, 2.0])

        with warnings.catch_warnings(record=True) as w:
            warnings.simplefilter('always')
            # assert_equal does not work on object arrays of nan
            assert_equal(list(np.nanmin(arr, axis=1)), [1.0, 4.0, np.nan])
            assert_(len(w) == 1, 'no warning raised')
            assert_(issubclass(w[0].category, RuntimeWarning))


class TestNanFunctions_ArgminArgmax(object):

    nanfuncs = [np.nanargmin, np.nanargmax]

    def test_mutation(self):
        # Check that passed array is not modified.
        ndat = _ndat.copy()
        for f in self.nanfuncs:
            f(ndat)
            assert_equal(ndat, _ndat)

    def test_result_values(self):
        for f, fcmp in zip(self.nanfuncs, [np.greater, np.less]):
            for row in _ndat:
                with suppress_warnings() as sup:
                    sup.filter(RuntimeWarning, "invalid value encountered in")
                    ind = f(row)
                    val = row[ind]
                    # comparing with NaN is tricky as the result
                    # is always false except for NaN != NaN
                    assert_(not np.isnan(val))
                    assert_(not fcmp(val, row).any())
                    assert_(not np.equal(val, row[:ind]).any())

    def test_allnans(self):
        mat = np.array([np.nan]*9).reshape(3, 3)
        for f in self.nanfuncs:
            for axis in [None, 0, 1]:
                assert_raises(ValueError, f, mat, axis=axis)
            assert_raises(ValueError, f, np.nan)

    def test_empty(self):
        mat = np.zeros((0, 3))
        for f in self.nanfuncs:
            for axis in [0, None]:
                assert_raises(ValueError, f, mat, axis=axis)
            for axis in [1]:
                res = f(mat, axis=axis)
                assert_equal(res, np.zeros(0))

    def test_scalar(self):
        for f in self.nanfuncs:
            assert_(f(0.) == 0.)

    def test_subclass(self):
        class MyNDArray(np.ndarray):
            pass

        # Check that it works and that type and
        # shape are preserved
        mine = np.eye(3).view(MyNDArray)
        for f in self.nanfuncs:
            res = f(mine, axis=0)
            assert_(isinstance(res, MyNDArray))
            assert_(res.shape == (3,))
            res = f(mine, axis=1)
            assert_(isinstance(res, MyNDArray))
            assert_(res.shape == (3,))
            res = f(mine)
            assert_(res.shape == ())


class TestNanFunctions_IntTypes(object):

    int_types = (np.int8, np.int16, np.int32, np.int64, np.uint8,
                 np.uint16, np.uint32, np.uint64)

    mat = np.array([127, 39, 93, 87, 46])

    def integer_arrays(self):
        for dtype in self.int_types:
            yield self.mat.astype(dtype)

    def test_nanmin(self):
        tgt = np.min(self.mat)
        for mat in self.integer_arrays():
            assert_equal(np.nanmin(mat), tgt)

    def test_nanmax(self):
        tgt = np.max(self.mat)
        for mat in self.integer_arrays():
            assert_equal(np.nanmax(mat), tgt)

    def test_nanargmin(self):
        tgt = np.argmin(self.mat)
        for mat in self.integer_arrays():
            assert_equal(np.nanargmin(mat), tgt)

    def test_nanargmax(self):
        tgt = np.argmax(self.mat)
        for mat in self.integer_arrays():
            assert_equal(np.nanargmax(mat), tgt)

    def test_nansum(self):
        tgt = np.sum(self.mat)
        for mat in self.integer_arrays():
            assert_equal(np.nansum(mat), tgt)

    def test_nanprod(self):
        tgt = np.prod(self.mat)
        for mat in self.integer_arrays():
            assert_equal(np.nanprod(mat), tgt)

    def test_nancumsum(self):
        tgt = np.cumsum(self.mat)
        for mat in self.integer_arrays():
            assert_equal(np.nancumsum(mat), tgt)

    def test_nancumprod(self):
        tgt = np.cumprod(self.mat)
        for mat in self.integer_arrays():
            assert_equal(np.nancumprod(mat), tgt)

    def test_nanmean(self):
        tgt = np.mean(self.mat)
        for mat in self.integer_arrays():
            assert_equal(np.nanmean(mat), tgt)

    def test_nanvar(self):
        tgt = np.var(self.mat)
        for mat in self.integer_arrays():
            assert_equal(np.nanvar(mat), tgt)

        tgt = np.var(mat, ddof=1)
        for mat in self.integer_arrays():
            assert_equal(np.nanvar(mat, ddof=1), tgt)

    def test_nanstd(self):
        tgt = np.std(self.mat)
        for mat in self.integer_arrays():
            assert_equal(np.nanstd(mat), tgt)

        tgt = np.std(self.mat, ddof=1)
        for mat in self.integer_arrays():
            assert_equal(np.nanstd(mat, ddof=1), tgt)


class SharedNanFunctionsTestsMixin(object):
    def test_mutation(self):
        # Check that passed array is not modified.
        ndat = _ndat.copy()
        for f in self.nanfuncs:
            f(ndat)
            assert_equal(ndat, _ndat)

    def test_keepdims(self):
        mat = np.eye(3)
        for nf, rf in zip(self.nanfuncs, self.stdfuncs):
            for axis in [None, 0, 1]:
                tgt = rf(mat, axis=axis, keepdims=True)
                res = nf(mat, axis=axis, keepdims=True)
                assert_(res.ndim == tgt.ndim)

    def test_out(self):
        mat = np.eye(3)
        for nf, rf in zip(self.nanfuncs, self.stdfuncs):
            resout = np.zeros(3)
            tgt = rf(mat, axis=1)
            res = nf(mat, axis=1, out=resout)
            assert_almost_equal(res, resout)
            assert_almost_equal(res, tgt)

    def test_dtype_from_dtype(self):
        mat = np.eye(3)
        codes = 'efdgFDG'
        for nf, rf in zip(self.nanfuncs, self.stdfuncs):
            for c in codes:
                with suppress_warnings() as sup:
                    if nf in {np.nanstd, np.nanvar} and c in 'FDG':
                        # Giving the warning is a small bug, see gh-8000
                        sup.filter(np.ComplexWarning)
                    tgt = rf(mat, dtype=np.dtype(c), axis=1).dtype.type
                    res = nf(mat, dtype=np.dtype(c), axis=1).dtype.type
                    assert_(res is tgt)
                    # scalar case
                    tgt = rf(mat, dtype=np.dtype(c), axis=None).dtype.type
                    res = nf(mat, dtype=np.dtype(c), axis=None).dtype.type
                    assert_(res is tgt)

    def test_dtype_from_char(self):
        mat = np.eye(3)
        codes = 'efdgFDG'
        for nf, rf in zip(self.nanfuncs, self.stdfuncs):
            for c in codes:
                with suppress_warnings() as sup:
                    if nf in {np.nanstd, np.nanvar} and c in 'FDG':
                        # Giving the warning is a small bug, see gh-8000
                        sup.filter(np.ComplexWarning)
                    tgt = rf(mat, dtype=c, axis=1).dtype.type
                    res = nf(mat, dtype=c, axis=1).dtype.type
                    assert_(res is tgt)
                    # scalar case
                    tgt = rf(mat, dtype=c, axis=None).dtype.type
                    res = nf(mat, dtype=c, axis=None).dtype.type
                    assert_(res is tgt)

    def test_dtype_from_input(self):
        codes = 'efdgFDG'
        for nf, rf in zip(self.nanfuncs, self.stdfuncs):
            for c in codes:
                mat = np.eye(3, dtype=c)
                tgt = rf(mat, axis=1).dtype.type
                res = nf(mat, axis=1).dtype.type
                assert_(res is tgt, "res %s, tgt %s" % (res, tgt))
                # scalar case
                tgt = rf(mat, axis=None).dtype.type
                res = nf(mat, axis=None).dtype.type
                assert_(res is tgt)

    def test_result_values(self):
        for nf, rf in zip(self.nanfuncs, self.stdfuncs):
            tgt = [rf(d) for d in _rdat]
            res = nf(_ndat, axis=1)
            assert_almost_equal(res, tgt)

    def test_scalar(self):
        for f in self.nanfuncs:
            assert_(f(0.) == 0.)

    def test_subclass(self):
        class MyNDArray(np.ndarray):
            pass

        # Check that it works and that type and
        # shape are preserved
        array = np.eye(3)
        mine = array.view(MyNDArray)
        for f in self.nanfuncs:
            expected_shape = f(array, axis=0).shape
            res = f(mine, axis=0)
            assert_(isinstance(res, MyNDArray))
            assert_(res.shape == expected_shape)
            expected_shape = f(array, axis=1).shape
            res = f(mine, axis=1)
            assert_(isinstance(res, MyNDArray))
            assert_(res.shape == expected_shape)
            expected_shape = f(array).shape
            res = f(mine)
            assert_(isinstance(res, MyNDArray))
            assert_(res.shape == expected_shape)


class TestNanFunctions_SumProd(SharedNanFunctionsTestsMixin):

    nanfuncs = [np.nansum, np.nanprod]
    stdfuncs = [np.sum, np.prod]

    def test_allnans(self):
        # Check for FutureWarning
        with warnings.catch_warnings(record=True) as w:
            warnings.simplefilter('always')
            res = np.nansum([np.nan]*3, axis=None)
            assert_(res == 0, 'result is not 0')
            assert_(len(w) == 0, 'warning raised')
            # Check scalar
            res = np.nansum(np.nan)
            assert_(res == 0, 'result is not 0')
            assert_(len(w) == 0, 'warning raised')
            # Check there is no warning for not all-nan
            np.nansum([0]*3, axis=None)
            assert_(len(w) == 0, 'unwanted warning raised')

    def test_empty(self):
        for f, tgt_value in zip([np.nansum, np.nanprod], [0, 1]):
            mat = np.zeros((0, 3))
            tgt = [tgt_value]*3
            res = f(mat, axis=0)
            assert_equal(res, tgt)
            tgt = []
            res = f(mat, axis=1)
            assert_equal(res, tgt)
            tgt = tgt_value
            res = f(mat, axis=None)
            assert_equal(res, tgt)


class TestNanFunctions_CumSumProd(SharedNanFunctionsTestsMixin):

    nanfuncs = [np.nancumsum, np.nancumprod]
    stdfuncs = [np.cumsum, np.cumprod]

    def test_allnans(self):
        for f, tgt_value in zip(self.nanfuncs, [0, 1]):
            # Unlike other nan-functions, sum/prod/cumsum/cumprod don't warn on all nan input
            with assert_no_warnings():
                res = f([np.nan]*3, axis=None)
                tgt = tgt_value*np.ones((3))
                assert_(np.array_equal(res, tgt), 'result is not %s * np.ones((3))' % (tgt_value))
                # Check scalar
                res = f(np.nan)
                tgt = tgt_value*np.ones((1))
                assert_(np.array_equal(res, tgt), 'result is not %s * np.ones((1))' % (tgt_value))
                # Check there is no warning for not all-nan
                f([0]*3, axis=None)

    def test_empty(self):
        for f, tgt_value in zip(self.nanfuncs, [0, 1]):
            mat = np.zeros((0, 3))
            tgt = tgt_value*np.ones((0, 3))
            res = f(mat, axis=0)
            assert_equal(res, tgt)
            tgt = mat
            res = f(mat, axis=1)
            assert_equal(res, tgt)
            tgt = np.zeros((0))
            res = f(mat, axis=None)
            assert_equal(res, tgt)

    def test_keepdims(self):
        for f, g in zip(self.nanfuncs, self.stdfuncs):
            mat = np.eye(3)
            for axis in [None, 0, 1]:
                tgt = f(mat, axis=axis, out=None)
                res = g(mat, axis=axis, out=None)
                assert_(res.ndim == tgt.ndim)

        for f in self.nanfuncs:
            d = np.ones((3, 5, 7, 11))
            # Randomly set some elements to NaN:
            rs = np.random.RandomState(0)
            d[rs.rand(*d.shape) < 0.5] = np.nan
            res = f(d, axis=None)
            assert_equal(res.shape, (1155,))
            for axis in np.arange(4):
                res = f(d, axis=axis)
                assert_equal(res.shape, (3, 5, 7, 11))

    def test_result_values(self):
        for axis in (-2, -1, 0, 1, None):
            tgt = np.cumprod(_ndat_ones, axis=axis)
            res = np.nancumprod(_ndat, axis=axis)
            assert_almost_equal(res, tgt)
            tgt = np.cumsum(_ndat_zeros,axis=axis)
            res = np.nancumsum(_ndat, axis=axis)
            assert_almost_equal(res, tgt)

    def test_out(self):
        mat = np.eye(3)
        for nf, rf in zip(self.nanfuncs, self.stdfuncs):
            resout = np.eye(3)
            for axis in (-2, -1, 0, 1):
                tgt = rf(mat, axis=axis)
                res = nf(mat, axis=axis, out=resout)
                assert_almost_equal(res, resout)
                assert_almost_equal(res, tgt)


class TestNanFunctions_MeanVarStd(SharedNanFunctionsTestsMixin):

    nanfuncs = [np.nanmean, np.nanvar, np.nanstd]
    stdfuncs = [np.mean, np.var, np.std]

    def test_dtype_error(self):
        for f in self.nanfuncs:
            for dtype in [np.bool_, np.int_, np.object_]:
                assert_raises(TypeError, f, _ndat, axis=1, dtype=dtype)

    def test_out_dtype_error(self):
        for f in self.nanfuncs:
            for dtype in [np.bool_, np.int_, np.object_]:
                out = np.empty(_ndat.shape[0], dtype=dtype)
                assert_raises(TypeError, f, _ndat, axis=1, out=out)

    def test_ddof(self):
        nanfuncs = [np.nanvar, np.nanstd]
        stdfuncs = [np.var, np.std]
        for nf, rf in zip(nanfuncs, stdfuncs):
            for ddof in [0, 1]:
                tgt = [rf(d, ddof=ddof) for d in _rdat]
                res = nf(_ndat, axis=1, ddof=ddof)
                assert_almost_equal(res, tgt)

    def test_ddof_too_big(self):
        nanfuncs = [np.nanvar, np.nanstd]
        stdfuncs = [np.var, np.std]
        dsize = [len(d) for d in _rdat]
        for nf, rf in zip(nanfuncs, stdfuncs):
            for ddof in range(5):
                with suppress_warnings() as sup:
                    sup.record(RuntimeWarning)
                    sup.filter(np.ComplexWarning)
                    tgt = [ddof >= d for d in dsize]
                    res = nf(_ndat, axis=1, ddof=ddof)
                    assert_equal(np.isnan(res), tgt)
                    if any(tgt):
                        assert_(len(sup.log) == 1)
                    else:
                        assert_(len(sup.log) == 0)

    def test_allnans(self):
        mat = np.array([np.nan]*9).reshape(3, 3)
        for f in self.nanfuncs:
            for axis in [None, 0, 1]:
                with warnings.catch_warnings(record=True) as w:
                    warnings.simplefilter('always')
                    assert_(np.isnan(f(mat, axis=axis)).all())
                    assert_(len(w) == 1)
                    assert_(issubclass(w[0].category, RuntimeWarning))
                    # Check scalar
                    assert_(np.isnan(f(np.nan)))
                    assert_(len(w) == 2)
                    assert_(issubclass(w[0].category, RuntimeWarning))

    def test_empty(self):
        mat = np.zeros((0, 3))
        for f in self.nanfuncs:
            for axis in [0, None]:
                with warnings.catch_warnings(record=True) as w:
                    warnings.simplefilter('always')
                    assert_(np.isnan(f(mat, axis=axis)).all())
                    assert_(len(w) == 1)
                    assert_(issubclass(w[0].category, RuntimeWarning))
            for axis in [1]:
                with warnings.catch_warnings(record=True) as w:
                    warnings.simplefilter('always')
                    assert_equal(f(mat, axis=axis), np.zeros([]))
                    assert_(len(w) == 0)


class TestNanFunctions_Median(object):

    def test_mutation(self):
        # Check that passed array is not modified.
        ndat = _ndat.copy()
        np.nanmedian(ndat)
        assert_equal(ndat, _ndat)

    def test_keepdims(self):
        mat = np.eye(3)
        for axis in [None, 0, 1]:
            tgt = np.median(mat, axis=axis, out=None, overwrite_input=False)
            res = np.nanmedian(mat, axis=axis, out=None, overwrite_input=False)
            assert_(res.ndim == tgt.ndim)

        d = np.ones((3, 5, 7, 11))
        # Randomly set some elements to NaN:
        w = np.random.random((4, 200)) * np.array(d.shape)[:, None]
        w = w.astype(np.intp)
        d[tuple(w)] = np.nan
        with suppress_warnings() as sup:
            sup.filter(RuntimeWarning)
            res = np.nanmedian(d, axis=None, keepdims=True)
            assert_equal(res.shape, (1, 1, 1, 1))
            res = np.nanmedian(d, axis=(0, 1), keepdims=True)
            assert_equal(res.shape, (1, 1, 7, 11))
            res = np.nanmedian(d, axis=(0, 3), keepdims=True)
            assert_equal(res.shape, (1, 5, 7, 1))
            res = np.nanmedian(d, axis=(1,), keepdims=True)
            assert_equal(res.shape, (3, 1, 7, 11))
            res = np.nanmedian(d, axis=(0, 1, 2, 3), keepdims=True)
            assert_equal(res.shape, (1, 1, 1, 1))
            res = np.nanmedian(d, axis=(0, 1, 3), keepdims=True)
            assert_equal(res.shape, (1, 1, 7, 1))

    def test_out(self):
        mat = np.random.rand(3, 3)
        nan_mat = np.insert(mat, [0, 2], np.nan, axis=1)
        resout = np.zeros(3)
        tgt = np.median(mat, axis=1)
        res = np.nanmedian(nan_mat, axis=1, out=resout)
        assert_almost_equal(res, resout)
        assert_almost_equal(res, tgt)
        # 0-d output:
        resout = np.zeros(())
        tgt = np.median(mat, axis=None)
        res = np.nanmedian(nan_mat, axis=None, out=resout)
        assert_almost_equal(res, resout)
        assert_almost_equal(res, tgt)
        res = np.nanmedian(nan_mat, axis=(0, 1), out=resout)
        assert_almost_equal(res, resout)
        assert_almost_equal(res, tgt)

    def test_small_large(self):
        # test the small and large code paths, current cutoff 400 elements
        for s in [5, 20, 51, 200, 1000]:
            d = np.random.randn(4, s)
            # Randomly set some elements to NaN:
            w = np.random.randint(0, d.size, size=d.size // 5)
            d.ravel()[w] = np.nan
            d[:,0] = 1.  # ensure at least one good value
            # use normal median without nans to compare
            tgt = []
            for x in d:
                nonan = np.compress(~np.isnan(x), x)
                tgt.append(np.median(nonan, overwrite_input=True))

            assert_array_equal(np.nanmedian(d, axis=-1), tgt)

    def test_result_values(self):
            tgt = [np.median(d) for d in _rdat]
            res = np.nanmedian(_ndat, axis=1)
            assert_almost_equal(res, tgt)

    def test_allnans(self):
        mat = np.array([np.nan]*9).reshape(3, 3)
        for axis in [None, 0, 1]:
            with suppress_warnings() as sup:
                sup.record(RuntimeWarning)

                assert_(np.isnan(np.nanmedian(mat, axis=axis)).all())
                if axis is None:
                    assert_(len(sup.log) == 1)
                else:
                    assert_(len(sup.log) == 3)
                # Check scalar
                assert_(np.isnan(np.nanmedian(np.nan)))
                if axis is None:
                    assert_(len(sup.log) == 2)
                else:
                    assert_(len(sup.log) == 4)

    def test_empty(self):
        mat = np.zeros((0, 3))
        for axis in [0, None]:
            with warnings.catch_warnings(record=True) as w:
                warnings.simplefilter('always')
                assert_(np.isnan(np.nanmedian(mat, axis=axis)).all())
                assert_(len(w) == 1)
                assert_(issubclass(w[0].category, RuntimeWarning))
        for axis in [1]:
            with warnings.catch_warnings(record=True) as w:
                warnings.simplefilter('always')
                assert_equal(np.nanmedian(mat, axis=axis), np.zeros([]))
                assert_(len(w) == 0)

    def test_scalar(self):
        assert_(np.nanmedian(0.) == 0.)

    def test_extended_axis_invalid(self):
        d = np.ones((3, 5, 7, 11))
        assert_raises(np.AxisError, np.nanmedian, d, axis=-5)
        assert_raises(np.AxisError, np.nanmedian, d, axis=(0, -5))
        assert_raises(np.AxisError, np.nanmedian, d, axis=4)
        assert_raises(np.AxisError, np.nanmedian, d, axis=(0, 4))
        assert_raises(ValueError, np.nanmedian, d, axis=(1, 1))

    def test_float_special(self):
        with suppress_warnings() as sup:
            sup.filter(RuntimeWarning)
            for inf in [np.inf, -np.inf]:
                a = np.array([[inf,  np.nan], [np.nan, np.nan]])
                assert_equal(np.nanmedian(a, axis=0), [inf,  np.nan])
                assert_equal(np.nanmedian(a, axis=1), [inf,  np.nan])
                assert_equal(np.nanmedian(a), inf)

                # minimum fill value check
                a = np.array([[np.nan, np.nan, inf],
                             [np.nan, np.nan, inf]])
                assert_equal(np.nanmedian(a), inf)
                assert_equal(np.nanmedian(a, axis=0), [np.nan, np.nan, inf])
                assert_equal(np.nanmedian(a, axis=1), inf)

                # no mask path
                a = np.array([[inf, inf], [inf, inf]])
                assert_equal(np.nanmedian(a, axis=1), inf)

                a = np.array([[inf, 7, -inf, -9],
                              [-10, np.nan, np.nan, 5],
                              [4, np.nan, np.nan, inf]],
                              dtype=np.float32)
                if inf > 0:
                    assert_equal(np.nanmedian(a, axis=0), [4., 7., -inf, 5.])
                    assert_equal(np.nanmedian(a), 4.5)
                else:
                    assert_equal(np.nanmedian(a, axis=0), [-10., 7., -inf, -9.])
                    assert_equal(np.nanmedian(a), -2.5)
                assert_equal(np.nanmedian(a, axis=-1), [-1., -2.5, inf])

                for i in range(0, 10):
                    for j in range(1, 10):
                        a = np.array([([np.nan] * i) + ([inf] * j)] * 2)
                        assert_equal(np.nanmedian(a), inf)
                        assert_equal(np.nanmedian(a, axis=1), inf)
                        assert_equal(np.nanmedian(a, axis=0),
                                     ([np.nan] * i) + [inf] * j)

                        a = np.array([([np.nan] * i) + ([-inf] * j)] * 2)
                        assert_equal(np.nanmedian(a), -inf)
                        assert_equal(np.nanmedian(a, axis=1), -inf)
                        assert_equal(np.nanmedian(a, axis=0),
                                     ([np.nan] * i) + [-inf] * j)


class TestNanFunctions_Percentile(object):

    def test_mutation(self):
        # Check that passed array is not modified.
        ndat = _ndat.copy()
        np.nanpercentile(ndat, 30)
        assert_equal(ndat, _ndat)

    def test_keepdims(self):
        mat = np.eye(3)
        for axis in [None, 0, 1]:
            tgt = np.percentile(mat, 70, axis=axis, out=None,
                                overwrite_input=False)
            res = np.nanpercentile(mat, 70, axis=axis, out=None,
                                   overwrite_input=False)
            assert_(res.ndim == tgt.ndim)

        d = np.ones((3, 5, 7, 11))
        # Randomly set some elements to NaN:
        w = np.random.random((4, 200)) * np.array(d.shape)[:, None]
        w = w.astype(np.intp)
        d[tuple(w)] = np.nan
        with suppress_warnings() as sup:
            sup.filter(RuntimeWarning)
            res = np.nanpercentile(d, 90, axis=None, keepdims=True)
            assert_equal(res.shape, (1, 1, 1, 1))
            res = np.nanpercentile(d, 90, axis=(0, 1), keepdims=True)
            assert_equal(res.shape, (1, 1, 7, 11))
            res = np.nanpercentile(d, 90, axis=(0, 3), keepdims=True)
            assert_equal(res.shape, (1, 5, 7, 1))
            res = np.nanpercentile(d, 90, axis=(1,), keepdims=True)
            assert_equal(res.shape, (3, 1, 7, 11))
            res = np.nanpercentile(d, 90, axis=(0, 1, 2, 3), keepdims=True)
            assert_equal(res.shape, (1, 1, 1, 1))
            res = np.nanpercentile(d, 90, axis=(0, 1, 3), keepdims=True)
            assert_equal(res.shape, (1, 1, 7, 1))

    def test_out(self):
        mat = np.random.rand(3, 3)
        nan_mat = np.insert(mat, [0, 2], np.nan, axis=1)
        resout = np.zeros(3)
        tgt = np.percentile(mat, 42, axis=1)
        res = np.nanpercentile(nan_mat, 42, axis=1, out=resout)
        assert_almost_equal(res, resout)
        assert_almost_equal(res, tgt)
        # 0-d output:
        resout = np.zeros(())
        tgt = np.percentile(mat, 42, axis=None)
        res = np.nanpercentile(nan_mat, 42, axis=None, out=resout)
        assert_almost_equal(res, resout)
        assert_almost_equal(res, tgt)
        res = np.nanpercentile(nan_mat, 42, axis=(0, 1), out=resout)
        assert_almost_equal(res, resout)
        assert_almost_equal(res, tgt)

    def test_result_values(self):
        tgt = [np.percentile(d, 28) for d in _rdat]
        res = np.nanpercentile(_ndat, 28, axis=1)
        assert_almost_equal(res, tgt)
        # Transpose the array to fit the output convention of numpy.percentile
        tgt = np.transpose([np.percentile(d, (28, 98)) for d in _rdat])
        res = np.nanpercentile(_ndat, (28, 98), axis=1)
        assert_almost_equal(res, tgt)

    def test_allnans(self):
        mat = np.array([np.nan]*9).reshape(3, 3)
        for axis in [None, 0, 1]:
            with warnings.catch_warnings(record=True) as w:
                warnings.simplefilter('always')
                assert_(np.isnan(np.nanpercentile(mat, 60, axis=axis)).all())
                if axis is None:
                    assert_(len(w) == 1)
                else:
                    assert_(len(w) == 3)
                assert_(issubclass(w[0].category, RuntimeWarning))
                # Check scalar
                assert_(np.isnan(np.nanpercentile(np.nan, 60)))
                if axis is None:
                    assert_(len(w) == 2)
                else:
                    assert_(len(w) == 4)
                assert_(issubclass(w[0].category, RuntimeWarning))

    def test_empty(self):
        mat = np.zeros((0, 3))
        for axis in [0, None]:
            with warnings.catch_warnings(record=True) as w:
                warnings.simplefilter('always')
                assert_(np.isnan(np.nanpercentile(mat, 40, axis=axis)).all())
                assert_(len(w) == 1)
                assert_(issubclass(w[0].category, RuntimeWarning))
        for axis in [1]:
            with warnings.catch_warnings(record=True) as w:
                warnings.simplefilter('always')
                assert_equal(np.nanpercentile(mat, 40, axis=axis), np.zeros([]))
                assert_(len(w) == 0)

    def test_scalar(self):
        assert_equal(np.nanpercentile(0., 100), 0.)
        a = np.arange(6)
        r = np.nanpercentile(a, 50, axis=0)
        assert_equal(r, 2.5)
        assert_(np.isscalar(r))

    def test_extended_axis_invalid(self):
        d = np.ones((3, 5, 7, 11))
        assert_raises(np.AxisError, np.nanpercentile, d, q=5, axis=-5)
        assert_raises(np.AxisError, np.nanpercentile, d, q=5, axis=(0, -5))
        assert_raises(np.AxisError, np.nanpercentile, d, q=5, axis=4)
        assert_raises(np.AxisError, np.nanpercentile, d, q=5, axis=(0, 4))
        assert_raises(ValueError, np.nanpercentile, d, q=5, axis=(1, 1))

    def test_multiple_percentiles(self):
        perc = [50, 100]
        mat = np.ones((4, 3))
        nan_mat = np.nan * mat
        # For checking consistency in higher dimensional case
        large_mat = np.ones((3, 4, 5))
        large_mat[:, 0:2:4, :] = 0
        large_mat[:, :, 3:] *= 2
        for axis in [None, 0, 1]:
            for keepdim in [False, True]:
                with suppress_warnings() as sup:
                    sup.filter(RuntimeWarning, "All-NaN slice encountered")
                    val = np.percentile(mat, perc, axis=axis, keepdims=keepdim)
                    nan_val = np.nanpercentile(nan_mat, perc, axis=axis,
                                               keepdims=keepdim)
                    assert_equal(nan_val.shape, val.shape)

                    val = np.percentile(large_mat, perc, axis=axis,
                                        keepdims=keepdim)
                    nan_val = np.nanpercentile(large_mat, perc, axis=axis,
                                               keepdims=keepdim)
                    assert_equal(nan_val, val)

        megamat = np.ones((3, 4, 5, 6))
        assert_equal(np.nanpercentile(megamat, perc, axis=(1, 2)).shape, (2, 3, 6))


class TestNanFunctions_Quantile(object):
    # most of this is already tested by TestPercentile

    def test_regression(self):
        ar = np.arange(24).reshape(2, 3, 4).astype(float)
        ar[0][1] = np.nan

        assert_equal(np.nanquantile(ar, q=0.5), np.nanpercentile(ar, q=50))
        assert_equal(np.nanquantile(ar, q=0.5, axis=0),
                     np.nanpercentile(ar, q=50, axis=0))
        assert_equal(np.nanquantile(ar, q=0.5, axis=1),
                     np.nanpercentile(ar, q=50, axis=1))
        assert_equal(np.nanquantile(ar, q=[0.5], axis=1),
                     np.nanpercentile(ar, q=[50], axis=1))
        assert_equal(np.nanquantile(ar, q=[0.25, 0.5, 0.75], axis=1),
                     np.nanpercentile(ar, q=[25, 50, 75], axis=1))

    def test_basic(self):
        x = np.arange(8) * 0.5
        assert_equal(np.nanquantile(x, 0), 0.)
        assert_equal(np.nanquantile(x, 1), 3.5)
        assert_equal(np.nanquantile(x, 0.5), 1.75)

    def test_no_p_overwrite(self):
        # this is worth retesting, because quantile does not make a copy
        p0 = np.array([0, 0.75, 0.25, 0.5, 1.0])
        p = p0.copy()
        np.nanquantile(np.arange(100.), p, interpolation="midpoint")
        assert_array_equal(p, p0)

        p0 = p0.tolist()
        p = p.tolist()
        np.nanquantile(np.arange(100.), p, interpolation="midpoint")
        assert_array_equal(p, p0)
Metadata
View Raw File