def test_nanvar_nans(self):
samples = np.nan * np.ones(2 * self.samples.shape[0])
samples[::2] = self.samples
actual_variance = nanops.nanvar(samples, skipna=True)
tm.assert_almost_equal(actual_variance, self.variance, check_less_precise=2)
actual_variance = nanops.nanvar(samples, skipna=False)
tm.assert_almost_equal(actual_variance, np.nan, check_less_precise=2)
def test_nanvar_nans(self):
samples = np.nan * np.ones(2 * self.samples.shape[0])
samples[::2] = self.samples
actual_variance = nanops.nanvar(samples, skipna=True)
np.testing.assert_almost_equal(actual_variance, self.variance, decimal=2)
actual_variance = nanops.nanvar(samples, skipna=False)
np.testing.assert_almost_equal(actual_variance, np.nan, decimal=2)
def var(self, axis=None, dtype=None, out=None, ddof=1, keepdims=False,
skipna=True):
nv.validate_stat_ddof_func((), dict(dtype=dtype, out=out,
keepdims=keepdims),
fname='var')
return nanops.nanvar(self._ndarray, axis=axis, skipna=skipna,
ddof=ddof)
def test_ground_truth(self):
# Test against values that were precomputed with Numpy.
samples = np.empty((4, 4))
samples[:3, :3] = np.array([[0.97303362, 0.21869576, 0.55560287
], [0.72980153, 0.03109364, 0.99155171],
[0.09317602, 0.60078248, 0.15871292]])
samples[3] = samples[:, 3] = np.nan
# Actual variances along axis=0, 1 for ddof=0, 1, 2
variance = np.array([[[0.13762259, 0.05619224, 0.11568816
], [0.20643388, 0.08428837, 0.17353224],
[0.41286776, 0.16857673, 0.34706449]],
[[0.09519783, 0.16435395, 0.05082054
], [0.14279674, 0.24653093, 0.07623082],
[0.28559348, 0.49306186, 0.15246163]]])
# Test nanvar.
for axis in range(2):
for ddof in range(3):
var = nanops.nanvar(samples, skipna=True, axis=axis, ddof=ddof)
tm.assert_almost_equal(var[:3], variance[axis, ddof])
self.assertTrue(np.isnan(var[3]))
# Test nanstd.
for axis in range(2):
for ddof in range(3):
std = nanops.nanstd(samples, skipna=True, axis=axis, ddof=ddof)
tm.assert_almost_equal(std[:3], variance[axis, ddof] ** 0.5)
self.assertTrue(np.isnan(std[3]))
def test_nanvar_ddof(self):
n = 5
samples = self.prng.uniform(size=(10000, n + 1))
samples[:, -1] = np.nan # Force use of our own algorithm.
variance_0 = nanops.nanvar(samples, axis=1, skipna=True, ddof=0).mean()
variance_1 = nanops.nanvar(samples, axis=1, skipna=True, ddof=1).mean()
variance_2 = nanops.nanvar(samples, axis=1, skipna=True, ddof=2).mean()
# The unbiased estimate.
var = 1.0 / 12
np.testing.assert_almost_equal(variance_1, var, decimal=2)
# The underestimated variance.
np.testing.assert_almost_equal(variance_0, (n - 1.0) / n * var, decimal=2)
# The overestimated variance.
np.testing.assert_almost_equal(variance_2, (n - 1.0) / (n - 2.0) * var, decimal=2)
def test_nanvar_axis(self):
# Generate some sample data.
samples_norm = self.samples
samples_unif = self.prng.uniform(size=samples_norm.shape[0])
samples = np.vstack([samples_norm, samples_unif])
actual_variance = nanops.nanvar(samples, axis=1)
tm.assert_almost_equal(actual_variance, np.array([self.variance, 1.0 / 12]), check_less_precise=2)
def test_nanvar_ddof(self):
n = 5
samples = self.prng.uniform(size=(10000, n + 1))
samples[:, -1] = np.nan # Force use of our own algorithm.
variance_0 = nanops.nanvar(samples, axis=1, skipna=True, ddof=0).mean()
variance_1 = nanops.nanvar(samples, axis=1, skipna=True, ddof=1).mean()
variance_2 = nanops.nanvar(samples, axis=1, skipna=True, ddof=2).mean()
# The unbiased estimate.
var = 1.0 / 12
tm.assert_almost_equal(variance_1, var, rtol=1e-2)
# The underestimated variance.
tm.assert_almost_equal(variance_0, (n - 1.0) / n * var, rtol=1e-2)
# The overestimated variance.
tm.assert_almost_equal(variance_2, (n - 1.0) / (n - 2.0) * var, rtol=1e-2)
def test_nanstd_nans(self):
samples = np.nan * np.ones(2 * self.samples.shape[0])
samples[::2] = self.samples
actual_std = nanops.nanstd(samples, skipna=True)
tm.assert_almost_equal(actual_std, self.variance ** 0.5, rtol=1e-2)
actual_std = nanops.nanvar(samples, skipna=False)
tm.assert_almost_equal(actual_std, np.nan, rtol=1e-2)
def test_nanvar_axis(self):
# Generate some sample data.
samples_norm = self.samples
samples_unif = self.prng.uniform(size=samples_norm.shape[0])
samples = np.vstack([samples_norm, samples_unif])
actual_variance = nanops.nanvar(samples, axis=1)
tm.assert_almost_equal(actual_variance, np.array(
[self.variance, 1.0 / 12]), check_less_precise=2)
def var(
self,
*,
axis=None,
dtype: Optional[NpDtype] = None,
out=None,
ddof=1,
keepdims=False,
skipna=True,
):
nv.validate_stat_ddof_func(
(), {"dtype": dtype, "out": out, "keepdims": keepdims}, fname="var"
)
result = nanops.nanvar(self._ndarray, axis=axis, skipna=skipna, ddof=ddof)
return self._wrap_reduction_result(axis, result)
def var(self,
axis=None,
dtype=None,
out=None,
ddof=1,
keepdims=False,
skipna=True):
nv.validate_stat_ddof_func((),
dict(dtype=dtype,
out=out,
keepdims=keepdims),
fname="var")
return nanops.nanvar(self._ndarray,
axis=axis,
skipna=skipna,
ddof=ddof)
def test_ground_truth(self):
# Test against values that were precomputed with Numpy.
samples = np.empty((4, 4))
samples[:3, :3] = np.array(
[
[0.97303362, 0.21869576, 0.55560287],
[0.72980153, 0.03109364, 0.99155171],
[0.09317602, 0.60078248, 0.15871292],
]
)
samples[3] = samples[:, 3] = np.nan
# Actual variances along axis=0, 1 for ddof=0, 1, 2
variance = np.array(
[
[
[0.13762259, 0.05619224, 0.11568816],
[0.20643388, 0.08428837, 0.17353224],
[0.41286776, 0.16857673, 0.34706449],
],
[
[0.09519783, 0.16435395, 0.05082054],
[0.14279674, 0.24653093, 0.07623082],
[0.28559348, 0.49306186, 0.15246163],
],
]
)
# Test nanvar.
for axis in range(2):
for ddof in range(3):
var = nanops.nanvar(samples, skipna=True, axis=axis, ddof=ddof)
tm.assert_almost_equal(var[:3], variance[axis, ddof])
assert np.isnan(var[3])
# Test nanstd.
for axis in range(2):
for ddof in range(3):
std = nanops.nanstd(samples, skipna=True, axis=axis, ddof=ddof)
tm.assert_almost_equal(std[:3], variance[axis, ddof] ** 0.5)
assert np.isnan(std[3])
def test_nanvar_all_finite(self):
samples = self.samples
actual_variance = nanops.nanvar(samples)
np.testing.assert_almost_equal(actual_variance,
self.variance,
decimal=2)
def test_nanvar_all_finite(self):
samples = self.samples
actual_variance = nanops.nanvar(samples)
tm.assert_almost_equal(actual_variance, self.variance,
check_less_precise=2)
def test_nanvar_all_finite(self):
samples = self.samples
actual_variance = nanops.nanvar(samples)
tm.assert_almost_equal(actual_variance, self.variance, rtol=1e-2)
def test_nanvar_all_finite(self):
samples = self.samples
actual_variance = nanops.nanvar(samples)
tm.assert_almost_equal(actual_variance,
self.variance,
check_less_precise=2)
def test_nanvar_all_finite(self):
samples = self.samples
actual_variance = nanops.nanvar(samples)
np.testing.assert_almost_equal(
actual_variance, self.variance, decimal=2)