def mannwhitney_u(x, y):
"""
Return the Mann-Whitney U statistic on the provided scores. Copied from
scipy.stats.mannwhitneyu except that we only return the U such that
large U means that population x was systematically larger than population
y, rather than the smaller U between x and y. The two possible U values
one can report are related by U' = n1*n2 - U.
"""
x = np.asarray(x)
y = np.asarray(y)
if x.ndim != 1 or y.ndim != 1:
raise ValueError, "populations must be rank 1 collections"
n1 = len(x)
n2 = len(y)
ranked = rankdata(np.concatenate((x,y)))
rankx = ranked[0:n1] # get the x-ranks
u1 = n1 * n2 + (n1 * (n1 + 1)) / 2.0 - rankx.sum() # calc U for x
return n1 * n2 - u1 # return U for y
def mannwhitney_u(x, y):
"""
Return the Mann-Whitney U statistic on the provided scores. Copied from
scipy.stats.mannwhitneyu except that we only return the U such that
large U means that population x was systematically larger than population
y, rather than the smaller U between x and y. The two possible U values
one can report are related by U' = n1*n2 - U.
"""
x = np.asarray(x)
y = np.asarray(y)
if x.ndim != 1 or y.ndim != 1:
raise ValueError, "populations must be rank 1 collections"
n1 = len(x)
n2 = len(y)
ranked = rankdata(np.concatenate((x,y)))
rankx = ranked[0:n1] # get the x-ranks
u1 = n1 * n2 + (n1 * (n1 + 1)) / 2.0 - rankx.sum() # calc U for x
return n1 * n2 - u1 # return U for y
def test_identical_discrete(self):
for _ in xrange(1000):
data = np.random.randint(0, 1000, size=1000).astype(float)
self.assertTrue((rankdata(data) == scipy_rankdata(data)).all())
def test_identical_continuous(self):
for _ in xrange(1000):
data = np.random.uniform(0, 1000, size=1000)
self.assertTrue((rankdata(data) == scipy_rankdata(data)).all())
def test_identical_discrete(self):
for _ in xrange(1000):
data = np.random.randint(0, 1000, size=1000).astype(float)
self.assertTrue((rankdata(data) == scipy_rankdata(data)).all())
def test_identical_continuous(self):
for _ in xrange(1000):
data = np.random.uniform(0, 1000, size=1000)
self.assertTrue((rankdata(data) == scipy_rankdata(data)).all())
