def _distSpearmanW_MA(x, y, w):
"""if any of x,y,w is a MA array containing masked values
"""
x = MA.asarray(x)
y = MA.asarray(y)
w = MA.asarray(w)
assert MA.rank(x) == MA.rank(y) == MA.rank(w) == 1
cond = MA.logical_not(
MA.logical_or(MA.logical_or(MA.getmaskarray(x), MA.getmaskarray(y)),
MA.getmaskarray(w)))
# with MA use compress before tolist() !
rankx = Numeric.array(statc.rankdata(MA.compress(cond, x).tolist()))
ranky = Numeric.array(statc.rankdata(MA.compress(cond, y).tolist()))
return distPearsonW(rankx, ranky, MA.compress(cond, w))
def distEuclidean(x, y):
"""normalized euclidean distance
"""
x = MA.asarray(x)
y = MA.asarray(y)
assert MA.rank(x) == MA.rank(y) == 1
sumWeights = MA.add.reduce(
MA.logical_not(MA.logical_or(
MA.getmaskarray(x), MA.getmaskarray(y))).astype(Numeric.Float))
return MA.sqrt(MA.add.reduce((x - y)**2) / sumWeights)
def distManhattan(x, y):
"""normalized Manhattan distance
"""
x = MA.asarray(x)
y = MA.asarray(y)
assert MA.rank(x) == MA.rank(y) == 1
sumWeights = MA.add.reduce(
MA.logical_not(MA.logical_or(
MA.getmaskarray(x), MA.getmaskarray(y))).astype(Numeric.Float))
return MA.add.reduce(MA.absolute(x - y)) / sumWeights
def distSpearman(x, y):
"""distance corresponding to 1 - spearman's correlation coefficient for arrays x,y
returns distance: 1 - spearman_r
"""
x = MA.asarray(x)
y = MA.asarray(y)
assert MA.rank(x) == MA.rank(y) == 1
cond = MA.logical_not(MA.logical_or(MA.getmaskarray(x),
MA.getmaskarray(y)))
return 1 - statc.spearmanr(
MA.compress(cond, x).tolist(),
MA.compress(cond, y).tolist())[0]
def distPearsonW(x, y, w):
"""weighted distance corresponding to 1 - pearson's correlation coefficient for arrays x,y and weights w
returns distance: 1 - pearson_r
"""
#TINY = 1.0e-20
# ones for non-masked places at x,y and w
x = MA.asarray(x)
y = MA.asarray(y)
w = MA.asarray(w)
assert MA.rank(x) == MA.rank(y) == MA.rank(w) == 1
mask = MA.logical_or(MA.logical_or(MA.getmaskarray(x), MA.getmaskarray(y)),
MA.getmaskarray(w))
# set mask to w that is equal to the mask from x, y and w
w = MA.masked_array(w, mask=mask)
n_w_mean = MA.add.reduce(w) # n * mean(w)
x_w = x * w # x * w
y_w = y * w # y * w
x_wmean = MA.divide(MA.add.reduce(x_w), n_w_mean) # weighted_mean(x)
y_wmean = MA.divide(MA.add.reduce(y_w), n_w_mean) # weighted_mean(x)
r_num = MA.add.reduce(x * y * w) - n_w_mean * x_wmean * y_wmean
r_den = MA.sqrt((MA.add.reduce(x_w * x) - n_w_mean * x_wmean**2) *
(MA.add.reduce(y_w * y) - n_w_mean * y_wmean**2))
return 1 - MA.divide(r_num, r_den)