def gen_sample(p, n):
"""Accepts two integers.
Returns a new dataset of x,y gaussians plus
x^2 and y^2 in a 2-tuple of 2 arrays; (p,4) and (n,4)
"""
pos = gaussian(mean_pos, cov_pos, p)
pos = add_x2_y2(pos)
neg = gaussian(mean_neg, cov_neg, n)
neg = add_x2_y2(neg)
return (pos, neg,) + logistic.sample_positive(c, pos, neg)
def gen_sample(c, p, n):
"""Accepts two integers.
Returns a new dataset of x,y gaussians plus
x^2 and y^2 in a 2-tuple of 2 arrays; (p,4) and (n,4)
"""
pos = gaussian(mean_pos, cov_pos, p)
pos = add_x2_y2(pos)
neg = gaussian(mean_neg, cov_neg, n)
neg = add_x2_y2(neg)
return (pos, neg,) + logistic.sample_positive(c, pos, neg)
def gen_sample(p, n):
"""Accepts two integers.
Returns a new dataset of x,y gaussians plus
x^2 and y^2 in a 2-tuple of 2 arrays; (p,4) and (n,4)
"""
def add_x2_y2(a):
"""Accepts an (N,2) array, adds 2 more columns
which are first col squared, second col squared.
"""
return logistic.vstack([a.T, a[:,0]**2, a[:,1]**2]).T
pos = gaussian(mean_pos, cov_pos, p)
pos = add_x2_y2(pos)
neg = gaussian(mean_neg, cov_neg, n)
neg = add_x2_y2(neg)
return logistic.sample_positive(c, pos, neg)
numpy.save(os.path.join(folder, 'data.test_pos.swissprot.npy'),
test_pos.todense())
print 'read data...'
table = []
for cp in [1.0, 0.5, 0.1, 0.7, 0.6, 0.4, 0.3, 0.2, 0.9, 0.8]:
# split out the validation set separately
split = lambda a: logistic.sample_split(a, int(0.8 * a.shape[0]))
half_pos, v_pos = split(pos)
half_neg, v_neg = split(neg)
half_test_pos, v_test_pos = split(test_pos)
# figure out the subset to sample (c)
u = logistic.vstack([half_neg, half_test_pos])
pos_sample, unlabeled = logistic.sample_positive(cp, half_pos, u)
# create validation set the same way
u = logistic.vstack([v_neg, v_test_pos])
v_p, v_u = logistic.sample_positive(cp, v_pos, u)
print 'set up data...'
data = (pos_sample, unlabeled, v_p, v_u)
#data, fixers = normalize_pu_nonnegative_data(*data)
print 'not-normalized...'
#print 'normalized...'
_, estimators = logistic.calculate_estimators(*data, max_iter=100)
t = (
cp,
print "read data..."
# set up data
table = []
for cp in [1.0, 0.5, 0.1, 0.7, 0.6, 0.4, 0.3, 0.2, 0.9, 0.8]:
# split out the validation set separately
split_half = lambda a: logistic.sample_split(a, len(a) / 2)
half_pos, v_pos = split_half(pos)
half_neg, v_neg = split_half(neg)
half_test_pos, v_test_pos = split_half(test_pos)
# figure out the subset to sample (c)
u = logistic.vstack([half_neg, half_test_pos])
pos_sample, unlabeled = logistic.sample_positive(cp, half_pos, u)
# create validation set the same way
u = logistic.vstack([v_neg, v_test_pos])
v_p, v_u = logistic.sample_positive(cp, v_pos, u)
print "set up data..."
_, estimators = logistic.calculate_estimators(pos_sample, unlabeled, v_p, v_u)
t = (
cp,
len(half_pos),
len(half_neg),
len(half_test_pos),
estimators,