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,
half_pos.shape[0],
half_neg.shape[0],
half_test_pos.shape[0],
estimators,
float(int(half_pos.shape[0] * cp)) /
(half_test_pos.shape[0] + half_pos.shape[0]),
)
table.append(t)
print t
pos_sample = scipy.sparse.csr_matrix(pos_sample)
unlabeled = scipy.sparse.csr_matrix(unlabeled)
testX = np.vstack([pos, neg])
testy = np.hstack([np.array([1] * pos.shape[0]),
np.array([0] * neg.shape[0]),])
scaler = sklearn.preprocessing.Scaler()
scaler.fit(testX)
testX = scaler.transform(testX)
data = (pos_sample, unlabeled, v_p, v_u)
#data, fixers = logistic.normalize_pu_data(*data)
params, estimators = logistic.calculate_estimators(*data, max_iter=1000)
theta, thetaM, b = params
t = ('vf:', vf, 'c:', c, ) + estimators
print t
table.append(t)
# run the LR on the true data
(thetaTrue, _, _), _ = logistic.calculate_estimators(*(pos, neg, v_p, v_u), max_iter=1000)
# unit area ellipse
fig = pyplot.figure()
ax = fig.add_subplot(111)
ax.scatter(pos[:,0], pos[:,1], s=6, c='b', marker='+')
ax.scatter(neg[:,0], neg[:,1], s=6, c='r', marker='o', lw=0)
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,
float(int(len(half_pos) * cp)) / (len(half_test_pos) + len(half_pos)),
)
table.append(t)
print t
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,
half_pos.shape[0], half_neg.shape[0], half_test_pos.shape[0],
estimators,
float(int(half_pos.shape[0] * cp)) / (half_test_pos.shape[0] + half_pos.shape[0]),
)
table.append(t)
print t
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,
float(int(len(half_pos) * cp)) /
(len(half_test_pos) + len(half_pos)),
)
table.append(t)
print t
pos_sample = scipy.sparse.csr_matrix(pos_sample)
unlabeled = scipy.sparse.csr_matrix(unlabeled)
testX = np.vstack([pos, neg])
testy = np.hstack([
np.array([1] * pos.shape[0]),
np.array([0] * neg.shape[0]),
])
scaler = sklearn.preprocessing.Scaler()
scaler.fit(testX)
testX = scaler.transform(testX)
data = (pos_sample, unlabeled, v_p, v_u)
#data, fixers = logistic.normalize_pu_data(*data)
params, estimators = logistic.calculate_estimators(*data,
max_iter=1000)
theta, thetaM, b = params
t = (
'vf:',
vf,
'c:',
c,
) + estimators
print t
table.append(t)
# run the LR on the true data
(thetaTrue, _, _), _ = logistic.calculate_estimators(*(pos, neg, v_p,
v_u),
max_iter=1000)
