def _test_size(self):
'''
Compare several competing methods changing the ratio of the positive
class in the dataset. We use binary class dataset for the easy of
interpretation.
'''
for set_size in numpy.arange(100, 1000, 100):
X_train_full, y_train_full, X_test, y_test = nc_rna_reader.toNumpy()
X_train, y_train= self.get_sub_set_with_size([X_train_full, y_train_full], set_size)
assert(len(y_train) == set_size)
train_set = (X_train, y_train)
test_set_original = (X_test, y_test)
ms = MS2(LogisticRegression)
ms.fit(train_set)
r = 0.05
X_test_new, y_test_new = SetGen.with_pos_ratio(test_set_original, r, pos_label=1)
test_set = [X_test_new, y_test_new]
dist_true = DE.arrayToDist(y_test_new)
dist_est = ms.predict(X_test_new)
err = rms(dist_est, dist_true)
print dist_est
print "size: %d, err: %f" % (set_size, err)
def run_for_estimator(self, estimator, test_set):
X_test, y_test = test_set
dist = estimator.predict(X_test)
assert len(dist) == 2
err = DE.rms(y_test, dist)
return err
def _test_ac_forest(self):
X_train_full, y_train_full, X_test, y_test = rcv1_binary_reader.toNumpy()
set_size = 200 # an arbitrary number
X_train, y_train= self.get_sub_set_with_size([X_train_full, y_train_full], set_size)
assert(len(y_train) == set_size)
train_set = (X_train, y_train)
test_set_original = (X_test, y_test)
r = 0.8
X_test_new, y_test_new = SetGen.with_pos_ratio(test_set_original, r, pos_label=1)
test_set = [X_test_new, y_test_new]
dist_true = DE.arrayToDist(y_test_new)
pos = []
for i in range(500):
train_sub = self.get_sub_set_with_size(train_set, 0.5)
ac = AC2(LogisticRegression)
ac.fit(train_sub)
dist_est = ac.predict(X_test_new)
pos.append(dist_est[1])
print pos
print numpy.mean(pos)
print numpy.median(pos)
def test_class_ratio(self):
'''
Compare several competing methods changing the ratio of the positive
class in the dataset. We use binary class dataset for the easy of
interpretation.
'''
#X_train_full, y_train_full, X_test, y_test = nc_rna_reader.toNumpy()
X_train_full, y_train_full, X_test, y_test = news_20_reader.toNumpy()
set_size = 1000
X_train, y_train = self.get_sub_set_with_size([X_train_full, y_train_full], set_size)
train_set = (X_train, y_train)
test_set_original = (X_test, y_test)
ms = MSHI(LinearSVC)
ms.fit(train_set)
print 'Done training'
for r in numpy.arange(0.05, 1.0, 0.05):
#for r in [0.05]:
X_test_new, y_test_new = SetGen.with_pos_ratio(test_set_original, r, pos_label=1)
test_set = [X_test_new, y_test_new]
dist_true = DE.arrayToDist(y_test_new)
dist_est = ms.predict(X_test_new)
err = rms(dist_est, dist_true)
print "r: %f, pos: %f" % (r, dist_est[1])
def test_ratio(self):
#X_train_full, y_train_full, X_test, y_test = nc_rna_reader.toNumpy()
#X_train_full, y_train_full, X_test, y_test = rcv1_binary_reader.toNumpy()
X_train_full, y_train_full, X_test, y_test = synthetic_reader.toNumpy(0.3, n_class=2)
set_size = 500 # an arbitrary number
X_train, y_train= self.get_sub_set_with_size([X_train_full, y_train_full], set_size)
assert(len(y_train) == set_size)
train_set = (X_train, y_train)
test_set_original = (X_test, y_test)
cc = CC2(KNeighborsClassifier)
cc.fit(train_set)
for r in numpy.arange(0.05, 1.0, 0.05):
X_test_new, y_test_new = SetGen.with_pos_ratio(test_set_original, r, pos_label=1)
test_set = [X_test_new, y_test_new]
dist_true = DE.arrayToDist(y_test_new)
dist_est = cc.predict(X_test_new)
err = rms(dist_est, dist_true)
#print dist_est
print "%f\t%f" % (dist_true[1], dist_est[1])
def adjust_count(y_pred, cm):
ncm = cm / cm.sum(1, dtype=numpy.float64)[:, numpy.newaxis]
tpr = ncm[1,1]
fpr = ncm[0,1]
pp = DE.to_bin_dist(y_pred)[1]
if tpr - fpr < .25:
raise TooLittleDifferenceException
new_pos = (pp - fpr) / float(tpr - fpr)
dist_est = numpy.array([1-new_pos, new_pos])
dist_est[dist_est<0] = 0
dist_est[dist_est>1] = 1
return dist_est / dist_est.sum()
def adjust_count(self, y_pred, cm):
ncm = cm / cm.sum(1, dtype=numpy.float64)[:, numpy.newaxis]
tpr = ncm[1,1]
fpr = ncm[0,1]
pp = DE.to_bin_dist(y_pred)[1]
if tpr == fpr:
new_pos = .5
else:
new_pos = (pp - fpr) / float(tpr - fpr)
dist_est = numpy.array([1-new_pos, new_pos])
if self.cap:
dist_est[dist_est<0] = 0
dist_est[dist_est>1] = 1
return dist_est / dist_est.sum()
def predict_binary(self, X_population, params):
clf, pos2neg, X, y = params
cost_fp = 1.0
cost_fn = 1.0
for i in range(self.itr_count):
new_label = clf.predict(X_population)
cn = Counter(new_label)
# We add a small prior (1) to prevent divide by zero error. This is
# not mentioned in the original paper, but we add this for fair
# comparison.
pos2neg_new = (cn[1] + 1) / float(cn[0] + 1)
cost_fp = pos2neg / pos2neg_new
# High cost means the examples are important, thus we should weigh
# them more.
clf = self.base_clf_class(class_weight = {0: cost_fn, 1:cost_fp})
clf.fit(X, y)
y_pred = clf.predict(X_population)
return DE.to_bin_dist(y_pred)
def predict_binary(self, X_population, params):
''' prediction outcome is length-2 array. '''
clf = params
y_pred = clf.predict(X_population)
return DE.to_bin_dist(y_pred)
