def _test_svm_based(self):
dataset = snippet_reader.toNumpy()
n_feature = 1000
print "Dataset: Snippet, Classifier: Linear SVM"
print
#self.run_ratio(LinearSVC, dataset, n_feature)
self.run_size(LinearSVC, dataset, n_feature)
def load_dataset2(self):
X, y, X_test, y_test = dataset = snippet_reader.toNumpy()
X, y = shuffle(X, y)
lb = LabelBinarizer()
lb.fit(y)
for y_bin in lb.transform(y).T:
return X, y_bin
def _test_debug(self):
X_train_full, y_train_full, X_test, y_test = snippet_reader.toNumpy()
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)
X_test_new, y_test_new = SetGen.with_pos_ratio(test_set_original, 0.5, pos_label=1)
test_set = [X_test_new, y_test_new]
en = EN(LogisticRegression, debug=True)
self.run_for_estimator(en, train_set, test_set, debug=True)
def _test_svm_based(self):
print "Compare Snippet with SVM"
dataset = snippet_reader.toNumpy()
from collections import Counter
X_train, y_train, X_test, y_test = dataset
print "training shape", X_train.shape
print "test shape", X_test.shape
print "training class dist", Counter(y_train)
print "test class dist", Counter(y_test)
#n_feature = 1000
#self.run_test_with(dataset, self.compare_svm_based, n_feature)
acc_matrix, f1_matrix, auc_matrix = self.compare_svm_based(dataset)
def load_dataset(self):
X, y, X_test, y_test = dataset = snippet_reader.toNumpy()
lb = LabelBinarizer()
lb.fit(y)
for y_bin in lb.transform(y).T:
y = y_bin
break
for y_bin in lb.transform(y_test).T:
y_test = y_bin
break
return X, y, X_test, y_test
def _test_change_training_size(self):
'''
Do compare using ncRNA dataset.
The dataset is from
Andrew V Uzilov, Joshua M Keegan, and David H Mathews.
Detection of non-coding RNAs on the basis of predicted secondary
structure formation free energy change.
BMC Bioinformatics, 7(173), 2006.
'''
X_train_full, y_train_full, X_test, y_test = snippet_reader.toNumpy()
test_set_original = [X_test, y_test]
pos_ratio = 0.7 # arbtrary ratio
X_test_new, y_test_new = SetGen.with_pos_ratio(test_set_original, pos_ratio, pos_label=1)
test_set = [X_test_new, y_test_new]
cc = CC(LogisticRegression)
ac = AC(LogisticRegression)
ms = MS(LogisticRegression)
it = Itr(LogisticRegression)
en = EN(LogisticRegression)
ests = [cc, ac, ms, it, en]
print "We compare performance as chaning the training set size."
print "Fixed positive ratio is %f" % pos_ratio
print "size\tcc\tac\tms\tit\ten"
for set_size in [100, 200, 300, 400, 500, 600, 700, 800, 900, 1000, 2000, 3000]:
X_train_sub, y_train_sub = self.get_sub_set_with_size(
[X_train_full, y_train_full], set_size)
train_set = [X_train_sub, y_train_sub]
en.find_hyperparameter(train_set)
errs = map(lambda e: self.run_for_estimator(e, train_set, test_set), ests)
print ("%d" + "\t%.4f" * 5) % (set_size,
errs[0], errs[1], errs[2], errs[3], errs[4])
def test_ratio(self):
dataset = snippet_reader.toNumpy()
for set_size in numpy.arange(100, 1100, 100):
self.run_ratio(dataset, set_size)
print
def _test_svm_based(self):
dataset = snippet_reader.toNumpy()
n_feature = 1000
print "Snippet with SVM"
self.run_test_with(dataset, LinearSVC, n_feature)