def setUp(self):
self.model = SGD(n=2**10, a=0.1, l1=1, l2=1, interaction=True)
self.sparse_file = '/tmp/dummy.sps'
"""Create dummpy sparse files."""
with open(self.sparse_file, 'w') as f:
f.write(DUMMY_SPARSE_STR)
class TestSGD(unittest.TestCase):
def setUp(self):
self.model = SGD(n=2**10, a=0.1, l1=1, l2=1, interaction=True)
self.sparse_file = '/tmp/dummy.sps'
"""Create dummpy sparse files."""
with open(self.sparse_file, 'w') as f:
f.write(DUMMY_SPARSE_STR)
def tearDown(self):
# If a dummy file exists, remove it.
if os.path.isfile(self.sparse_file):
os.remove(self.sparse_file)
def test_read_sparse(self):
len_xs = []
ys = []
for x, y in self.model.read_sparse(self.sparse_file):
# check hash collision for feature index
self.assertEqual(len(set(x)), len(x))
ys.append(y)
len_xs.append(len(x))
# check if target values are correct
self.assertEqual(ys, DUMMY_Y)
# check if the number of feature index are correct
self.assertEqual(len_xs, DUMMY_LEN_X)
def setUp(self):
self.model = SGD(n=2**10, a=0.1, l1=1, l2=1, interaction=True)
self.sparse_file = '/tmp/dummy.sps'
"""Create dummpy sparse files."""
with open(self.sparse_file, 'w') as f:
f.write(DUMMY_SPARSE_STR)
class TestSGD(unittest.TestCase):
def setUp(self):
self.model = SGD(n=2**10, a=0.1, l1=1, l2=1, interaction=True)
self.sparse_file = '/tmp/dummy.sps'
"""Create dummpy sparse files."""
with open(self.sparse_file, 'w') as f:
f.write(DUMMY_SPARSE_STR)
def tearDown(self):
# If a dummy file exists, remove it.
if os.path.isfile(self.sparse_file):
os.remove(self.sparse_file)
def test_read_sparse(self):
len_xs = []
ys = []
for x, y in self.model.read_sparse(self.sparse_file):
# check hash collision for feature index
self.assertEqual(len(set(x)), len(x))
ys.append(y)
len_xs.append(len(x))
# check if target values are correct
self.assertEqual(ys, DUMMY_Y)
# check if the number of feature index are correct
self.assertEqual(len_xs, DUMMY_LEN_X)
X = train[train_indices]
y = label[train_indices]
X_test = train[test_indices]
X = sparse.csr_matrix(X)
X_test = sparse.csr_matrix(X_test)
#clf = RandomForestClassifier(n_estimators=500,n_jobs=-1,verbose = 1)
#clf = KNeighborsClassifier(n_neighbors=15, weights='distance', algorithm='auto', leaf_size=30, p=1, metric='minkowski', metric_params=None)
#clf = GaussianNB()
#clf = OneVsRestClassifier(SVC(kernel='linear'),n_jobs = 2)
#clf = MultinomialNB()
#clf = AdaBoostClassifier(DecisionTreeClassifier(max_depth=30),n_estimators=600,learning_rate=1.5,algorithm="SAMME.R")
#clf = VBGMM(n_components=8, covariance_type='diag', alpha=1.0, random_state=None, thresh=None, tol=0.001, verbose=1, min_covar=None, n_iter=500, params='wmc', init_params='wmc')
print 'clf fit'
clf = SGD(a=.01, # learning rate
l1=1e-6, # L1 regularization parameter
l2=1e-6, # L2 regularization parameter
n=983, # number of hashed features
epoch=10, # number of epochs
interaction=True) # use feature interaction or not
clf.fit(X,y)
print 'Classifier Trained'
#Convert the predicted array
'''
Y_prob = clf.predict_proba(X_test)
Y_pred = []
for i in range(len(Y_prob)):
Y_pred.append([])
for j in range(len(Y_prob[i])):
if len(Y_prob[i][j]) == 2:
Y_pred[i].append(Y_prob[i][j][1]) #positive class prob
else:
y = label[train_indices]
X_test = train[test_indices]
X = sparse.csr_matrix(X)
X_test = sparse.csr_matrix(X_test)
#clf = RandomForestClassifier(n_estimators=500,n_jobs=-1,verbose = 1)
#clf = KNeighborsClassifier(n_neighbors=15, weights='distance', algorithm='auto', leaf_size=30, p=1, metric='minkowski', metric_params=None)
#clf = GaussianNB()
#clf = OneVsRestClassifier(SVC(kernel='linear'),n_jobs = 2)
#clf = MultinomialNB()
#clf = AdaBoostClassifier(DecisionTreeClassifier(max_depth=30),n_estimators=600,learning_rate=1.5,algorithm="SAMME.R")
#clf = VBGMM(n_components=8, covariance_type='diag', alpha=1.0, random_state=None, thresh=None, tol=0.001, verbose=1, min_covar=None, n_iter=500, params='wmc', init_params='wmc')
print 'clf fit'
clf = SGD(
a=.01, # learning rate
l1=1e-6, # L1 regularization parameter
l2=1e-6, # L2 regularization parameter
n=983, # number of hashed features
epoch=10, # number of epochs
interaction=True) # use feature interaction or not
clf.fit(X, y)
print 'Classifier Trained'
#Convert the predicted array
'''
Y_prob = clf.predict_proba(X_test)
Y_pred = []
for i in range(len(Y_prob)):
Y_pred.append([])
for j in range(len(Y_prob[i])):
if len(Y_prob[i][j]) == 2:
Y_pred[i].append(Y_prob[i][j][1]) #positive class prob
