def testQueryData(self):
np.random.seed(100)
floattype = np.float64
m, n = 100, 400 #data, features
Xtrain = np.mat(np.random.rand(m, n))
Y = np.mat(np.zeros((m, 1), dtype=floattype))
Y[:, 0] = np.sum(Xtrain, 1)
qidlist = [0 for i in range(100)]
for h in range(5, 12):
qidlist[h] = 1
for h in range(12, 32):
qidlist[h] = 2
for h in range(32, 34):
qidlist[h] = 3
for h in range(34, 85):
qidlist[h] = 4
for h in range(85, 100):
qidlist[h] = 5
kwargs = {}
kwargs['X'] = Xtrain
kwargs['Y'] = Y
kwargs['qids'] = qidlist
kwargs['regparam'] = 1.0
learner1 = QueryRankRLS(**kwargs)
learner2 = CGRankRLS(**kwargs)
mdiff = np.max(1. - learner1.predictor.W / learner2.predictor.W)
if mdiff > 0.01:
assert False
def train_rls():
X_train, Y_train, X_test, Y_test = load_newsgroups()
#CGRLS does not support multi-output learning, so we train
#one classifier for the first column of Y. Multi-class learning
#would be implemented by training one CGRLS for each column, and
#taking the argmax of class predictions.
predictions = []
rls = CGRankRLS(X_train, Y_train[:, 0], regparam=100.0)
P = rls.predict(X_test)
perf = auc(Y_test[:, 0], P)
print("auc for task 1 %f" % perf)
def testOrdinalRegression(self):
m, n = 100, 300
for regparam in [0.00000001, 1, 100000000]:
#for regparam in [1000]:
Xtrain = np.mat(np.random.rand(n, m))
Y = np.mat(np.random.rand(m, 1))
rpool = {}
rpool['X'] = Xtrain.T
rpool['Y'] = Y
rpool['regparam'] = regparam
rpool["bias"] = 1.0
rls = CGRankRLS(**rpool)
model = rls.predictor
W = model.W
In = np.mat(np.identity(n))
Im = np.mat(np.identity(m))
L = np.mat(Im - (1. / m) * np.ones((m, m), dtype=np.float64))
G = Xtrain * L * Xtrain.T + regparam * In
W2 = np.squeeze(np.array(G.I * Xtrain * L * Y))
for i in range(W.shape[0]):
#for j in range(W.shape[1]):
# self.assertAlmostEqual(W[i,j],W2[i,j], places=5)
self.assertAlmostEqual(W[i], W2[i], places=5)
