def test_holdout(self):
for X in [self.Xtrain1, self.Xtrain2]:
for Y in [self.Ytrain1, self.Ytrain2]:
m = X.shape[0]
qids, L = generate_qids(m)
qids = np.array(qids)
hoindices = np.where(qids == 1)[0]
hocompl = list(set(range(m)) - set(hoindices))
#Holdout with linear kernel
rls1 = QueryRankRLS(X, Y, qids)
rls2 = QueryRankRLS(X[hocompl], Y[hocompl], qids[hocompl])
P1 = rls1.holdout(hoindices)
P2 = rls2.predict(X[hoindices])
assert_allclose(P1, P2)
#Holdout with bias
rls1 = QueryRankRLS(X, Y, qids, bias=3.0)
rls2 = QueryRankRLS(X[hocompl],
Y[hocompl],
qids[hocompl],
bias=3.0)
P1 = rls1.holdout(hoindices)
P2 = rls2.predict(X[hoindices])
assert_allclose(P1, P2)
#Fast regularization
for i in range(-5, 5):
rls1.solve(2**i)
rls2.solve(2**i)
P1 = rls1.holdout(hoindices)
P2 = rls2.predict(X[hoindices])
assert_allclose(P1, P2)
#Kernel holdout
rls1 = QueryRankRLS(X,
Y,
qids,
kernel="GaussianKernel",
gamma=0.01)
rls2 = QueryRankRLS(X[hocompl],
Y[hocompl],
qids[hocompl],
kernel="GaussianKernel",
gamma=0.01)
P1 = rls1.holdout(hoindices)
P2 = rls2.predict(X[hoindices])
assert_allclose(P1, P2)
for i in range(-15, 15):
rls1.solve(2**i)
rls2.solve(2**i)
P1 = rls1.holdout(hoindices)
P2 = rls2.predict(X[hoindices])
assert_allclose(P1, P2)
#Incorrect indices
I = [0, 3, 100]
self.assertRaises(IndexError, rls1.holdout, I)
I = [-1, 0, 2]
self.assertRaises(IndexError, rls1.holdout, I)
I = [1, 1, 2]
self.assertRaises(IndexError, rls1.holdout, I)
I = [0, 4, 8]
self.assertRaises(IndexError, rls1.holdout, I)
def test_holdout(self):
for X in [self.Xtrain1, self.Xtrain2]:
for Y in [self.Ytrain1, self.Ytrain2]:
m = X.shape[0]
qids, L = generate_qids(m)
qids = np.array(qids)
hoindices = np.where(qids == 1)[0]
hocompl = list(set(range(m)) - set(hoindices))
#Holdout with linear kernel
rls1 = QueryRankRLS(X, Y, qids)
rls2 = QueryRankRLS(X[hocompl], Y[hocompl], qids[hocompl])
P1 = rls1.holdout(hoindices)
P2 = rls2.predict(X[hoindices])
assert_allclose(P1, P2)
#Holdout with bias
rls1 = QueryRankRLS(X, Y, qids, bias = 3.0)
rls2 = QueryRankRLS(X[hocompl], Y[hocompl], qids[hocompl], bias = 3.0)
P1 = rls1.holdout(hoindices)
P2 = rls2.predict(X[hoindices])
assert_allclose(P1, P2)
#Fast regularization
for i in range(-5, 5):
rls1.solve(2**i)
rls2.solve(2**i)
P1 = rls1.holdout(hoindices)
P2 = rls2.predict(X[hoindices])
assert_allclose(P1, P2)
#Kernel holdout
rls1 = QueryRankRLS(X, Y, qids, kernel = "GaussianKernel", gamma = 0.01)
rls2 = QueryRankRLS(X[hocompl], Y[hocompl], qids[hocompl], kernel = "GaussianKernel", gamma = 0.01)
P1 = rls1.holdout(hoindices)
P2 = rls2.predict(X[hoindices])
assert_allclose(P1, P2)
for i in range(-15, 15):
rls1.solve(2**i)
rls2.solve(2**i)
P1 = rls1.holdout(hoindices)
P2 = rls2.predict(X[hoindices])
assert_allclose(P1, P2)
#Incorrect indices
I = [0, 3, 100]
self.assertRaises(IndexError, rls1.holdout, I)
I = [-1, 0, 2]
self.assertRaises(IndexError, rls1.holdout, I)
I = [1,1,2]
self.assertRaises(IndexError, rls1.holdout, I)
I = [0,4,8]
self.assertRaises(IndexError, rls1.holdout, I)
def train_rls():
#Select regparam with k-fold cross-validation,
#where instances related to a single sentence form
#together a fold
X_train = read_sparse("train_2000_x.txt")
Y_train = np.loadtxt("train_2000_y.txt")
X_test = read_sparse("test_2000_x.txt", X_train.shape[1])
Y_test = np.loadtxt("test_2000_y.txt")
#list of sentence ids
qids_train = np.loadtxt("train_2000_qids.txt")
qids_test = np.loadtxt("test_2000_qids.txt")
learner = QueryRankRLS(X_train, Y_train, qids_train)
P_test = learner.predict(X_test)
folds = map_ids(qids_train)
perfs = []
for fold in folds:
if np.var(Y_train[fold]) != 0:
P = learner.holdout(fold)
c = cindex(Y_train[fold], P)
perfs.append(c)
perf = np.mean(perfs)
print("leave-query-out cross-validation cindex %f" % perf)
partition = map_ids(qids_test)
test_perfs = []
#compute the ranking accuracy separately for each test query
for query in partition:
#skip such queries, where all instances have the same
#score, since in this case cindex is undefined
if np.var(Y_test[query]) != 0:
perf = cindex(Y_test[query], P_test[query])
test_perfs.append(perf)
test_perf = np.mean(test_perfs)
print("test cindex %f" % test_perf)
def train_rls():
#Select regparam with k-fold cross-validation,
#where instances related to a single sentence form
#together a fold
X_train = read_sparse("train_2000_x.txt")
Y_train = np.loadtxt("train_2000_y.txt")
X_test = read_sparse("test_2000_x.txt", X_train.shape[1])
Y_test = np.loadtxt("test_2000_y.txt")
#list of sentence ids
qids_train = np.loadtxt("train_2000_qids.txt")
qids_test = np.loadtxt("test_2000_qids.txt")
learner = QueryRankRLS(X_train, Y_train, qids_train)
P_test = learner.predict(X_test)
folds = map_ids(qids_train)
perfs = []
for fold in folds:
if np.var(Y_train[fold]) != 0:
P = learner.holdout(fold)
c = cindex(Y_train[fold], P)
perfs.append(c)
perf = np.mean(perfs)
print("leave-query-out cross-validation cindex %f" %perf)
partition = map_ids(qids_test)
test_perfs = []
#compute the ranking accuracy separately for each test query
for query in partition:
#skip such queries, where all instances have the same
#score, since in this case cindex is undefined
if np.var(Y_test[query]) != 0:
perf = cindex(Y_test[query], P_test[query])
test_perfs.append(perf)
test_perf = np.mean(test_perfs)
print("test cindex %f" %test_perf)
