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)
def main():
X1_train, X2_train, Y_train, X1_test, X2_test, Y_test = davis_data.setting3_split()
learner = TwoStepRLS(X1 = X1_train, X2 = X2_train, Y = Y_train, regparam1=1.0, regparam2=1.0)
log_regparams1 = range(-8, -4)
log_regparams2 = range(20,25)
for log_regparam1 in log_regparams1:
for log_regparam2 in log_regparams2:
learner.solve(2.**log_regparam1, 2.**log_regparam2)
P = learner.predict(X1_test, X2_test)
perf = cindex(Y_test, P)
print("regparam 2**%d 2**%d, test set cindex %f" %(log_regparam1, log_regparam2, perf))
P = learner.leave_x2_out()
perf = cindex(Y_train, P)
print("regparam 2**%d 2**%d, leave-column-out cindex %f" %(log_regparam1, log_regparam2, perf))
def main():
X1_train, X2_train, Y_train, X1_test, X2_test, Y_test = davis_data.setting4_split()
learner = TwoStepRLS(X1 = X1_train, X2 = X2_train, Y = Y_train, regparam1=1.0, regparam2=1.0)
log_regparams1 = range(-8, -4)
log_regparams2 = range(20,25)
for log_regparam1 in log_regparams1:
for log_regparam2 in log_regparams2:
learner.solve(2.**log_regparam1, 2.**log_regparam2)
P = learner.predict(X1_test, X2_test)
perf = cindex(Y_test, P)
print("regparam 2**%d 2**%d, test set cindex %f" %(log_regparam1, log_regparam2, perf))
P = learner.out_of_sample_loo()
perf = cindex(Y_train, P)
print("regparam 2**%d 2**%d, out-of-sample loo cindex %f" %(log_regparam1, log_regparam2, perf))
def train_rls():
#Trains RLS with default parameters (regparam=1.0, kernel='LinearKernel')
X_train, Y_train, X_test, Y_test = load_housing()
#generate fold partition, arguments: train_size, k, random_seed
folds = random_folds(len(Y_train), 5, 10)
learner = GlobalRankRLS(X_train, Y_train)
perfs = []
for fold in folds:
P = learner.holdout(fold)
c = cindex(Y_train[fold], P)
perfs.append(c)
perf = np.mean(perfs)
print("5-fold cross-validation cindex %f" % perf)
P_test = learner.predict(X_test)
print("test cindex %f" % cindex(Y_test, P_test))
def train_rls():
#Trains RLS with default parameters (regparam=1.0, kernel='LinearKernel')
X_train, Y_train, X_test, Y_test = load_housing()
#generate fold partition, arguments: train_size, k, random_seed
folds = random_folds(len(Y_train), 5, 10)
learner = GlobalRankRLS(X_train, Y_train)
perfs = []
for fold in folds:
P = learner.holdout(fold)
c = cindex(Y_train[fold], P)
perfs.append(c)
perf = np.mean(perfs)
print("5-fold cross-validation cindex %f" %perf)
P_test = learner.predict(X_test)
print("test cindex %f" %cindex(Y_test, P_test))
def train_rls():
#Trains RLS with default parameters (regparam=1.0, kernel='LinearKernel')
X_train, Y_train, X_test, Y_test = load_housing()
learner = GlobalRankRLS(X_train, Y_train)
#Test set predictions
P_test = learner.predict(X_test)
print("test cindex %f" %cindex(Y_test, P_test))
def train_rls():
#Selects both the gamma parameter for Gaussian kernel, and regparam with kfoldcv
X_train, Y_train, X_test, Y_test = load_housing()
folds = random_folds(len(Y_train), 5, 10)
regparams = [2.**i for i in range(-15, 16)]
gammas = regparams
best_regparam = None
best_gamma = None
best_perf = 0.
best_learner = None
for gamma in gammas:
#New RLS is initialized for each kernel parameter
learner = KfoldRankRLS(X_train,
Y_train,
kernel="GaussianKernel",
folds=folds,
gamma=gamma,
regparams=regparams,
measure=cindex)
perf = np.max(learner.cv_performances)
if perf > best_perf:
best_perf = perf
best_regparam = learner.regparam
best_gamma = gamma
best_learner = learner
P_test = best_learner.predict(X_test)
print("best parameters gamma %f regparam %f" % (best_gamma, best_regparam))
print("best kfoldcv cindex %f" % best_perf)
print("test cindex %f" % cindex(Y_test, P_test))
def skcv_rls(coordinates, Xdata, Ydata, number_of_folds, dzradii, regparam, visualization):
print("Starting skcv-rls analysis...")
# Calculate sorted pairwise distance matrix and indexes
performanceTable = np.zeros([len(dzradii),2])
data_distances, data_distance_indexes = distanceMatrix(coordinates)
folds = random_folds(len(Ydata), number_of_folds)
for rind, dzradius in enumerate(dzradii):
print("Analysis ongoing, dead zone radius: " + str(dzradius) + "m / " + str(dzradii[len(dzradii)-1]) + "m")
# Calculate dead zone folds
dz_folds = dzfolds(dzradius, folds, data_distances, data_distance_indexes)
learner = RLS(Xdata, Ydata, regparam=regparam)
P = np.zeros(Ydata.shape)
for fold_id, dz_fold in enumerate(dz_folds):
preds = learner.holdout(dz_fold)
if preds.ndim == 0:
P[folds[fold_id]] = preds
else:
P[folds[fold_id]] = preds[0:len(folds[fold_id])]
if visualization: # Check for visualization
testcoords = coordinates[folds[fold_id],:]
dzcoords = coordinates[dz_fold, :]
visualize_skcv(coordinates, testcoords, dzcoords, dzradius)
perf = cindex(Ydata, P)
performanceTable[rind,0] = dzradius
performanceTable[rind, 1] = perf
plotRes_skcv(performanceTable, rind, number_of_folds, "rls")
print("Analysis done.")
return performanceTable
def skcv_knn(coordinates, Xdata, Ydata, number_of_folds, dzradii, k_neighbors, visualization):
print("Starting skcv-knn analysis...")
# Calculate sorted pairwise distance matrix and indexes
performanceTable = np.zeros([len(dzradii),2])
data_distances, data_distance_indexes = distanceMatrix(coordinates)
folds = random_folds(len(Ydata), number_of_folds)
for rind, dzradius in enumerate(dzradii):
print("Analysis ongoing, dead zone radius: " + str(dzradius) + "m / " + str(dzradii[len(dzradii)-1]) + "m")
# Calculate dead zone folds
dz_folds = dzfolds(dzradius, folds, data_distances, data_distance_indexes)
# Initialize performance variables
P = np.zeros(Ydata.shape)
for fold_id, dz_fold in enumerate(dz_folds):
X_tr = np.delete(Xdata, dz_fold, axis=0)
Y_tr = np.delete(Ydata, dz_fold, axis=0)
learner = KNeighborsRegressor(n_neighbors=k_neighbors)
learner.fit(X_tr, Y_tr)
preds = learner.predict(Xdata[dz_fold])
if preds.ndim == 0:
P[folds[fold_id]] = preds
else:
P[folds[fold_id]] = preds[0:len(folds[fold_id])]
if visualization: # Check for visualization
testcoords = coordinates[folds[fold_id],:]
dzcoords = coordinates[dz_fold, :]
visualize_skcv(coordinates, testcoords, dzcoords, dzradius)
perf = cindex(Ydata, P)
performanceTable[rind,0] = dzradius
performanceTable[rind, 1] = perf
plotRes_skcv(performanceTable, rind, number_of_folds, "K-nn")
print("Analysis done.")
return performanceTable
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")
regparams = [2.**i for i in range(-10, 10)]
learner = LeaveQueryOutRankRLS(X_train, Y_train, qids_train, regparams = regparams, measure = cindex)
lqo_perfs = learner.cv_performances
P_test = learner.predict(X_test)
print("leave-query-out performances " +str(lqo_perfs))
print("chosen regparam %f" %learner.regparam)
partition = map_ids(qids_test)
#compute the ranking accuracy separately for each test query
test_perfs = []
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 main():
X1_train, X2_train, Y_train, X1_test, X2_test, Y_test = davis_data.settingC_split()
m = X2_train.shape[0]
learner = TwoStepRLS(X1 = X1_train, X2 = X2_train, Y = Y_train, regparam1=1.0, regparam2=1.0)
log_regparams1 = range(-8, -4)
log_regparams2 = range(20,25)
#Create random split to 5 folds for the targets
folds = random_folds(m, 5, seed=12345)
for log_regparam1 in log_regparams1:
for log_regparam2 in log_regparams2:
learner.solve(2.**log_regparam1, 2.**log_regparam2)
P = learner.predict(X1_test, X2_test)
perf = cindex(Y_test, P)
print("regparam 2**%d 2**%d, test set cindex %f" %(log_regparam1, log_regparam2, perf))
P = learner.x2_kfold_cv(folds)
perf = cindex(Y_train, P)
print("regparam 2**%d 2**%d, K-fold cindex %f" %(log_regparam1, log_regparam2, perf))
def main():
X1_train, X2_train, Y_train, X1_test, X2_test, Y_test = davis_data.settingB_split()
learner = KronRLS(X1 = X1_train, X2 = X2_train, Y = Y_train)
log_regparams = range(15, 35)
for log_regparam in log_regparams:
learner.solve(2.**log_regparam)
P = learner.predict(X1_test, X2_test)
perf = cindex(Y_test, P)
print("regparam 2**%d, cindex %f" %(log_regparam, perf))
def main():
X1_train, X2_train, Y_train, X1_test, X2_test, Y_test = davis_data.setting2_split()
learner = KronRLS(X1 = X1_train, X2 = X2_train, Y = Y_train)
log_regparams = range(15, 35)
for log_regparam in log_regparams:
learner.solve(2.**log_regparam)
P = learner.predict(X1_test, X2_test)
perf = cindex(Y_test, P)
print("regparam 2**%d, cindex %f" %(log_regparam, perf))
def train_rls():
#Trains RankRLS with automatically selected regularization parameter
X_train, Y_train, X_test, Y_test = load_housing()
regparams = [2.**i for i in range(-10, 10)]
learner = LeavePairOutRankRLS(X_train, Y_train, regparams = regparams)
loo_errors = learner.cv_performances
P_test = learner.predict(X_test)
print("leave-pair-out performances " +str(loo_errors))
print("chosen regparam %f" %learner.regparam)
print("test set cindex %f" %cindex(Y_test, P_test))
def main():
X1, X2, Y = davis_data.load_davis()
Y = Y.ravel(order='F')
learner = KronRLS(X1 = X1, X2 = X2, Y = Y)
log_regparams = range(15, 35)
for log_regparam in log_regparams:
learner.solve(2.**log_regparam)
P = learner.in_sample_loo()
perf = cindex(Y, P)
print("regparam 2**%d, cindex %f" %(log_regparam, perf))
def train_rls():
#Trains RLS with automatically selected regularization parameter
X_train, Y_train, X_test, Y_test = load_housing()
regparams = [2.**i for i in range(-15, 16)]
learner = LeaveOneOutRLS(X_train, Y_train, regparams = regparams, measure=cindex)
loo_errors = learner.cv_performances
P_test = learner.predict(X_test)
print("leave-one-out cindex " +str(loo_errors))
print("chosen regparam %f" %learner.regparam)
print("test cindex %f" %cindex(Y_test, P_test))
def main():
X1_train, X2_train, Y_train, X1_test, X2_test, Y_test = davis_data.settingD_split()
n = X1_train.shape[0]
m = X2_train.shape[0]
learner = TwoStepRLS(X1 = X1_train, X2 = X2_train, Y = Y_train, regparam1=1.0, regparam2=1.0)
log_regparams1 = range(-8, -4)
log_regparams2 = range(20,25)
#Create random split to 5 folds for both drugs and targets
drug_folds = random_folds(n, 5, seed=123)
target_folds = random_folds(m, 5, seed=456)
for log_regparam1 in log_regparams1:
for log_regparam2 in log_regparams2:
learner.solve(2.**log_regparam1, 2.**log_regparam2)
P = learner.predict(X1_test, X2_test)
perf = cindex(Y_test, P)
print("regparam 2**%d 2**%d, test set cindex %f" %(log_regparam1, log_regparam2, perf))
P = learner.out_of_sample_kfold_cv(drug_folds, target_folds)
perf = cindex(Y_train, P)
print("regparam 2**%d 2**%d, out-of-sample loo cindex %f" %(log_regparam1, log_regparam2, perf))
def main():
X1, X2, Y = davis_data.load_davis()
Y = Y.ravel(order='F')
learner = TwoStepRLS(X1 = X1, X2 = X2, Y = Y, regparam1=1.0, regparam2=1.0)
log_regparams1 = range(-8, -4)
log_regparams2 = range(20,25)
for log_regparam1 in log_regparams1:
for log_regparam2 in log_regparams2:
learner.solve(2.**log_regparam1, 2.**log_regparam2)
P = learner.in_sample_loo()
perf = cindex(Y, P)
print("regparam 2**%d 2**%d, cindex %f" %(log_regparam1, log_regparam2, perf))
def train_rls():
#Trains RankRLS with automatically selected regularization parameter
X_train, Y_train, X_test, Y_test = load_housing()
#generate fold partition, arguments: train_size, k, random_seed
folds = random_folds(len(Y_train), 5, 10)
regparams = [2.**i for i in range(-10, 10)]
learner = KfoldRankRLS(X_train, Y_train, folds = folds, regparams = regparams, measure=cindex)
kfold_perfs = learner.cv_performances
P_test = learner.predict(X_test)
print("kfold performances " +str(kfold_perfs))
print("chosen regparam %f" %learner.regparam)
print("test set cindex %f" %cindex(Y_test, P_test))
def main():
X = np.loadtxt("drug-drug_similarities_2D.txt")
Y = np.loadtxt("drug-drug_similarities_ECFP4.txt")
Y = Y.ravel(order='F')
K = np.dot(X, X)
learner = TwoStepRLS(K1 = K, K2 = K, Y = Y, regparam1=1.0, regparam2=1.0)
log_regparams = range(-10, 0)
for log_regparam in log_regparams:
learner.solve(2.**log_regparam, 2.**log_regparam)
P = learner.out_of_sample_loo_symmetric()
perf = cindex(Y, P)
print("regparam 2**%d, cindex %f" %(log_regparam, perf))
def main():
X = np.loadtxt("drug-drug_similarities_2D.txt")
Y = np.loadtxt("drug-drug_similarities_ECFP4.txt")
Y = Y.ravel(order='F')
K = np.dot(X, X)
learner = TwoStepRLS(K1=K, K2=K, Y=Y, regparam1=1.0, regparam2=1.0)
log_regparams = range(-10, 0)
for log_regparam in log_regparams:
learner.solve(2.**log_regparam, 2.**log_regparam)
P = learner.out_of_sample_loo_symmetric()
perf = cindex(Y, P)
print("regparam 2**%d, cindex %f" % (log_regparam, perf))
def main():
X1_train, X2_train, Y_train, X1_test, X2_test, Y_test = davis_data.settingB_split(
)
learner = TwoStepRLS(X1=X1_train,
X2=X2_train,
Y=Y_train,
regparam1=1.0,
regparam2=1.0)
log_regparams1 = range(-8, -4)
log_regparams2 = range(20, 25)
for log_regparam1 in log_regparams1:
for log_regparam2 in log_regparams2:
learner.solve(2.**log_regparam1, 2.**log_regparam2)
P = learner.predict(X1_test, X2_test)
perf = cindex(Y_test, P)
print("regparam 2**%d 2**%d, test set cindex %f" %
(log_regparam1, log_regparam2, perf))
P = learner.leave_x1_out()
perf = cindex(Y_train, P)
print("regparam 2**%d 2**%d, leave-row-out cindex %f" %
(log_regparam1, log_regparam2, perf))
def main():
X1, X2, Y = davis_data.load_davis()
Y = Y.ravel(order='F')
learner = TwoStepRLS(X1=X1, X2=X2, Y=Y, regparam1=1.0, regparam2=1.0)
log_regparams1 = range(-8, -4)
log_regparams2 = range(20, 25)
for log_regparam1 in log_regparams1:
for log_regparam2 in log_regparams2:
learner.solve(2.**log_regparam1, 2.**log_regparam2)
P = learner.in_sample_loo()
perf = cindex(Y, P)
print("regparam 2**%d 2**%d, cindex %f" %
(log_regparam1, log_regparam2, perf))
def train_rls():
#Trains RLS with automatically selected regularization parameter
X_train, Y_train, X_test, Y_test = load_housing()
regparams = [2.**i for i in range(-15, 16)]
learner = LeaveOneOutRLS(X_train,
Y_train,
regparams=regparams,
measure=cindex)
loo_errors = learner.cv_performances
P_test = learner.predict(X_test)
print("leave-one-out cindex " + str(loo_errors))
print("chosen regparam %f" % learner.regparam)
print("test cindex %f" % cindex(Y_test, P_test))
def main():
X1_train, X2_train, Y_train, X1_test, X2_test, Y_test = davis_data.settingD_split()
kernel1 = GaussianKernel(X1_train, gamma=0.01)
kernel2 = GaussianKernel(X2_train, gamma=10**-9)
K1_train = kernel1.getKM(X1_train)
K1_test = kernel1.getKM(X1_test)
K2_train = kernel2.getKM(X2_train)
K2_test = kernel2.getKM(X2_test)
learner = KronRLS(K1 = K1_train, K2 = K2_train, Y = Y_train)
log_regparams = range(-15, 15)
for log_regparam in log_regparams:
learner.solve(2.**log_regparam)
P = learner.predict(K1_test, K2_test)
perf = cindex(Y_test, P)
print("regparam 2**%d, cindex %f" %(log_regparam, perf))
def main():
X1_train, X2_train, Y_train, X1_test, X2_test, Y_test = davis_data.settingC_split(
)
m = X2_train.shape[0]
learner = TwoStepRLS(X1=X1_train,
X2=X2_train,
Y=Y_train,
regparam1=1.0,
regparam2=1.0)
log_regparams1 = range(-8, -4)
log_regparams2 = range(20, 25)
#Create random split to 5 folds for the targets
folds = random_folds(m, 5, seed=12345)
for log_regparam1 in log_regparams1:
for log_regparam2 in log_regparams2:
learner.solve(2.**log_regparam1, 2.**log_regparam2)
P = learner.predict(X1_test, X2_test)
perf = cindex(Y_test, P)
print("regparam 2**%d 2**%d, test set cindex %f" %
(log_regparam1, log_regparam2, perf))
P = learner.x2_kfold_cv(folds)
perf = cindex(Y_train, P)
print("regparam 2**%d 2**%d, K-fold cindex %f" %
(log_regparam1, log_regparam2, perf))
def train_rls():
#Trains RankRLS with automatically selected regularization parameter
X_train, Y_train, X_test, Y_test = load_housing()
#generate fold partition, arguments: train_size, k, random_seed
folds = random_folds(len(Y_train), 5, 10)
regparams = [2.**i for i in range(-10, 10)]
learner = KfoldRankRLS(X_train,
Y_train,
folds=folds,
regparams=regparams,
measure=cindex)
kfold_perfs = learner.cv_performances
P_test = learner.predict(X_test)
print("kfold performances " + str(kfold_perfs))
print("chosen regparam %f" % learner.regparam)
print("test set cindex %f" % cindex(Y_test, P_test))
def main():
X1, X2, Y = davis_data.load_davis()
n = X1.shape[0]
m = X2.shape[0]
Y = Y.ravel(order='F')
learner = TwoStepRLS(X1 = X1, X2 = X2, Y = Y, regparam1=1.0, regparam2=1.0)
log_regparams1 = range(-8, -4)
log_regparams2 = range(20,25)
#Create random split to 5 folds for the drug-target pairs
folds = random_folds(n*m, 5, seed=12345)
#Map the indices back to (drug_indices, target_indices)
folds = [np.unravel_index(fold, (n,m)) for fold in folds]
for log_regparam1 in log_regparams1:
for log_regparam2 in log_regparams2:
learner.solve(2.**log_regparam1, 2.**log_regparam2)
P = learner.in_sample_kfoldcv(folds)
perf = cindex(Y, P)
print("regparam 2**%d 2**%d, cindex %f" %(log_regparam1, log_regparam2, perf))
def main():
X1, X2, Y = davis_data.load_davis()
n = X1.shape[0]
m = X2.shape[0]
Y = Y.ravel(order='F')
learner = TwoStepRLS(X1=X1, X2=X2, Y=Y, regparam1=1.0, regparam2=1.0)
log_regparams1 = range(-8, -4)
log_regparams2 = range(20, 25)
#Create random split to 5 folds for the drug-target pairs
folds = random_folds(n * m, 5, seed=12345)
#Map the indices back to (drug_indices, target_indices)
folds = [np.unravel_index(fold, (n, m)) for fold in folds]
for log_regparam1 in log_regparams1:
for log_regparam2 in log_regparams2:
learner.solve(2.**log_regparam1, 2.**log_regparam2)
P = learner.in_sample_kfoldcv(folds)
perf = cindex(Y, P)
print("regparam 2**%d 2**%d, cindex %f" %
(log_regparam1, log_regparam2, perf))
def train_rls():
#Trains RLS with default parameters (regparam=1.0, kernel='LinearKernel')
X_train, Y_train, X_test, Y_test = load_housing()
pairs_start = []
pairs_end = []
#Sample 1000 pairwise preferences from the data
trange = range(len(Y_train))
while len(pairs_start) < 1000:
ind0 = random.choice(trange)
ind1 = random.choice(trange)
if Y_train[ind0] > Y_train[ind1]:
pairs_start.append(ind0)
pairs_end.append(ind1)
elif Y_train[ind0] < Y_train[ind1]:
pairs_start.append(ind1)
pairs_end.append(ind0)
learner = PPRankRLS(X_train, pairs_start, pairs_end)
#Test set predictions
P_test = learner.predict(X_test)
print("test cindex %f" % cindex(Y_test, P_test))
def train_rls():
#Selects both the gamma parameter for Gaussian kernel, and regparam with kfoldcv
X_train, Y_train, X_test, Y_test = load_housing()
folds = random_folds(len(Y_train), 5, 10)
regparams = [2.**i for i in range(-15, 16)]
gammas = regparams
best_regparam = None
best_gamma = None
best_perf = 0.
best_learner = None
for gamma in gammas:
#New RLS is initialized for each kernel parameter
learner = KfoldRankRLS(X_train, Y_train, kernel = "GaussianKernel", folds = folds, gamma = gamma, regparams = regparams, measure=cindex)
perf = np.max(learner.cv_performances)
if perf > best_perf:
best_perf = perf
best_regparam = learner.regparam
best_gamma = gamma
best_learner = learner
P_test = best_learner.predict(X_test)
print("best parameters gamma %f regparam %f" %(best_gamma, best_regparam))
print("best kfoldcv cindex %f" %best_perf)
print("test cindex %f" %cindex(Y_test, P_test))
import numpy as np
from rlscore.learner.global_rankrls import KfoldRankRLS
from rlscore.utilities.reader import read_folds
from rlscore.utilities.reader import read_sparse
from rlscore.measure import cindex
train_labels = np.loadtxt("./legacy_tests/data/rank_train.labels")
test_labels = np.loadtxt("./legacy_tests/data/rank_test.labels")
folds = read_folds("./legacy_tests/data/folds.txt")
train_features = read_sparse("./legacy_tests/data/rank_train.features")
test_features = read_sparse("./legacy_tests/data/rank_test.features")
kwargs = {}
kwargs['measure']=cindex
kwargs['regparams'] = [2**i for i in range(-10,11)]
kwargs["Y"] = train_labels
kwargs["X"] = train_features
kwargs["folds"] = folds
learner = KfoldRankRLS(**kwargs)
grid = kwargs['regparams']
perfs = learner.cv_performances
for i in range(len(grid)):
print "parameter %f cv_performance %f" %(grid[i], perfs[i])
P = learner.predict(test_features)
test_perf = cindex(test_labels, P)
print "test set performance: %f" %test_perf
import numpy as np
from rlscore.learner.global_rankrls import LeavePairOutRankRLS
from rlscore.reader import read_sparse
from rlscore.reader import read_sparse
from rlscore.measure import cindex
train_labels = np.loadtxt("./examples/data/rank_train.labels")
test_labels = np.loadtxt("./examples/data/rank_test.labels")
train_features = read_sparse("./examples/data/rank_train.features")
test_features = read_sparse("./examples/data/rank_test.features")
kwargs = {}
kwargs['measure'] = cindex
kwargs['regparams'] = [2**i for i in range(-10, 11)]
kwargs["Y"] = train_labels
kwargs["X"] = train_features
learner = LeavePairOutRankRLS(**kwargs)
grid = kwargs['regparams']
perfs = learner.cv_performances
for i in range(len(grid)):
print "parameter %f cv_performance %f" % (grid[i], perfs[i])
P = learner.predict(test_features)
test_perf = cindex(test_labels, P)
print "test set performance: %f" % test_perf
def callback(self, learner):
if self.iter % 10 == 0:
P = learner.predict(self.X1, self.X2, self.row_inds, self.col_inds)
perf = cindex(self.Y, P)
print("iteration %d cindex %f" % (self.iter, perf))
self.iter += 1
import numpy as np
from rlscore.measure import cindex
#Concordance index is a pairwise ranking measure
#Equivalent to AUC for bi-partite ranking problems
Y = [-1, -1, -1, 1, 1]
P = [-5, 2, -1, 1, 3.2]
cind1 = cindex(Y, P)
print("My cindex is %f" %cind1)
#Can handle also real-valued Y-values
Y2 = [-2.2, -1.3, -0.2, 0.5, 1.1]
#Almost correct ranking, but last two inverted
P2 = [-2.7, -1.1, 0.3, 0.6, 0.5]
cind2 = cindex(Y2, P2)
print("My cindex is %f" %cind2)
#Most performance measures take average over the columns for multi-target problems:
Y_big = np.vstack((Y, Y2)).T
P_big = np.vstack((P, P2)).T
print(Y_big)
print(P_big)
print("(cind1+cind2)/2 %f" %((cind1+cind2)/2.))
pred=clf.predict(K_test)
#print(pred.shape)
#print(Y_train.shape)
mse=np.sqrt(sqerror(np.ravel(Y_test,'F'),np.ravel(pred,'F')))
MSE[i,j]=mse
MSE_m = np.mean(MSE, axis=0)
opt_regpram = 10. ** (reg_par[np.argmin(MSE_m)])
clf = KernelRidge(alpha=opt_regpram)
K_train_o=K[train_out][:,train_out]
K_test_o = K[test_out][:, train_out]
Y_train_o = Y[train_out]
Y_test_o = Y[test_out]
clf.fit(K_train_o, Y_train_o)
pred_o = clf.predict(K_test_o)
mse_o[k] = np.sqrt(sqerror(np.ravel(Y_test_o, 'F'), np.ravel(pred_o, 'F')))
cind_o[k] = cindex(np.ravel(Y_test_o, 'F'), np.ravel(pred_o, 'F'))
pear_o[k] = pearsonr(np.ravel(Y_test_o, 'F'), np.ravel(pred_o, 'F'))[0]
spear_o[k] = spearmanr(np.ravel(Y_test_o, 'F'), np.ravel(pred_o, 'F'))[0]
#plt.scatter(np.ravel(Y_test_o, 'F'), np.ravel(pred_o, 'F'))
#plt.show()
print("op_reg:%f, fold RMSE:%f, fold Cindex:%f, fold Pearson:%f, fold Spearman:%f" % (opt_regpram,mse_o[k],
cind_o[k],
pear_o[k],
spear_o[k]))
k+=1
#MSE_diff_pca_comp[s]=np.mean(mse_o)
#s+=1
print("overall RMSE:%f, overall Cindex:%f, overall Pearson:%f, overall Spearman:%f" % (np.mean(mse_o),
np.mean(cind_o),
np.mean(pear_o),
np.mean(spear_o)))
train_labels = np.loadtxt("./examples/data/rank_train.labels")
test_labels = np.loadtxt("./examples/data/rank_test.labels")
train_qids = read_qids("./examples/data/rank_train.qids")
test_features = read_sparse("./examples/data/rank_test.features")
train_features = read_sparse("./examples/data/rank_train.features")
test_qids = read_qids("./examples/data/rank_test.qids")
kwargs = {}
kwargs['measure'] = cindex
kwargs['regparams'] = [2**i for i in range(-10, 11)]
kwargs["Y"] = train_labels
kwargs["X"] = train_features
kwargs["qids"] = train_qids
learner = LeaveQueryOutRankRLS(**kwargs)
grid = kwargs['regparams']
perfs = learner.cv_performances
for i in range(len(grid)):
print "parameter %f cv_performance %f" % (grid[i], perfs[i])
P = learner.predict(test_features)
from rlscore.measure.measure_utilities import UndefinedPerformance
from rlscore.measure.measure_utilities import qids_to_splits
test_qids = qids_to_splits(test_qids)
perfs = []
for query in test_qids:
try:
perf = cindex(test_labels[query], P[query])
perfs.append(perf)
except UndefinedPerformance:
pass
test_perf = np.mean(perfs)
print "test set performance: %f" % test_perf
import numpy as np
from rlscore.learner.query_rankrls import QueryRankRLS
from rlscore.utilities.reader import read_qids
from rlscore.utilities.reader import read_sparse
from rlscore.measure import cindex
train_labels = np.loadtxt("./legacy_tests/data/rank_train.labels")
test_labels = np.loadtxt("./legacy_tests/data/rank_test.labels")
train_qids = read_qids("./legacy_tests/data/rank_train.qids")
test_features = read_sparse("./legacy_tests/data/rank_test.features")
train_features = read_sparse("./legacy_tests/data/rank_train.features")
test_qids = read_qids("./legacy_tests/data/rank_test.qids")
kwargs = {}
kwargs["Y"] = train_labels
kwargs["X"] = train_features
kwargs["qids"] = train_qids
kwargs["regparam"] = 1
learner = QueryRankRLS(**kwargs)
P = learner.predict(test_features)
from rlscore.measure.measure_utilities import UndefinedPerformance
from rlscore.measure.measure_utilities import qids_to_splits
test_qids = qids_to_splits(test_qids)
perfs = []
for query in test_qids:
try:
perf = cindex(test_labels[query], P[query])
perfs.append(perf)
except UndefinedPerformance:
pass
test_perf = np.mean(perfs)
print("test set performance: %f" %test_perf)
def callback(self, learner):
if self.iter%10 == 0:
P = learner.predict(self.X1, self.X2, self.row_inds, self.col_inds)
perf = cindex(self.Y, P)
print("iteration %d cindex %f" %(self.iter, perf))
self.iter += 1
import numpy as np
from rlscore.measure import cindex
#Concordance index is a pairwise ranking measure
#Equivalent to AUC for bi-partite ranking problems
Y = [-1, -1, -1, 1, 1]
P = [-5, 2, -1, 1, 3.2]
cind1 = cindex(Y, P)
print("My cindex is %f" % cind1)
#Can handle also real-valued Y-values
Y2 = [-2.2, -1.3, -0.2, 0.5, 1.1]
#Almost correct ranking, but last two inverted
P2 = [-2.7, -1.1, 0.3, 0.6, 0.5]
cind2 = cindex(Y2, P2)
print("My cindex is %f" % cind2)
#Most performance measures take average over the columns for multi-target problems:
Y_big = np.vstack((Y, Y2)).T
P_big = np.vstack((P, P2)).T
print(Y_big)
print(P_big)
print("(cind1+cind2)/2 %f" % ((cind1 + cind2) / 2.))