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 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 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 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 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 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 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_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, 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():
#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 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))