# split data into train+validation set and test set
X_trainval, X_test, y_trainval, y_test = train_test_split(dataset.data, dataset.target)
# split train+validation set into training and validation sets
X_train, X_valid, y_train, y_valid = train_test_split(X_trainval, y_trainval)
# train on classifier
clf.fit(X_train, y_train)
# evaluate the classifier on the test set
score = svm.score(X_valid, y_valid)
# combined training & validation set and evaluate it on the test set
clf.fit(X_trainval, y_trainval)
test_score = svm.score(X_test, y_test)

import numpy as np
from sklearn import metrics
y = np.array([1, 1, 2, 2])
scores = np.array([0.1, 0.4, 0.35, 0.8])
fpr, tpr, thresholds = metrics.roc_curve(y, scores, pos_label=2)

print(fpr)

print(tpr)

print(thresholds)

y_preds = clf.predict(X_test)

from sklearn.metrics import roc_curve, auc

fpr, tpr, thresholds = roc_curve(y, y_preds, pos_label=1)
auc_roc = auc(fpr, tpr)