n_features=20,
n_informative=2,
n_redundant=2,
n_repeated=0,
n_classes=2,
n_clusters_per_class=2,
weights=None,
flip_y=0.01,
class_sep=1.0,
hypercube=True,
shift=0.0,
scale=1.0,
shuffle=True,
random_state=None)
y[np.where(y == 0)[0]] = -1.
estimator = SVC(C=10,
kernel='rbf',
gamma=0.4,
probability=True)
pu_estimator = PUAdapter(estimator, hold_out_ratio=0.2)
pu_estimator.fit(X, y)
print pu_estimator
print
print "Comparison of estimator and PUAdapter(estimator):"
print "Number of disagreements: ", len(np.where((pu_estimator.predict(X) == estimator.predict(X)) == False)[0])
print "Number of agreements: ", len(np.where((pu_estimator.predict(X) == estimator.predict(X)) == True)[0])
sacrifice = pos[:n_sacrifice]
y_train_pu[sacrifice] = -1.
print "PU transformation applied. We now have:"
print len(np.where(y_train_pu == -1.)[0])," are bening"
print len(np.where(y_train_pu == +1.)[0])," are malignant"
print
#Get f1 score with pu_learning
print "PU learning in progress..."
estimator = RandomForestClassifier(n_estimators=100,
criterion='gini',
bootstrap=True,
n_jobs=1)
pu_estimator = PUAdapter(estimator)
pu_estimator.fit(X_train,y_train_pu)
y_pred = pu_estimator.predict(X_test)
precision, recall, f1_score, _ = precision_recall_fscore_support(y_test, y_pred)
pu_f1_scores.append(f1_score[1])
print "F1 score: ", f1_score[1]
print "Precision: ", precision[1]
print "Recall: ", recall[1]
print
#Get f1 score without pu_learning
print "Regular learning in progress..."
estimator = RandomForestClassifier(n_estimators=100,
bootstrap=True,
n_jobs=1)
estimator.fit(X_train,y_train_pu)
y_pred = estimator.predict(X_test)