【高级编程技术】第15周作业

from sklearn import datasets, cross_validation
from sklearn.naive_bayes import GaussianNB
from sklearn.svm import SVC
from sklearn.ensemble import RandomForestClassifier
from sklearn import metrics

def evaluate(y_test, pred, method):
	acc = metrics.accuracy_score(y_test, pred)
	f1 = metrics.f1_score(y_test, pred)
	auc = metrics.roc_auc_score(y_test, pred)
	print(method + ":")
	print("\nacc: ")
	print(acc)
	print("\nf1: ")
	print(f1)
	print("\nauc: ")
	print(auc)
	print("\n")


dataset = datasets.make_classification(n_samples=1000, 
	n_features=10,n_informative=2, 
	n_redundant=2, n_repeated=0, n_classes=2)

kf = cross_validation.KFold(1000, n_folds=10, shuffle=True)
for train_index, test_index in kf:
	X_train, y_train = dataset[0][train_index], dataset[1][train_index]
	X_test, y_test = dataset[0][test_index], dataset[1][test_index]


clf = GaussianNB()
clf.fit(X_train, y_train)
pred = clf.predict(X_test)
evaluate(y_test,pred,"naive_bayes")

C_values = [1e-02, 1e-01, 1e00, 1e01, 1e02]
for C_value in C_values:
	clf = SVC(C=C_value, kernel='rbf', gamma=0.1)
	clf.fit(X_train, y_train)
	pred = clf.predict(X_test)
	evaluate(y_test,pred,"SVC, C_value= %s" % str(C_value))


clf = RandomForestClassifier(n_estimators = 6)
clf.fit(X_train, y_train)
pred = clf.predict(X_test)
evaluate(y_test,pred,"RandomForestClassifier")