第十五周作业（sklearn）

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

# Datasets
dataset = datasets.make_classification(n_samples=1000, n_features=10)

# 10-fold cross validation
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]

# GaussianNB
GaussianNB_clf = GaussianNB() 
GaussianNB_clf.fit(X_train, y_train) 
GaussianNB_pred = GaussianNB_clf.predict(X_test)

# SVM
SVM_clf = SVC(C=1e-01, kernel='rbf', gamma=0.1) 
SVM_clf.fit(X_train, y_train) 
SVM_pred = SVM_clf.predict(X_test)

# Random Forest
Random_Forest_clf = RandomForestClassifier(n_estimators=6) 
Random_Forest_clf.fit(X_train, y_train) 
Random_Forest_pred = Random_Forest_clf.predict(X_test)

# Evaluate the cross-validated performance
# GaussionNB
GaussianNB_acc = metrics.accuracy_score(y_test, GaussianNB_pred) 
print("GaussionNB_Accuracy: ", GaussianNB_acc) 
GaussianNB_f1 = metrics.f1_score(y_test, GaussianNB_pred) 
print("GaussionNB_F1_score: ", GaussianNB_f1)
GaussianNB_auc = metrics.roc_auc_score(y_test, GaussianNB_pred) 
print("GaussionNB_AUC_ROC: ", GaussianNB_auc)

#SVM
SVM_acc = metrics.accuracy_score(y_test, SVM_pred) 
print("SVM_Accuracy: ", SVM_acc) 
SVM_f1 = metrics.f1_score(y_test, SVM_pred) 
print("SVM_F1_score: ", SVM_f1)
SVM_auc = metrics.roc_auc_score(y_test, SVM_pred) 
print("SVM_AUC_ROC: ", SVM_auc)

#Random Forest
Random_Forest_acc = metrics.accuracy_score(y_test, Random_Forest_pred) 
print("Random_Forest_Accuracy: ", Random_Forest_acc) 
Random_Forest_f1 = metrics.f1_score(y_test, Random_Forest_pred) 
print("Random_Forest_F1_score: ", Random_Forest_f1)
Random_Forest_auc = metrics.roc_auc_score(y_test, Random_Forest_pred) 
print("Random_Forest_ROC: ", Random_Forest_auc)

总共有Gaussian、SVM和Random Forest三种机械学习算法，分别用Accuracy、F1-score和AUC ROC三种性能指标测试其cross-validated性能。