sklearn习题

Step1：

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

Step2：

from sklearn.model_selection import KFold
kf = KFold(n_splits=10)
for train_index, test_index in kf.split(dataset[0]):
    X_train, X_test = dataset[0][train_index], dataset[0][test_index]
    y_train, y_test = dataset[1][train_index], dataset[1][test_index]

Step3和Step4：

from sklearn.naive_bayes import GaussianNB
from sklearn import metrics
def test_GaussianNB(X_train, y_train, X_test, y_test):
    clf = GaussianNB()
    clf.fit(X_train, y_train)
    pred = clf.predict(X_test)
    print("GaussianNB: ")
    acc = metrics.accuracy_score(y_test, pred)
    print('acc: ', acc)
    f1 = metrics.f1_score(y_test, pred)
    print('f1: ', f1)
    auc = metrics.roc_auc_score(y_test, pred)
    print('auc: ', auc)


from sklearn.svm import SVC
def test_SVC(X_train, y_train, X_test, y_test):
    clf = SVC(C=1e-01, kernel='rbf', gamma=0.1)
    clf.fit(X_train, y_train)
    pred = clf.predict(X_test)
    print("SVC: ")
    acc = metrics.accuracy_score(y_test, pred)
    print('acc: ', acc)
    f1 = metrics.f1_score(y_test, pred)
    print('f1: ', f1)
    auc = metrics.roc_auc_score(y_test, pred)
    print('auc: ', auc)


from sklearn.ensemble import RandomForestClassifier
def test_nRandomForest(X_train, y_train, X_test, y_test):
    clf = RandomForestClassifier(n_estimators=6)
    clf.fit(X_train, y_train)
    pred = clf.predict(X_test)
    print("RandomForest: ")
    acc = metrics.accuracy_score(y_test, pred)
    print('acc: ', acc)
    f1 = metrics.f1_score(y_test, pred)
    print('f1: ', f1)
    auc = metrics.roc_auc_score(y_test, pred)
    print('auc: ', auc)

测试：

k = 1
for train_index, test_index in kf.split(dataset[0]):
    X_train, X_test = dataset[0][train_index], dataset[0][test_index]
    y_train, y_test = dataset[1][train_index], dataset[1][test_index]
    print('test ', k, ': ')
    test_GaussianNB(X_train, y_train, X_test, y_test)
    test_SVC(X_train, y_train, X_test, y_test)
    test_nRandomForest(X_train, y_train, X_test, y_test)
    print('\n')
    k += 1

结果：

test  1 : 
GaussianNB: 
acc:  0.93
f1:  0.9391304347826087
auc:  0.9242424242424243
SVC: 
acc:  0.93
f1:  0.9380530973451328
auc:  0.9262626262626262
RandomForest: 
acc:  0.93
f1:  0.9369369369369368
auc:  0.9282828282828283


test  2 : 
GaussianNB: 
acc:  0.91
f1:  0.9158878504672897
auc:  0.9089635854341738
SVC: 
acc:  0.94
f1:  0.9423076923076923
auc:  0.9395758303321329
RandomForest: 
acc:  0.95
f1:  0.9514563106796117
auc:  0.9497799119647861


test  3 : 
GaussianNB: 
acc:  0.97
f1:  0.9696969696969697
auc:  0.9701880752300921
SVC: 
acc:  0.91
f1:  0.9052631578947369
auc:  0.9093637454981992
RandomForest: 
acc:  0.93
f1:  0.9263157894736843
auc:  0.9293717486994799


test  4 : 
GaussianNB: 
acc:  0.89
f1:  0.8865979381443299
auc:  0.8914090726615816
SVC: 
acc:  0.91
f1:  0.9072164948453608
auc:  0.9114813327980731
RandomForest: 
acc:  0.93
f1:  0.9263157894736843
auc:  0.930349257326375


test  5 : 
GaussianNB: 
acc:  0.91
f1:  0.9203539823008849
auc:  0.9053945249597423
SVC: 
acc:  0.97
f1:  0.9724770642201834
auc:  0.9690016103059581
RandomForest: 
acc:  0.95
f1:  0.9514563106796117
auc:  0.9537037037037037


test  6 : 
GaussianNB: 
acc:  0.9
f1:  0.8936170212765957
auc:  0.9009661835748792
SVC: 
acc:  0.93
f1:  0.9230769230769231
auc:  0.928743961352657
RandomForest: 
acc:  0.95
f1:  0.945054945054945
auc:  0.9488727858293077


test  7 : 
GaussianNB: 
acc:  0.96
f1:  0.9545454545454546
auc:  0.9594155844155845
SVC: 
acc:  0.96
f1:  0.9545454545454546
auc:  0.9594155844155845
RandomForest: 
acc:  0.98
f1:  0.9767441860465117
auc:  0.9772727272727273


test  8 : 
GaussianNB: 
acc:  0.93
f1:  0.9278350515463919
auc:  0.9335748792270531
SVC: 
acc:  0.93
f1:  0.9278350515463919
auc:  0.9335748792270531
RandomForest: 
acc:  0.96
f1:  0.9574468085106383
auc:  0.9613526570048309


test  9 : 
GaussianNB: 
acc:  0.94
f1:  0.9400000000000001
auc:  0.9403761504601841
SVC: 
acc:  0.95
f1:  0.9494949494949495
auc:  0.9501800720288115
RandomForest: 
acc:  0.95
f1:  0.9494949494949495
auc:  0.9501800720288115


test  10 : 
GaussianNB: 
acc:  0.95
f1:  0.9557522123893805
auc:  0.9480519480519481
SVC: 
acc:  0.94
f1:  0.9464285714285714
auc:  0.9391233766233766
RandomForest: 
acc:  0.96
f1:  0.9636363636363636
auc:  0.9618506493506493

Step5：

通过观察这十个测试，可以知道RandomForest是三个算法中最好的，而SVC差一些，朴素贝叶斯是最差的。