高编作业（十二）

Sklearn作业

作业截图

代码

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
# 得到数据集
dataset = datasets.make_classification(n_samples=2000, n_features=15,
n_repeated=0, n_classes=2)

X, Y = dataset[0], dataset[1]
kf = cross_validation.KFold(len(Y), n_folds=10, shuffle=True) # 交叉检验划分
num = 1
for train_index, test_index in kf:
    X_train, y_train = X[train_index], Y[train_index]
    X_test, y_test = X[test_index], Y[test_index]

    print("Test%d:"%num)
    # 朴素贝叶斯
    print("Naive Bayes：")
    clf = GaussianNB()
    clf.fit(X_train, y_train)
    pred = clf.predict(X_test)
    print("Accuracy：", metrics.accuracy_score(y_test, pred))
    print("F1-score:", metrics.f1_score(y_test, pred))
    print("AUC ROC:",metrics.roc_auc_score(y_test, pred))

    # 支持向量机
    print("SVM：")
    clf = SVC(C=1e-01, kernel='rbf', gamma=0.1)
    clf.fit(X_train, y_train)
    pred = clf.predict(X_test)
    print("Accuracy：", metrics.accuracy_score(y_test, pred))
    print("F1-score:", metrics.f1_score(y_test, pred))
    print("AUC ROC:",metrics.roc_auc_score(y_test, pred))

    # 随机森林
    print("Random Forest：")
    clf = RandomForestClassifier(n_estimators=100)
    clf.fit(X_train, y_train)
    pred = clf.predict(X_test)
    print("Accuracy：", metrics.accuracy_score(y_test, pred))
    print("F1-score:", metrics.f1_score(y_test, pred))
    print("AUC ROC:",metrics.roc_auc_score(y_test, pred))

    print()
    num += 1

结果截图

（共有十次测试，此处只放出四次的结果截图）
根据截图可知，在二分类问题中，对于相同的数据集，随机森林算法的效果比朴素贝叶斯和支持向量机的效果要好