Weak15 Sklearn Homework

代码：

import 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
dataset = datasets.make_classification(n_samples=1000,n_features=10)
data = dataset[0]
target = dataset[1]
kf = cross_validation.KFold(len(data),n_folds=10,shuffle=True)

先import一堆库，以及生成数据集和kf

GaussianNB：

i = 1
for train_index,test_index in kf:
    x_train,y_train = data[train_index],target[train_index]
    x_test,y_test = data[test_index],target[test_index]
    clf = GaussianNB()
    clf.fit(x_train,y_train)
    pred = clf.predict(x_test)
    print("Group:",i)
    i += 1
    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))

SVC：

for c in [1e-02, 1e-01, 1e00, 1e01, 1e02]:
    i = 1
    for train_index,test_index in kf:
        x_train,y_train = data[train_index],target[train_index]
        x_test,y_test = data[test_index],target[test_index]
        clf = SVC(C=c,kernel='rbf',gamma=0.1)
        clf.fit(x_train,y_train)
        pred = clf.predict(x_test)
        print("Group:",i)
        i += 1
        print("C = ",c)
        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))

截图只截每个C的第一组。





RandomForestClassifier：

for n in [10, 100, 1000]:
    i = 1
    for train_index,test_index in kf:
        x_train,y_train = data[train_index],target[train_index]
        x_test,y_test = data[test_index],target[test_index]
        clf = RandomForestClassifier(n_estimators=n)
        clf.fit(x_train,y_train)
        pred = clf.predict(x_test)
        print("Group:",i)
        i += 1
        print("n_estimators = ",n)
        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))

截图只截每个n_estimators的第一组。



分析：
实验使用相同的数据集，从结果可知随机森林算法的精确度比其他两种算法要高。SVC需要选择适合的参数才能得到一个比较高的精确度。朴素贝叶斯算法比适合参数的SVM略差，但是比其余参数的SVC略好。