Sklearn习题 [python]

最新推荐文章于 2024-05-16 11:37:17 发布

原创最新推荐文章于 2024-05-16 11:37:17 发布 · 500 阅读

0 ·

本内容遵循CC 4.0 BY-SA版权协议

本文通过一道具体的习题，深入探讨了使用Python的Sklearn库进行机器学习操作的方法。通过代码实现，展示了如何运用Sklearn进行数据处理和模型训练，并得到了相应的输出结果。

题目：

代码：

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)  
kf = cross_validation.KFold(len(dataset[0]), 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)

print("GaussianNB:")
acc = metrics.accuracy_score(y_test, pred)
print('Accuracy:', acc)
f1 = metrics.f1_score(y_test, pred)
print('F1_score:', f1)
auc = metrics.roc_auc_score(y_test, pred)
print('ACU ROC:', auc)
print("")

print("SVC")
for C in [1e-02, 1e-01, 1e00, 1e01, 1e02]:
    clf = SVC(C, kernel='rbf', gamma=0.1)
    clf.fit(X_train, y_train)
    pred = clf.predict(X_test)
    
    print(str(C)+":")
    acc = metrics.accuracy_score(y_test, pred)
    print('Accuracy:', acc)
    f1 = metrics.f1_score(y_test, pred)
    print('F1_score:', f1)
    auc = metrics.roc_auc_score(y_test, pred)
    print('ACU ROC:', auc)
print("")

print("RandomForestClassifier:")
for n_estimators in [10, 100, 1000]:
    clf = RandomForestClassifier(n_estimators)
    clf.fit(X_train, y_train)
    pred = clf.predict(X_test)

    print(str(n_estimators) + ":")
    acc = metrics.accuracy_score(y_test, pred)
    print('Accuracy:', acc)
    f1 = metrics.f1_score(y_test, pred)
    print('F1_score:', f1)
    auc = metrics.roc_auc_score(y_test, pred)
    print('ACU ROC:', auc)

输出：