1.使用隨機森林做預測並繪製ROC曲線

X = train[['Pclass', 'Sex', 'SibSp', 'Parch', 'Cabin', 'Embarked',
       'title', 'isalone', 'Family', 'mother', 'person', 'ticket-same', 'age',
       'fare']]
Y = train['Survived']
#使用隨機森林做預測
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import cross_val_score, train_test_split
from sklearn.metrics import roc_curve, auc
import matplotlib.pyplot as plt
clf = RandomForestClassifier(n_estimators=10, max_depth=None, min_samples_split=2, random_state=0)
clf.fit(X, Y)
scores = cross_val_score(clf, X, Y, cv=5)
print('正確率：', np.mean(scores), scores)
train_x, test_x, train_label, test_label = train_test_split(X, Y, test_size=0.3, random_state= 0)
clf.fit(train_x, train_label)
probas_ = clf.predict_proba(test_x)
fpr, tpr, thresholds = roc_curve(test_label, probas_[:, 1])
roc_auc = auc(fpr, tpr)
plt.plot(fpr, tpr, lw=1, label='ROC (area = %0.2f)' % (roc_auc))
#畫對角線
plt.plot([0, 1], [0, 1], '--', color=(0.6, 0.6, 0.6), label='Luck')
plt.xlim([-0.05, 1.05])
plt.ylim([-0.05, 1.05])
plt.xlabel('False Positive Rate')
plt.ylabel('True Positive Rate')
plt.title('Roc-rf')
plt.legend(loc="lower right")
plt.show()
 

2.使用xgb做預測並繪製ROC曲線

from xgboost import XGBClassifier
clf = XGBClassifier()
clf.fit(X,Y)
scores = cross_val_score(clf, X, Y, cv=5)
print('正確率：', np.mean(scores), scores)
train_x, test_x, train_label, test_label = train_test_split(X, Y, test_size=0.3, random_state= 0)
clf.fit(train_x, train_label)
probas_ = clf.predict_proba(test_x)
fpr, tpr, thresholds = roc_curve(test_label, probas_[:, 1])
roc_auc = auc(fpr, tpr)
plt.plot(fpr, tpr, lw=1, label='ROC (area = %0.2f)' % (roc_auc))
#畫對角線
plt.plot([0, 1], [0, 1], '--', color=(0.6, 0.6, 0.6), label='Luck')
plt.xlim([-0.05, 1.05])
plt.ylim([-0.05, 1.05])
plt.xlabel('False Positive Rate')
plt.ylabel('True Positive Rate')
plt.title('Roc-xgb')
plt.legend(loc="lower right")
plt.show()
 

從ROC曲線來看xgb的效果要好一些。

參考資料https://blog.csdn.net/u010454729/article/details/45098305