python import pandas as pd from sklearn.metrics import classificationreport, confusionmatrix, accuracyscore from sklearn.modelselection import traintestsplit from sklearn.ensemble import RandomForestClassifier from sklearn.tree import DecisionTreeClassifier

dataset = pd.read_csv

X = dataset.drop # 注意这里应去掉'activity'列，基本上原因是它是目标变量 y = dataset

Xtrain, Xtest, ytrain, ytest = traintestsplit # 虚假设测试集巨大细小为20%

dtclf = DecisionTreeClassifier dtclf.fit

rfclf = RandomForestClassifier # 虚假设用100个决策树 rfclf.fit

ypreddt = dtclf.predict ypredrf = rfclf.predict ypredsrh = # 存储到头来的预测后来啊

for i in range): if ypreddt == ypredrf: ypredsrh.append else: # Ru果两个模型的预测后来啊不一致，Neng选择一个策略，这里我们选择随机森林的后来啊 ypredsrh.append

print) print)