python机器学习之用决策树处理泰坦尼克号数据

首先需要引入需要的类

from sklearn.tree import DecisionTreeClassifier,export_graphviz
from sklearn.feature_extraction import DictVectorizer

from sklearn.model_selection import train_test_split

然后写入函数tree_titanic()

def tree_titanic():
    path="E:\data\\titanic.csv" #注意此处‘\t’会被认为是特殊字符，需要加两个‘\’
    titanic=pd.read_csv(path)
    print("type(titanic):",type(titanic))
    #1.处理特征值和目标值
    x=titanic[["pclass","age","sex"]]#注意此处DataFrame选用多个列的时候，要用两个中括号“[]”
    print(x)
    y=titanic["survived"]
    print(y)
   # print("x1:",x,type(x))
    #2.特征值处理
   # （1）缺失值处理
    x["age"].fillna(x["age"].mean(), inplace=True)#注意此处我刚开始时犯了一个错误，好长时间才找到，是mean(),而不是mean
  #  print("x2:", x)
   #  #(2)转化成字典
    x=x.to_dict(orient="records")
    print("x3:", x)
    # #3.数据集划分
    x_train, x_test, y_train, y_test=train_test_split(x, y, random_state=22)
    # print(x_train)
    # #4.字典特征抽取
    transfer=DictVectorizer()
    x_train= transfer.fit_transform(x_train)
    x_test=transfer.transform(x_test)
    #5.决策树预估器
    estimator=DecisionTreeClassifier(criterion="entropy")
    estimator.fit(x_train,y_train)
    #6.模型评估
    #（1）方法1：直接比对真实值和预测值
    y_predict = estimator.predict(x_test)
    print("y_predict:\n", y_predict)
    print("直接比对真实值和预测值：\n", y_test == y_predict)
    # （2）.计算准确率
    score = estimator.score(x_test, y_test)
    print("准确率为：\n", score)
    #7.可视化决策树
    export_graphviz(estimator, out_file="titanic_tree.dot", feature_names=transfer.get_feature_names())
    return  None

结果为：