决策树---预测泰坦尼克号的生存

决策树---预测泰坦尼克号的生存

#!/usr/bin/python
# -*- coding:utf-8 -*-

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.feature_extraction import DictVectorizer
from sklearn.tree import DecisionTreeClassifier

def mydesiontree():
    '''
    决策树预测泰坦尼克号的生死
    :return:
    '''
    data=pd.read_csv("http://biostat.mc.vanderbilt.edu/wiki/pub/Main/DataSets/titanic.txt")
    # print(data.columns)
    x=data[['pclass','age','sex']]
    y=data['survived']
    x['age'].fillna(x['age'].mean(),inplace=True)
    print(x['age'])
    x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.25,random_state=34)
    dictver=DictVectorizer(sparse=False)
    x_train=dictver.fit_transform(x_train.to_dict(orient="records"))
    print(dictver.get_feature_names())

    x_test=dictver.fit_transform(x_test.to_dict(orient="records"))
    decisiontree=DecisionTreeClassifier()
    decisiontree.fit(x_train,y_train)
    y_predict=decisiontree.predict(x_test)
    print("预测结果：",y_predict)
    print("预测准确率：",decisiontree.score(x_test,y_test))

    pass
if __name__ == '__main__':
    print("hello")
    mydesiontree()