学习笔记：用决策树预测泰坦尼克号伤亡情况

# -*- coding: utf-8 -*-
"""
Created on Mon May 14 09:29:48 2018

@author: eagle
"""

# =============================================================================
# 用决策树预测泰坦尼克号伤亡情况
# =============================================================================

import pandas as pd
from sklearn.cross_validation import train_test_split
from sklearn.feature_extraction import DictVectorizer
from sklearn.tree import DecisionTreeClassifier
from sklearn.metrics import classification_report

#读取数据
titanic = pd.read_csv('http://biostat.mc.vanderbilt.edu/wiki/pub/Main/DataSets/titanic.txt')
#titanic.head()
#titanic.info()   #共1313条信息

#选取特征
X = titanic[['pclass','age','sex']]
y = titanic['survived']
#X.info()
X['age'].fillna(X['age'].mean(),inplace = True)     #用中位数填充

#数据分割
X_train,X_test,y_train,y_test = train_test_split(X,y,test_size = 0.25,random_state = 33)


#特征转换
vec=DictVectorizer(sparse=False)
X_train=vec.fit_transform(X_train.to_dict(orient='record'))
#print(vec.feature_names_)
X_test=vec.transform(X_test.to_dict(orient='record'))

#用决策树进行预测
dtc=DecisionTreeClassifier()
#训练
dtc.fit(X_train,y_train)
#预测
y_predict=dtc.predict(X_test)

#评价
print('The Accuracy of DecisionTree is:',dtc.score(X_test,y_test))
print(classification_report(y_test,y_predict,target_names=['died','survived']))