所需數據下載地址：https://www.kaggle.com/c/titanic/data
# -*- coding:utf-8 -*-
import pandas as pd
import numpy as np
from sklearn import preprocessing
titanic_train=pd.read_csv("train.csv")
age_median=titanic_train['Age'].median()
titanic_train["Embarked"] = titanic_train["Embarked"].fillna("S")
titanic_train.loc[titanic_train["Sex"]=="male","Sex"]=0
titanic_train.loc[titanic_train["Sex"]=="female","Sex"]=1
titanic_train.loc[titanic_train["Embarked"]=="C","Embarked"]=-1
titanic_train.loc[titanic_train["Embarked"]=="Q","Embarked"]=0
titanic_train.loc[titanic_train["Embarked"]=="S","Embarked"]=1
titanic_train["Family_size"]=titanic_train["SibSp"]+titanic_train["Parch"]
# titanic_train['Age']=titanic_train['Age'].fillna(age_median)
train_noage=titanic_train[titanic_train["Age"].isnull()]
train_age=titanic_train[-titanic_train["Age"].isnull()]
train_age_features=train_age[["Pclass","Sex","Age","Embarked","Family_size"]]
train_noage_features=train_noage[["Pclass","Sex","Embarked","Family_size"]]
train_age_target=train_age["Survived"]
train_noage_target=train_noage["Survived"]
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import cross_val_score
classifier = LogisticRegression()
scores = cross_val_score(classifier,train_age_features,train_age_target,cv=5) #交叉驗證
# print "包含Age特徵：",scores,scores.mean()
# #
classifier_noage=LogisticRegression()
scores_noage = cross_val_score(classifier_noage,train_noage_features,train_noage_target,cv=5) #交叉驗證
# print "不包含Age特徵：",scores_noage,scores_noage.mean()
titanic_test= pd.read_csv("test.csv")
titanic_gender=pd.read_csv("gender_submission.csv")
titanic_test.loc[titanic_test["Sex"]=="male","Sex"]=0
titanic_test.loc[titanic_test["Sex"]=="female","Sex"]=1
titanic_test.loc[titanic_test["Embarked"]=="C","Embarked"]=-1
titanic_test.loc[titanic_test["Embarked"]=="Q","Embarked"]=0
titanic_test.loc[titanic_test["Embarked"]=="S","Embarked"]=1
titanic_test["Embarked"]=titanic_test["Embarked"].fillna("S")
titanic_test["Family_size"]=titanic_test["SibSp"]+titanic_test["Parch"]
titanic_test["gender"]=titanic_gender["Survived"]
age_test=titanic_test[titanic_test["Age"].notnull()]
noage_test=titanic_test[titanic_test["Age"].isnull()]
age_features=age_test[["Pclass","Sex","Age","Embarked","Family_size"]]
noage_features=noage_test[["Pclass","Sex","Embarked","Family_size"]]
titanic_test["predict"]=''
# 擬合
classifier.fit(train_age_features,train_age_target)
classifier_noage.fit(train_noage_features,train_noage_target)
titanic_test.loc[titanic_test["Age"].isnull(),"predict"]=classifier_noage.predict(noage_features)
titanic_test.loc[titanic_test["Age"].notnull(),"predict"]=classifier.predict(age_features)
acc=1-sum(abs(titanic_test["predict"]-titanic_test["gender"]))*1.0/len(titanic_test)
predicted=titanic_test[["PassengerId","predict"]]
predicted.to_csv('predicted.csv',index=False)
print acc