使用adaboost做Kaggle中Titanic

这里测试了使用adaboost的效果，代码如下：

#coding=utf-8
import pandas as pd
from pandas import Series,DataFrame 
import random
import numpy as np
from datetime import date
import datetime as dt
from numpy import nan as NA
from sklearn.tree import DecisionTreeRegressor  
from sklearn.ensemble import RandomForestRegressor  
from sklearn.ensemble import RandomForestClassifier
from sklearn.ensemble import GradientBoostingRegressor

import warnings
warnings.filterwarnings("ignore")

#读取数据
traindata = pd.read_csv("train.csv",header=0)
testdata = pd.read_csv("test.csv",header=0)

traindata.Age[traindata.Age.isnull()] = 30
print(traindata.Age.describe())
testdata.Age[testdata.Age.isnull()] = 30
print(testdata.Age.describe())

#新加一列，儿童，年轻还是老年人
traindata['Age1'] = 1
testdata['Age1'] = 1
traindata.Age1[traindata.Age<12] = 0
testdata.Age1[testdata.Age<12] = 0
traindata.Age1[traindata.Age>50] = 2
testdata.Age1[testdata.Age>50] = 2

#新加一列，是否人多
traindata['Parch1'] = 0
testdata['Parch1'] = 0
traindata.Parch1[traindata.Parch>1] = 1
testdata.Parch1[testdata.Parch>1] = 1

print(traindata.describe())

traindata.Sex[traindata.Sex=='male'] = 0
traindata.Sex[traindata.Sex=='female'] = 1
print(traindata.Sex.describe())
testdata.Sex[testdata.Sex=='male'] = 0
testdata.Sex[testdata.Sex=='female'] = 1
print(testdata.Sex.describe())

testdata.Fare[testdata.Fare.isnull()]=35
print(testdata.Fare.describe())

UseFlag = traindata['Survived'].values
UseFeature = traindata[['Pclass','Sex','Age','SibSp','Parch','Fare','Age1','Parch1']].values

from sklearn import preprocessing
scaler = preprocessing.StandardScaler().fit(UseFeature)
scaler.transform(UseFeature)

TestFeature = testdata[['Pclass','Sex','Age','SibSp','Parch','Fare','Age1','Parch1']].values
scaler.transform(TestFeature)

from sklearn.ensemble import AdaBoostClassifier  
clf = AdaBoostClassifier(n_estimators=100) #迭代100次  
clf.fit(UseFeature,UseFlag)#进行模型的训练  

temp = clf.predict(TestFeature)

testdata['tadaboost']=temp
temp = clf.predict(TestFeature)

testdata['Survived']=0
testdata.Survived = testdata.tadaboost
testdata.Survived = testdata.Survived.astype(int)

outdata = testdata[['PassengerId','Survived']]#提取出需要的列
outdata.to_csv("test_2018_2_26_adaboost.csv",index=False,header=True)#保存数据集

最终结果：0.74162