XGBoost 模型（分类）

import pandas as pd
titanic=pd.read_csv('http://biostat.mc.vanderbilt.edu/wiki/pub/Main/DataSets/titanic.txt')
X=titanic[['pclass','age','sex']]
y=titanic['survived']
X['age'].fillna(X['age'].mean(),inplace=True)
from sklearn.cross_validation import train_test_split
X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.25,random_state=33)

#处理类别特征向量
from sklearn.feature_extraction import DictVectorizer
vec=DictVectorizer(sparse=False)
X_train=vec.fit_transform(X_train.to_dict(orient='record'))
X_test=vec.transform(X_test.to_dict(orient='record'))

#随机森林
from sklearn.ensemble import RandomForestClassifier
rfc=RandomForestClassifier()
rfc.fit(X_train,y_train)
print('随机森林的accuracy:',rfc.score(X_test,y_test))
#随机森林的accuracy: 0.78419452887538

#XGBoost
from xgboost import XGBClassifier
xgbc=XGBClassifier()
xgbc.fit(X_train,y_train)
print('xgb的accuracy:',xgbc.score(X_test,y_test))
#xgb的accuracy: 0.7872340425531915