【机器学习】集成学习之xgboost的sklearn版XGBClassifier使用教程

      XGBClassifier是xgboost的sklearn版本。代码完整的展示了使用xgboost建立模型的过程，并比较xgboost和randomForest的性能。

# -*- coding: utf-8 -*-
"""
# 作者：wanglei5205
# 邮箱：wanglei5205@126.com
# 博客：http://cnblogs.com/wanglei5205
# github：http://github.com/wanglei5205
"""
### 导入模块
import pandas as pd

### load_data
titanic = pd.read_csv('http://biostat.mc.vanderbilt.edu/wiki/pub/Main/DataSets/titanic.txt')
X = titanic[['pclass', 'age', 'sex']]     # 输入空间
y = titanic['survived']                   # 输出空间
X.age.fillna(X.age.mean(), inplace=True)  # 填充缺失值（均值），inplace=True(无返回值，原地替换）

### split_data
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)

### feature_extraction
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'))

### create_model
# rfc
from sklearn.ensemble import RandomForestClassifier
rfc = RandomForestClassifier()
rfc.fit(X_train, y_train)

# xgbc
from xgboost import XGBClassifier
xgbc = XGBClassifier()
xgbc.fit(X_train, y_train)

### model_score
print ('rfc.score=',rfc.score(X_test, y_test))
print('xgbc.score=',xgbc.score(X_test, y_test))
"""
rfc.score= 0.787234042553
xgbc.score= 0.787234042553
"""