Xgboost内置建模方式详解一

内置建模方式的特点
1.交叉验证
2.添加预处理的交叉验证
3.自定义损失函数与评估准则
4.只用前n棵树预测

#内置建模方式：交叉验证与高级功能
#添加预处理的交叉验证，自定义损失函数和评估准则，
#!/usr/bin/python
import warnings
warnings.filterwarnings("ignore")
import numpy as np
import pandas as pd
import pickle
import xgboost as xgb
from sklearn.model_selection import train_test_split
from sklearn.externals import joblib


dtrain = xgb.DMatrix('./data/agaricus.txt.train')
dtest = xgb.DMatrix('./data/agaricus.txt.test')
# 基本例子，从csv文件中读取数据，做二分类

# 用pandas读入数据
data = pd.read_csv('./data/Pima-Indians-Diabetes.csv')


# 做数据切分
train, test = train_test_split(data)

# 转换成Dmatrix格式
feature_columns = ['Pregnancies', 'Glucose', 'BloodPressure', 'SkinThickness', 'Insulin', 'BMI', 'DiabetesPedigreeFunction', 'Age']
target_column = 'Outcome'
# 取出numpy array去初始化DMatrix对象
xgtrain = xgb.DMatrix(train[feature_columns].values, train[target_column].values)
xgtest = xgb.DMatrix(test[feature_columns].values, test[target_column].values)

#参数设定
param = {'max_depth':5, 'eta':0.1, 'silent':1, 'subsample':0.7, 'colsample_bytree':0.7, 'objective':'binary:logistic' }

# 设定watchlist用于查看模型状态
watchlist  = [(xgtest,'eval'), (xgtrain,'train')]
num_round = 10
bst = xgb.train(param, xgtrain, num_round, watchlist)

print(xgb.cv(param, dtrain, num_round, nfold=5,metrics={'error'}, seed = 0))

#添加预处理的交叉验证
#计算正负样本比，调整样本权重
def fpreproc(dtrain,dtest,param):
    label = dtrain.get_label()
    ratio = float(np.sum(label == 0)) / np.sum(label == 1)
    param['scale_pos_weight']=ratio
    return (dtrain,dtest,param)

# 先做预处理，计算样本权重，再做交叉验证
print(xgb.cv(param, dtrain, num_round, nfold=5,
       metrics={'auc'}, seed = 0, fpreproc = fpreproc))

#自定义损失函数与评估准则
print("'使用自定义损失函数进行交叉验证")
#自定义损失函数，需要提供损失函数的一阶导和二阶导
def logregobj(preds,dtrain):
    labels = dtrain.get_label()
    preds = 1.0 / (1.0 + np.exp(-preds))
    grad = preds - labels
    hess = preds * (1.0 - preds)
    return grad, hess


# 自定义评估准则，评估预估值和标准答案之间的差距
def evalerror(preds, dtrain):
    labels = dtrain.get_label()
    return 'error', float(sum(labels != (preds > 0.0))) / len(labels)


watchlist = [(dtest, 'eval'), (dtrain, 'train')]
param = {'max_depth': 3, 'eta': 0.1, 'silent': 1}
num_round = 5
# 自定义损失函数训练
bst = xgb.train(param, dtrain, num_round, watchlist, logregobj, evalerror)
# 交叉验证
xgb.cv(param, dtrain, num_round, nfold=5, seed=0,
       obj=logregobj, feval=evalerror)