kaggle 入门 digit recognizer Python xgboost

# coding:utf-8
import numpy

__author__ = 'WHP'
__mtime__ = '2016/5/12'
__name__ = ''

import xgboost
import pandas
import time

now = time.time()

dataset = pandas.read_csv("...input\\train.csv")
trainData = dataset.iloc[:, 1:].values
labelData = dataset.iloc[:, :1].values
testData = pandas.read_csv("...input\\test.csv")
test = testData.iloc[:, :].values
#参数列表 http://xgboost.readthedocs.io/en/latest/parameter.html param = {"booster": "gbtree", "max_depth": 12, "eta": 0.03, "seed": 710, "objective": "multi:softmax", "num_class": 10,
"gamma": 0.03}

offset = 35000   <span style="font-size: 13.3333339691162px; font-family: Arial, Helvetica, sans-serif;">#分割点 将原数据一部分作为训练集 一部分作为验证集</span>
num_rounds = 500 #最大迭代次数
#数据转换为DMatrix矩阵 此格式为xgboost接受格式
xgtest = xgboost.DMatrix(test)
xgtrain = xgboost.DMatrix(trainData[:offset, :], label=labelData[:offset])
xgeval = xgboost.DMatrix(trainData[offset:, :], label=labelData[offset:])

watchlist = [(xgtrain, 'train'), (xgeval, 'val')]
#进行模型拟合  官方函数列表 http://xgboost.readthedocs.io/en/latest/python/python_api.html model = xgboost.train(list(param.items()), xgtrain, num_rounds, watchlist, early_stopping_rounds=100)
#根据模型 进行预测
preds = model.predict(xgtest, ntree_limit=model.best_iteration)

numpy.savetxt('submission_xgb_MultiSoftmax.csv', numpy.c_[range(1, len(testData) + 1), preds], delimiter=',',
header='ImageId,Label', comments='', fmt='%d')

print("cost time:", time.time() - now)