xgboost入门以及windows下安装及使用二

来源：互联网发布：做淘宝刷客的被骗报警编辑：程序博客网时间：2024/06/02 05:55

如果看到上篇，xgboost没有安装成功的可以提问我，本文主要讲xgboost的测试例子，例子模仿别人的，但补充了很多，希望能帮到更多人！

import sys,ossys.path.append('E:\\xgboost-master\\xgboost-master\\wrapper')import numpy as npimport scipy.sparseimport xgboost as xgbdtrain = xgb.DMatrix('E:\\my-train.txt');dtest = xgb.DMatrix('E:\\my-test.txt');param = {'max_depth':6, 'eta':0.3, 'silent':1, 'objective':'binary:logistic'}watchlist  = [(dtest,'eval'), (dtrain,'train')]  num_round = 20  bst = xgb.train(param, dtrain, num_round, watchlist)    # this is prediction  preds = bst.predict(dtest)  labels = dtest.get_label()  print ('error=%f' % (  sum(1 for i in range(len(preds)) if int(preds[i]>0.5)!=labels[i]) /float(len(preds))))  bst.save_model('C:\\xgb.model')

我把xgboost放到E盘，简单测试了两个文件：

my-train.txt

1 1:1 2:1 3:1 4:11 1:2 2:2 3:2 4:21 1:3 2:3 3:3 4:31 1:4 2:4 3:4 4:41 1:5 2:5 3:5 4:51 1:6 2:6 3:6 4:60 1:62 2:32 3:24 4:260 1:39 2:73 3:93 4:350 1:41 2:43 3:42 4:430 1:5 2:35 3:52 4:530 1:64 2:16 3:46 4:36

my-test.txt

1 1:5 2:5 3:5 4:51 1:6 2:6 3:6 4:60 1:62 2:32 3:24 4:260 1:39 2:73 3:93 4:350 1:41 2:43 3:42 4:43

运行结果：

Error when loading sklearn/plotting. Please install scikit-learn
error=0.000000
11x5 matrix with 44 entries is loaded from E:\my-train.txt
5x5 matrix with 20 entries is loaded from E:\my-test.txt
[0] eval-error:0.000000train-error:0.000000
[1] eval-error:0.000000train-error:0.000000
[2] eval-error:0.000000train-error:0.000000
[3] eval-error:0.000000train-error:0.000000
[4] eval-error:0.000000train-error:0.000000
[5] eval-error:0.000000train-error:0.000000
[6] eval-error:0.000000train-error:0.000000
[7] eval-error:0.000000train-error:0.000000
[8] eval-error:0.000000train-error:0.000000
[9] eval-error:0.000000train-error:0.000000
[10] eval-error:0.000000train-error:0.000000
[11] eval-error:0.000000train-error:0.000000
[12] eval-error:0.000000train-error:0.000000
[13] eval-error:0.000000train-error:0.000000
[14] eval-error:0.000000train-error:0.000000
[15] eval-error:0.000000train-error:0.000000
[16] eval-error:0.000000train-error:0.000000
[17] eval-error:0.000000train-error:0.000000
[18] eval-error:0.000000train-error:0.000000
[19] eval-error:0.000000train-error:0.000000

预测代码，先加载模型和数据，然后进行预测。

#! /usr/bin/env python#coding=utf-8import sys,os  sys.path.append('E:\\xgboost-master\\xgboost-master\\wrapper')    import numpy as np  import scipy.sparse  import xgboost as xgb      dtest2 = xgb.DMatrix('E:\\my-test2.txt')  bst2 = xgb.Booster(model_file='C:\\xgb.model')  preds2 = bst2.predict(dtest2)  print preds2# this is prediction  outing = open('C:\\Result.txt', 'w')  outing.write(str(int(preds2[0]>0.5))) #只输出了一个  outing.close()

my-test2:

1 1:15 2:15 3:15 4:151 1:6 2:6 3:6 4:61 1:16 2:16 3:16 4:160 1:62 2:32 3:24 4:260 1:39 2:73 3:93 4:350 1:411 2:43 3:42 4:43

输出结果：

[ 0.26937994  0.77472818  0.26937994  0.26937994  0.26937994  0.26937994]6x5 matrix with 24 entries is loaded from E:\my-test2.txt

1 0