机器学习-采用正态贝叶斯分类器、决策树、随机森林对wine数据集分类

 关于wine数据集描述：http://archive.ics.uci.edu/ml/datasets/Wine

#include "opencv2/ml/ml.hpp"
#include "opencv2/core/core.hpp"
#include "opencv2/core/utility.hpp"
#include <stdio.h>
#include <string>
#include <map>
#include <vector>
#include<iostream>

using namespace std;
using namespace cv;
using namespace cv::ml;

static void help()
{
	printf(
		"\nThis sample demonstrates how to use different decision trees and forests including boosting and random trees.\n"
		"Usage:\n\t./tree_engine [-r <response_column>] [-ts type_spec] <csv filename>\n"
		"where -r <response_column> specified the 0-based index of the response (0 by default)\n"
		"-ts specifies the var type spec in the form ord[n1,n2-n3,n4-n5,...]cat[m1-m2,m3,m4-m5,...]\n"
		"<csv filename> is the name of training data file in comma-separated value format\n\n");
}

static void train_and_print_errs(Ptr<StatModel> model, const Ptr<TrainData>& data)
{
	bool ok = model->train(data);
	if (!ok)
	{
		printf("Training failed\n");
	}
	else
	{
		printf("train error: %f\n", model->calcError(data, false, noArray()));
		printf("test error: %f\n\n", model->calcError(data, true, noArray()));
	}
}

int main(int argc, char** argv)
{
	if (argc < 2)
	{
		help();
		return 0;
	}
	const char* filename = 0;
	int response_idx = 0;
	std::string typespec;

	for (int i = 1; i < argc; i++)
	{
		if (strcmp(argv[i], "-r") == 0)
			sscanf(argv[++i], "%d", &response_idx);
		else if (strcmp(argv[i], "-ts") == 0)
			typespec = argv[++i];
		else if (argv[i][0] != '-')
			filename = argv[i];
		else
		{
			printf("Error. Invalid option %s\n", argv[i]);
			help();
			return -1;
		}
	}

	printf("\nReading in %s...\n\n", filename);
	const double train_test_split_ratio = 0.5;
	//加载训练数据
	Ptr<TrainData> data = TrainData::loadFromCSV(filename, 0, response_idx, response_idx + 1, typespec);
	if (data.empty()) 
	{
		printf("ERROR: File %s can not be read\n", filename);
		return 0;
	}

	data->setTrainTestSplitRatio(train_test_split_ratio);
	//预测数据
	float test1[] = { 14.23, 1.71, 2.43, 15.6, 127, 2.8, 3.06, .28, 2.29, 5.64, 1.04, 3.92, 1065 };
	float test2[] = { 12.37, .94, 1.36, 10.6, 88, 1.98, .57, .28, .42, 1.95, 1.05, 1.82, 520 };
	float test3[] = { 12.86, 1.35, 2.32, 18, 122, 1.51, 1.25, .21, .94, 4.1, .76, 1.29, 630 };
	Mat test1Map(1, 13, CV_32FC1, test1);
	Mat test2Map(1, 13, CV_32FC1, test2);
	Mat test3Map(1, 13, CV_32FC1, test3);

	printf("============正太贝叶斯分类器================\n");
	//创建正态贝叶斯分类器
	Ptr<NormalBayesClassifier> bayes = NormalBayesClassifier::create();
	//训练模型
	train_and_print_errs(bayes, data);
	//保存模型
	bayes->save("bayes_result.xml");
	//读取模型，强行使用一下，为了强调这种用法，当然此处完全没必要
	Ptr<NormalBayesClassifier> bayes2 = NormalBayesClassifier::load<NormalBayesClassifier>("bayes_result.xml");
	cout << bayes2->predict(test1Map) << endl;
	cout << bayes2->predict(test2Map) << endl;
	cout << bayes2->predict(test3Map) << endl;
	cout << "============================================" << endl;

	printf("======DTREE=====\n");
	//创建决策树
	Ptr<DTrees> dtree = DTrees::create();
	dtree->setMaxDepth(10);    //设置决策树的最大深度
	dtree->setMinSampleCount(2);  //设置决策树叶子节点的最小样本数
	dtree->setRegressionAccuracy(0);  //设置回归精度
	dtree->setUseSurrogates(false);   //不使用替代分叉属性
	dtree->setMaxCategories(16);   //设置最大的类数量
	dtree->setCVFolds(0);  //设置不交叉验证
	dtree->setUse1SERule(false);  //不使用1SE规则
	dtree->setTruncatePrunedTree(false);  //不对分支进行修剪
	dtree->setPriors(Mat());  //设置先验概率
	train_and_print_errs(dtree, data);
	dtree->save("dtree_result.xml");
	//读取模型，强行使用一下，为了强调这种用法，当然此处完全没必要
	Ptr<DTrees> dtree2 = DTrees::load<DTrees>("dtree_result.xml");
	cout << dtree2->predict(test1Map) << endl;
	cout << dtree2->predict(test2Map) << endl;
	cout << dtree2->predict(test3Map) << endl;
	cout << "============================================" << endl;

	//if ((int)data->getClassLabels().total() <= 2) // regression or 2-class classification problem
	//{
	//	printf("======BOOST=====\n");
	//	Ptr<Boost> boost = Boost::create();
	//	boost->setBoostType(Boost::GENTLE);
	//	boost->setWeakCount(100);
	//	boost->setWeightTrimRate(0.95);
	//	boost->setMaxDepth(2);
	//	boost->setUseSurrogates(false);
	//	boost->setPriors(Mat());
	//	train_and_print_errs(boost, data);
	//}

	printf("======RTREES=====\n");
	Ptr<RTrees> rtrees = RTrees::create();
	rtrees->setMaxDepth(10);
	rtrees->setMinSampleCount(2);
	rtrees->setRegressionAccuracy(0);
	rtrees->setUseSurrogates(false);
	rtrees->setMaxCategories(16);
	rtrees->setPriors(Mat());
	rtrees->setCalculateVarImportance(false);
	rtrees->setActiveVarCount(0);
	rtrees->setTermCriteria(TermCriteria(TermCriteria::MAX_ITER, 100, 0));
	train_and_print_errs(rtrees, data);

	cout << rtrees->predict(test1Map) << endl;
	cout << rtrees->predict(test2Map) << endl;
	cout << rtrees->predict(test3Map) << endl;
	cout << "============================================" << endl;

	return 0;
}

此处可以看出，对于wine数据集的分类，效果比较   rtress > dtree > normalbayes

wine数据集包含为178条数据