机器学习-采用正态贝叶斯分类器、决策树、随机森林对abalone数据集分类

1.abalone（鲍鱼）数据集描述

http://archive.ics.uci.edu/ml/datasets/Abalone

总共包含4177条数据，每条数据中包含8个特征值，一个分类（鲍鱼年龄，看看圈数），可以看做是分类问题或者回归问题

2.数据集预处理

数据的部分展示

Sex / nominal / -- / M, F, and I (infant) 
Length / continuous / mm / Longest shell measurement 
Diameter / continuous / mm / perpendicular to length 
Height / continuous / mm / with meat in shell 
Whole weight / continuous / grams / whole abalone 
Shucked weight / continuous / grams / weight of meat 
Viscera weight / continuous / grams / gut weight (after bleeding) 
Shell weight / continuous / grams / after being dried 
Rings / integer / -- / +1.5 gives the age in years 

M 0.455 0.365 0.095 0.514 0.2245 0.101 0.15 15 M 0.35 0.265 0.09 0.2255 0.0995 0.0485 0.07 7 F 0.53 0.42 0.135 0.677 0.2565 0.1415 0.21 9 M 0.44 0.365 0.125 0.516 0.2155 0.114 0.155 10 I 0.33 0.255 0.08 0.205 0.0895 0.0395 0.055 7

为了便于写程序，我把数据文件中的M、F、I分别替换成1,2,3。（注：为什么要这么做？方便编程而已，有些机器学习库直接读取的话可能会因为数据类型碰到一些问题）

3.代码实例（我采用opencv3.0中的机器学习库来做实验）

#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);
	Ptr<TrainData> data = TrainData::loadFromCSV(filename, 0);
	if (data.empty())
	{ 
		printf("ERROR: File %s can not be read\n", filename);
		return 0;
	}
	data->setTrainTestSplit(train_test_split_ratio);
	
	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 << "============================================" << endl;

	return 0;
}

我们可以通过控制数据集的记录条数来观察不同方法的效果

读10条数据的效果：

读100条数据的效果：

读1000条数据的效果：

读3000条数据的效果：

读4177条数据的效果：

仅从此次试验的运行过程中可以发现，随机森林的分类效果最好，但计算过程比较耗时，随着训练数据量的增大，三者的效果都趋于越来越差。