mlpack 训练随机森林分类模型，并保存、加载网络，预测结果

mlpack 是一个C++的机器学习库，它重点在于其扩展性、高速性和易用性。它的目的是让新用户通过简单、一致的API使用机器学习，同时为专业用户提供C++的高性能和最大灵活性。他的性能超出大量类似的机器学习库，如WEKA、Shogun、MATLAB、mlpy及sklearn,适合机器学习算法的工程化

以下代码示例了mlpack 训练随机森林分类模型，并保存、加载网络，预测结果

#include "mlpack/core.hpp"
#include "mlpack/methods/random_forest/random_forest.hpp"
#include "mlpack/methods/decision_tree/random_dimension_select.hpp"
#include "mlpack/core/cv/k_fold_cv.hpp"
#include "mlpack/core/cv/metrics/accuracy.hpp"
#include "mlpack/core/cv/metrics/precision.hpp"
#include "mlpack/core/cv/metrics/recall.hpp"
#include "mlpack/core/cv/metrics/F1.hpp"

using namespace arma;
using namespace mlpack;
using namespace mlpack::tree;
using namespace mlpack::cv;


int  main()
{
	mat dataset;
	bool loaded = mlpack::data::Load("D:/MLPackProject/data/german.csv", dataset);
	if (!loaded)
		return -1;

	Row<size_t> labels;
	labels = conv_to<Row<size_t>>::from(dataset.row(dataset.n_rows - 1));
	dataset.shed_row(dataset.n_rows - 1);

	const size_t numClasses = 2;
	const size_t minimumLeafSize = 5;
	const size_t numTrees = 10;
	RandomForest<GiniGain, RandomDimensionSelect> rf;
	rf = RandomForest<GiniGain, RandomDimensionSelect>(dataset, labels,
		numClasses, numTrees, minimumLeafSize);

	Row<size_t> predictions;
	rf.Classify(dataset, predictions);
	const size_t correct = arma::accu(predictions == labels);
	cout << "\nTraining Accuracy: " << (double(correct) / double(labels.n_elem));

	// Instead of training the Random Forest directly, we could also use K-fold cross-validation
	//for training, which will give us a measure of performance on a held-out test set. This can give
	//us a better estimate of how the model will perform when given new data. We also define which metric 
	//to use in order to assess the quality of the trained model.
	const size_t k = 10;
	KFoldCV<RandomForest<GiniGain, RandomDimensionSelect>, Accuracy> cv(k,
		dataset, labels, numClasses);
	double cvAcc = cv.Evaluate(numTrees, minimumLeafSize);
	cout << "\nKFoldCV Accuracy: " << cvAcc;
	
	//To compute other relevant metrics, such as Precision, Recall and F1:
	double cvPrecision = Precision<Binary>::Evaluate(rf, dataset, labels);
	cout << "\nPrecision: " << cvPrecision;
	double cvRecall = Recall<Binary>::Evaluate(rf, dataset, labels);
	cout << "\nRecall: " << cvRecall;
	double cvF1 = F1<Binary>::Evaluate(rf, dataset, labels);
	cout << "\nF1: " << cvF1;

	//Saving the model
	mlpack::data::Save("mymodel.xml", "model", rf, false);

	//Loading the model
	mlpack::data::Load("mymodel.xml", "model", rf);

	// Create a test sample containing only one point.  Because Armadillo is
	// column-major, this matrix has one column (one point) and the number of rows
	// is equal to the dimensionality of the point (23).
	mat sample("2; 12; 2; 13; 1; 2; 2; 1; 3; 24; 3; 1; 1; 1; 1; 1; 0; 1; 0; 1;"
		" 0; 0; 0");
	mat probabilities;
	rf.Classify(sample, predictions, probabilities);
	u64 result = predictions.at(0);
	cout << "\nClassification result: " << result << " , Probabilities: " <<
		probabilities.at(0) << "/" << probabilities.at(1);
}