From c5ada79be574f8e9cce91f0c099134b5156d6ad4 Mon Sep 17 00:00:00 2001
From: kalenhaha <chenkl198812@gmail.com>
Date: Mon, 10 Feb 2014 23:40:38 +0800
Subject: [PATCH] gbrt implemented

---
 booster/gbrt.h                           | 82 ++++++++++++++++++++++++
 booster/xgboost_regression_data_reader.h | 76 ++++++++++++++++++++++
 2 files changed, 158 insertions(+)
 create mode 100644 booster/gbrt.h
 create mode 100644 booster/xgboost_regression_data_reader.h

diff --git a/booster/gbrt.h b/booster/gbrt.h
new file mode 100644
index 000000000..6046364ea
--- /dev/null
+++ b/booster/gbrt.h
@@ -0,0 +1,82 @@
+#ifndef _GBRT_H_
+#define _GBRT_H_
+
+#include "../utils/xgboost_config.h"
+#include "xgboost_regression_data_reader.h"
+#include "xgboost_gbmbase.h"
+#include <math.h>
+using namespace xgboost::utils;
+using namespace xgboost::booster;
+
+class gbrt{
+
+public:
+	gbrt(const char* config_path){
+		ConfigIterator config_itr(config_path);
+		while(config_itr.Next()){
+			SetParam(config_itr.name,config_itr.val);
+			base_model.SetParam(config_itr.name,config_itr.val);
+		}
+	}
+
+	void SetParam( const char *name, const char *val ){
+		param.SetParam(name, val);
+	}
+
+	void train(){
+		xgboost_regression_data_reader data_reader(param.train_file_path);
+		base_model.InitModel();
+		base_model.InitTrainer();
+		std::vector<float> grad,hess;
+		std::vector<unsigned> root_index;
+		int instance_num = data_reader.InsNum();
+		float label = 0,pred_transform = 0;
+		grad.resize(instance_num); hess.resize(instance_num);
+		for(int i = 0; i < 100; i++){
+			grad.clear();hess.clear();
+			for(int j = 0; j < instance_num; j++){
+				label = data_reader.GetLabel(j);
+				pred_transform = Logistic(base_model.Predict(data_reader.GetLine(j)));
+				grad.push_back(FirstOrderGradient(pred_transform,label));
+				hess.push_back(SecondOrderGradient(pred_transform));
+			}
+			base_model.DoBoost(grad,hess,data_reader.GetImage(),root_index );
+		}
+	}
+
+	struct GBRTParam{
+
+		/*! \brief path of input training data */
+		const char* train_file_path;
+
+		GBRTParam( void ){
+		}
+		/*! 
+		* \brief set parameters from outside 
+		* \param name name of the parameter
+		* \param val  value of the parameter
+		*/
+		inline void SetParam( const char *name, const char *val ){
+			if( !strcmp("train_file_path", name ) )  train_file_path = val;
+		}
+	};
+
+private:
+	inline float FirstOrderGradient(float pred_transform,float label){
+		return label - pred_transform;
+	}
+
+	inline float SecondOrderGradient(float pred_transform){
+		return pred_transform * ( 1 - pred_transform );
+	}
+
+	inline float Logistic(float x){
+		return 1.0/(1.0 + exp(-x));
+	}
+
+	GBMBaseModel base_model;	
+	GBRTParam param;
+
+};
+
+#endif
\ No newline at end of file
diff --git a/booster/xgboost_regression_data_reader.h b/booster/xgboost_regression_data_reader.h
new file mode 100644
index 000000000..13c7b0d8d
--- /dev/null
+++ b/booster/xgboost_regression_data_reader.h
@@ -0,0 +1,76 @@
+#include"xgboost_data.h"
+#include<stdio.h>
+#include<vector>
+
+using namespace xgboost::booster;
+/*!
+ * \file xgboost_gbmbase.h
+ * \brief A reader to read the data for regression task from a specified file
+ *        The data should contain each data instance in each line.
+ *		  The format of line data is as below:
+ *        label nonzero feature dimension[ feature index:feature value]+
+ * \author Kailong Chen: chenkl198812@gmail.com
+ */
+
+class xgboost_regression_data_reader{
+
+public:
+	xgboost_regression_data_reader(const char* file_path){
+		Load(file_path);
+	}
+
+	void Load(const char* file_path){
+		data_matrix.Clear();
+		FILE* file = fopen(file_path,"r");
+		if(file == NULL){
+			printf("The file is missing at %s",file_path);
+			return;
+		}
+		float label;
+		int nonzero_dimension,index,value,num_row = 0;
+		std::vector<bst_uint> findex;
+		std::vector<bst_float> fvalue;
+	
+		while(fscanf(file,"%f %i",label,nonzero_dimension)){
+			findex.clear();
+			fvalue.clear();
+			findex.resize(nonzero_dimension);
+			fvalue.resize(nonzero_dimension);
+			for(int i = 0; i < nonzero_dimension; i++){
+				if(!fscanf(file," %i:%f",index,value)){
+					printf("The feature dimension is not coincident \
+						with the indicated one");
+					return;
+				}
+				findex.push_back(index);
+				fvalue.push_back(value);
+			}
+			data_matrix.AddRow(findex, fvalue);
+			labels.push_back(label);
+			num_row++;
+		}
+		printf("%i rows of data is loaded from %s",num_row,file_path);
+		fclose(file);
+	}
+
+	
+	float GetLabel(int index){
+		return labels[index];
+	}
+
+	FMatrixS::Line GetLine(int index){
+		return data_matrix[index];
+	}
+
+	int InsNum(){
+		return labels.size();
+	}
+
+	FMatrixS::Image GetImage(){
+		return FMatrixS::Image(data_matrix);
+	}
+
+private:
+	FMatrixS data_matrix;
+	std::vector<float> labels;
+};
\ No newline at end of file