update regression

Author: tqchen

README.md

@@ -2,11 +2,12 @@ xgboost: eXtreme Gradient Boosting
 =======
 A General purpose gradient boosting (tree) library.
 
-Creater: Tianqi Chen
+Authors:
+* Tianqi Chen, project creater
+* Kailong Chen, contributes regression module
 
 Turorial and Documentation: https://github.com/tqchen/xgboost/wiki
 
-
 Features
 =======
 * Sparse feature format:
@@ -37,4 +38,3 @@ File extension convention
 * .h are interface, utils and data structures, with detailed comment; 
 * .cpp are implementations that will be compiled, with less comment; 
 * .hpp are implementations that will be included by .cpp, with less comment
-

demo/binary_classification/dump2json.py

@@ -1,17 +1,27 @@
-# General Parameters
-booster_type = 0
-loss_type = 2
+# General Parameters, see comment for each definition
+# choose the tree booster, 0: tree, 1: linear
+booster_type = 0 
+# choose logistic regression loss function for binary classification
+loss_type = 2 
 
 # Tree Booster Parameters
-bst:tree_maker=2
-bst:eta=1.0
-bst:gamma=1.0
-bst:min_child_weight=1   
-bst:max_depth=3           
+# step size shrinkage
+bst:eta = 1.0 
+# minimum loss reduction required to make a further partition
+bst:gamma = 1.0 
+# minimum sum of instance weight(hessian) needed in a child
+bst:min_child_weight = 1 
+# maximum depth of a tree
+bst:max_depth = 3 
 
-# Binary Classification Parameters
-num_round=2
-save_period=0
-data = "agaricus.txt.train"
-eval[test] = "agaricus.txt.test"
-test:data =  "agaricus.txt.test"
+# Task Parameters
+# the number of round to do boosting
+num_round = 2
+# 0 means do not save any model except the final round model
+save_period = 0 
+# The path of training data
+data = "agaricus.txt.train" 
+# The path of validation data, used to monitor training process, here [test] sets name of the validation set
+eval[test] = "agaricus.txt.test" 
+# The path of test data 
+test:data = "agaricus.txt.test"      

demo/binary_classification/mushroom.conf

@@ -0,0 +1,30 @@
+# General Parameters, see comment for each definition
+# choose the tree booster, 0: tree, 1: linear
+booster_type = 0 
+# this is the only difference with classification, use 0: linear regression
+# when labels are in [0,1] we can also use 1: logistic regression
+loss_type = 0
+
+# Tree Booster Parameters
+# step size shrinkage
+bst:eta = 1.0 
+# minimum loss reduction required to make a further partition
+bst:gamma = 1.0 
+# minimum sum of instance weight(hessian) needed in a child
+bst:min_child_weight = 1 
+# maximum depth of a tree
+bst:max_depth = 3 
+
+# Task parameters
+# the number of round to do boosting
+num_round = 2
+# 0 means do not save any model except the final round model
+save_period = 0 
+# The path of training data
+data = "machine.txt.train" 
+# The path of validation data, used to monitor training process, here [test] sets name of the validation set
+eval[test] = "machine.txt.test" 
+# The path of test data 
+test:data = "machine.txt.test"      
+
+

demo/regression/dump2json.py

@@ -19,5 +19,3 @@
     fo.write('\n')
 
 fo.close()
-
- 

demo/regression/machine.conf

@@ -6,6 +6,6 @@ python mknfold.py machine.txt 1
 # training and output the models
 ../../xgboost machine.conf
 # output predictions of test data
-../../xgboost machine.conf task=pred model_in=0003.model
-# print the boosters of 00003.model in dump.raw.txt
-../../xgboost machine.conf task=dump model_in=0003.model name_dump=dump.raw.txt 
+../../xgboost machine.conf task=pred model_in=0002.model
+# print the boosters of 00002.model in dump.raw.txt
+../../xgboost machine.conf task=dump model_in=0002.model name_dump=dump.raw.txt