add python interface for xgboost

.gitignore

@@ -17,3 +17,4 @@
 *buffer
 *model
 xgboost
+*pyc

python/README.md

@@ -1,2 +1,4 @@
-beta version:
 python wrapper for xgboost using ctypes
+
+see example for usage
+

python/example/README.md

@@ -0,0 +1,3 @@
+example to use python xgboost, the data is generated from demo/binary_classification, in libsvm format
+
+for usage: see demo.py and comments in demo.py

python/example/demo.py

@@ -0,0 +1,74 @@
+#!/usr/bin/python
+import sys
+import scipy.sparse
+# append the path to xgboost
+sys.path.append('../')
+import xgboost as xgb
+
+### simple example
+# load file from text file, also binary buffer generated by xgboost
+dtrain = xgb.DMatrix('agaricus.txt.train')
+dtest = xgb.DMatrix('agaricus.txt.test')
+
+# specify parameters via map, definition are same as c++ version
+param = {'bst:max_depth':4, 'bst:eta':1, 'silent':1, 'loss_type':2 }
+
+# specify validations set to watch performance
+evallist  = [(dtest,'eval'), (dtrain,'train')]
+num_round = 2
+bst = xgb.train( param, dtrain, num_round, evallist )
+
+# this is prediction
+preds = bst.predict( dtest )
+labels = dtest.get_label()
+print 'error=%f' % (  sum(1 for i in xrange(len(preds)) if int(preds[i]>0.5)!=labels[i]) /float(len(preds)))
+bst.save_model('0001.model')
+
+
+###
+# build dmatrix in python iteratively
+#
+print 'start running example of build DMatrix in python'
+dtrain = xgb.DMatrix()
+labels = []
+for l in open('agaricus.txt.train'):
+    arr = l.split()
+    labels.append( int(arr[0]))
+    feats = []
+    for it in arr[1:]:
+        k,v = it.split(':')
+        feats.append( (int(k), float(v)) )
+    dtrain.add_row( feats )
+dtrain.set_label( labels )
+evallist  = [(dtest,'eval'), (dtrain,'train')]
+
+bst = xgb.train( param, dtrain, num_round, evallist )
+
+###
+# build dmatrix from scipy.sparse
+print 'start running example of build DMatrix from scipy.sparse'
+labels = []
+row = []; col = []; dat = []
+i = 0
+for l in open('agaricus.txt.train'):
+    arr = l.split()
+    labels.append( int(arr[0]))
+    for it in arr[1:]:
+        k,v = it.split(':')
+        row.append(i); col.append(int(k)); dat.append(float(v))
+    i += 1
+
+csr = scipy.sparse.csr_matrix( (dat, (row,col)) )
+dtrain = xgb.DMatrix( csr )
+dtrain.set_label(labels)
+evallist  = [(dtest,'eval'), (dtrain,'train')]
+bst = xgb.train( param, dtrain, num_round, evallist )
+
+print 'start running example of build DMatrix from numpy array'
+# NOTE: npymat is numpy array, we will convert it into scipy.sparse.csr_matrix in internal implementation,then convert to DMatrix
+npymat = csr.todense()
+dtrain = xgb.DMatrix( npymat )
+dtrain.set_label(labels)
+evallist  = [(dtest,'eval'), (dtrain,'train')]
+bst = xgb.train( param, dtrain, num_round, evallist )
+

python/example/featmap.txt

@@ -0,0 +1,126 @@
+0	cap-shape=bell	i
+1	cap-shape=conical	i
+2	cap-shape=convex	i
+3	cap-shape=flat	i
+4	cap-shape=knobbed	i
+5	cap-shape=sunken	i
+6	cap-surface=fibrous	i
+7	cap-surface=grooves	i
+8	cap-surface=scaly	i
+9	cap-surface=smooth	i
+10	cap-color=brown	i
+11	cap-color=buff	i
+12	cap-color=cinnamon	i
+13	cap-color=gray	i
+14	cap-color=green	i
+15	cap-color=pink	i
+16	cap-color=purple	i
+17	cap-color=red	i
+18	cap-color=white	i
+19	cap-color=yellow	i
+20	bruises?=bruises	i
+21	bruises?=no	i
+22	odor=almond	i
+23	odor=anise	i
+24	odor=creosote	i
+25	odor=fishy	i
+26	odor=foul	i
+27	odor=musty	i
+28	odor=none	i
+29	odor=pungent	i
+30	odor=spicy	i
+31	gill-attachment=attached	i
+32	gill-attachment=descending	i
+33	gill-attachment=free	i
+34	gill-attachment=notched	i
+35	gill-spacing=close	i
+36	gill-spacing=crowded	i
+37	gill-spacing=distant	i
+38	gill-size=broad	i
+39	gill-size=narrow	i
+40	gill-color=black	i
+41	gill-color=brown	i
+42	gill-color=buff	i
+43	gill-color=chocolate	i
+44	gill-color=gray	i
+45	gill-color=green	i
+46	gill-color=orange	i
+47	gill-color=pink	i
+48	gill-color=purple	i
+49	gill-color=red	i
+50	gill-color=white	i
+51	gill-color=yellow	i
+52	stalk-shape=enlarging	i
+53	stalk-shape=tapering	i
+54	stalk-root=bulbous	i
+55	stalk-root=club	i
+56	stalk-root=cup	i
+57	stalk-root=equal	i
+58	stalk-root=rhizomorphs	i
+59	stalk-root=rooted	i
+60	stalk-root=missing	i
+61	stalk-surface-above-ring=fibrous	i
+62	stalk-surface-above-ring=scaly	i
+63	stalk-surface-above-ring=silky	i
+64	stalk-surface-above-ring=smooth	i
+65	stalk-surface-below-ring=fibrous	i
+66	stalk-surface-below-ring=scaly	i
+67	stalk-surface-below-ring=silky	i
+68	stalk-surface-below-ring=smooth	i
+69	stalk-color-above-ring=brown	i
+70	stalk-color-above-ring=buff	i
+71	stalk-color-above-ring=cinnamon	i
+72	stalk-color-above-ring=gray	i
+73	stalk-color-above-ring=orange	i
+74	stalk-color-above-ring=pink	i
+75	stalk-color-above-ring=red	i
+76	stalk-color-above-ring=white	i
+77	stalk-color-above-ring=yellow	i
+78	stalk-color-below-ring=brown	i
+79	stalk-color-below-ring=buff	i
+80	stalk-color-below-ring=cinnamon	i
+81	stalk-color-below-ring=gray	i
+82	stalk-color-below-ring=orange	i
+83	stalk-color-below-ring=pink	i
+84	stalk-color-below-ring=red	i
+85	stalk-color-below-ring=white	i
+86	stalk-color-below-ring=yellow	i
+87	veil-type=partial	i
+88	veil-type=universal	i
+89	veil-color=brown	i
+90	veil-color=orange	i
+91	veil-color=white	i
+92	veil-color=yellow	i
+93	ring-number=none	i
+94	ring-number=one	i
+95	ring-number=two	i
+96	ring-type=cobwebby	i
+97	ring-type=evanescent	i
+98	ring-type=flaring	i
+99	ring-type=large	i
+100	ring-type=none	i
+101	ring-type=pendant	i
+102	ring-type=sheathing	i
+103	ring-type=zone	i
+104	spore-print-color=black	i
+105	spore-print-color=brown	i
+106	spore-print-color=buff	i
+107	spore-print-color=chocolate	i
+108	spore-print-color=green	i
+109	spore-print-color=orange	i
+110	spore-print-color=purple	i
+111	spore-print-color=white	i
+112	spore-print-color=yellow	i
+113	population=abundant	i
+114	population=clustered	i
+115	population=numerous	i
+116	population=scattered	i
+117	population=several	i
+118	population=solitary	i
+119	habitat=grasses	i
+120	habitat=leaves	i
+121	habitat=meadows	i
+122	habitat=paths	i
+123	habitat=urban	i
+124	habitat=waste	i
+125	habitat=woods	i

python/xgboost.py

@@ -1,10 +1,12 @@
 # module for xgboost
 import ctypes 
+import os
 # optinally have scipy sparse, though not necessary
 import numpy as np
 import scipy.sparse as scp
+
 # set this line correctly
-XGBOOST_PATH = './libxgboostpy.so'
+XGBOOST_PATH = os.path.dirname(__file__)+'/libxgboostpy.so'
 
 # entry type of sparse matrix
 class REntry(ctypes.Structure):
@@ -34,9 +36,9 @@ class DMatrix:
         else:
             try:
                 csr = scp.csr_matrix(data)
-                self.__init_from_csr(data)
+                self.__init_from_csr(csr)
             except:
-                raise "DMatrix", "can not intialize DMatrix from"+type(data)                
+                raise Exception, "can not intialize DMatrix from"+str(type(data))
         if label != None:
             self.set_label(label)
 

python/xgboost_python.cpp

@@ -32,6 +32,7 @@ namespace xgboost{
                 mat.row_data_.resize( mat.row_ptr_.back() + len );
                 memcpy( &mat.row_data_[mat.row_ptr_.back()], data, sizeof(XGEntry)*len );
                 mat.row_ptr_.push_back( mat.row_ptr_.back() + len );
+                init_col_ = false;
             }
             inline const XGEntry* GetRow(unsigned ridx, size_t* len) const{
                 const xgboost::booster::FMatrixS &mat = this->data;
@@ -72,7 +73,7 @@ namespace xgboost{
                 return &(this->info.labels[0]);
             }
             inline void CheckInit(void){
-                if(!this->data.HaveColAccess()){
+                if(!init_col_){
                     this->data.InitData();
                 }
                 utils::Assert( this->data.NumRow() == this->info.labels.size(), "DMatrix: number of labels must match number of rows in matrix");
@@ -163,7 +164,9 @@ extern "C"{
     void *XGBoosterCreate( void *dmats[], size_t len ){
         std::vector<const xgboost::regrank::DMatrix*> mats;
         for( size_t i = 0; i < len; ++i ){
-            mats.push_back( static_cast<DMatrix*>(dmats[i]) );
+            DMatrix *dtr = static_cast<DMatrix*>(dmats[i]);
+            dtr->CheckInit();
+            mats.push_back( dtr );
         }
         return new Booster( mats );
     }

regrank/xgboost_regrank_data.h

@@ -112,9 +112,11 @@ namespace xgboost{
                     unsigned ngptr;
                     if( fs.Read(&ngptr, sizeof(unsigned) ) != 0 ){
                         info.group_ptr.resize( ngptr );
+                        if( ngptr != 0 ){
                             utils::Assert( fs.Read(&info.group_ptr[0], sizeof(unsigned) * ngptr) != 0, "Load group file");
                         }
                     }
+                }
                 fs.Close();
                 
                 if (!silent){
@@ -143,8 +145,10 @@ namespace xgboost{
                 {// write out group ptr
                     unsigned ngptr = static_cast<unsigned>( info.group_ptr.size() );                    
                     fs.Write(&ngptr, sizeof(unsigned) );
+                    if( ngptr != 0 ){
                         fs.Write(&info.group_ptr[0], sizeof(unsigned) * ngptr);                    
                     }
+                }
                 fs.Close();
                 if (!silent){
                     printf("%ux%u matrix with %lu entries is saved to %s\n",