make wrapper ok

multi-node/col-split/README.md

@@ -1,6 +1,11 @@
 Distributed XGBoost: Column Split Version
 ====
-* run ```bash mushroom-row.sh <n-mpi-process>```
+* run ```bash mushroom-col.sh <n-mpi-process>```
+* run ```bash mushroom-col-tcp.sh <n-process>```
+  - mushroom-col-tcp.sh starts xgboost job using xgboost's buildin allreduce 
+* run ```bash mushroom-col-python.sh <n-process>```
+  - mushroom-col-python.sh starts xgboost python job using xgboost's buildin all reduce
+  - see mushroom-col.py
 
 How to Use
 ====

multi-node/col-split/mushroom-col-python.sh

@@ -0,0 +1,22 @@
+#!/bin/bash
+if [[ $# -ne 1 ]]
+then
+    echo "Usage: nprocess"
+    exit -1
+fi
+
+#
+# This script is same as mushroom-col except that we will be using xgboost python module
+# 
+# xgboost used built in tcp-based allreduce module, and can be run on more enviroment, so long as we know how to start job by modifying ../submit_job_tcp.py
+#
+rm -rf train.col* *.model
+k=$1
+
+# split the lib svm file into k subfiles
+python splitsvm.py ../../demo/data/agaricus.txt.train train $k
+
+# run xgboost mpi
+../submit_job_tcp.py $k python mushroom-col.py
+
+cat dump.nice.$k.txt

multi-node/col-split/mushroom-col.py

@@ -0,0 +1,29 @@
+import os
+import sys
+sys.path.append(os.path.dirname(__file__)+'/../wrapper')
+import xgboost as xgb
+# this is example script of running distributed xgboost using python
+
+# call this additional function to intialize the xgboost sync module
+# in distributed mode
+xgb.sync_init(sys.argv)
+rank = xgb.sync_get_rank()
+# read in dataset
+dtrain = xgb.DMatrix('train.col%d' % rank)
+param = {'max_depth':3, 'eta':1, 'silent':1, 'objective':'binary:logistic' }
+param['dsplit'] = 'col'
+nround = 3
+
+if rank == 0:
+    dtest = xgb.DMatrix('../../demo/data/agaricus.txt.test')
+    model = xgb.train(param, dtrain, nround, [(dtrain, 'train') , (dtest, 'test')])
+else:
+    # if it is a slave node, do not run evaluation
+    model = xgb.train(param, dtrain, nround)
+
+if rank == 0:
+    model.save_model('%04d.model' % nround)
+    # dump model with feature map
+    model.dump_model('dump.nice.%d.txt' % xgb.sync_get_world_size(),'../../demo/data/featmap.txt')
+# shutdown the synchronization module
+xgb.sync_finalize()