ok

multi-node/col-split/README.md

@@ -1,6 +1,7 @@
 Distributed XGBoost: Column Split Version
 ====
 * run ```bash mushroom-col.sh <n-mpi-process>```
+  - mushroom-col.sh starts xgboost-mpi job
 * 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>```

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

@@ -0,0 +1,28 @@
+#!/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 instead of xgboost-mpi
+# 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 $k ../../xgboost mushroom-col.conf dsplit=col
+
+# the model can be directly loaded by single machine xgboost solver, as usuall
+../../xgboost mushroom-col.conf task=dump model_in=0002.model fmap=../../demo/data/featmap.txt name_dump=dump.nice.$k.txt
+
+# run for one round, and continue training
+../submit_job_tcp.py $k ../../xgboost mushroom-col.conf dsplit=col num_round=1
+../submit_job_tcp.py $k ../../xgboost mushroom-col.conf dsplit=col model_in=0001.model
+
+cat dump.nice.$k.txt