cleanup multi-node

multi-node/row-split/README.md

@@ -1,10 +1,8 @@
 Distributed XGBoost: Row Split Version
 ====
+* You might be interested to checkout the [Hadoop example](../hadoop)
 * Machine Rabit: run ```bash machine-row-rabit.sh <n-mpi-process>```
   - machine-col-rabit.sh starts xgboost job using rabit
-* Mushroom: run ```bash mushroom-row-mpi.sh <n-mpi-process>```
-* Machine: run ```bash machine-row-mpi.sh <n-mpi-process>```
-  - Machine case also include example to continue training from existing model
 
 How to Use
 ====

multi-node/row-split/machine-row-map.sh

@@ -1,20 +0,0 @@
-#!/bin/bash
-if [[ $# -ne 1 ]]
-then
-    echo "Usage: nprocess"
-    exit -1
-fi
-
-rm -rf train-machine.row* *.model
-k=$1
-# make machine data
-cd ../../demo/regression/
-python mapfeat.py
-python mknfold.py machine.txt 1
-cd -
-
-# split the lib svm file into k subfiles
-python splitrows.py ../../demo/regression/machine.txt.train train-machine $k
-
-# run xgboost mpi, take data from stdin
-../submit_job_tcp.py $k "bash map.sh train-machine.row ../../xgboost machine-row.conf dsplit=row num_round=3 data=stdin"

multi-node/row-split/machine-row-mpi.sh

@@ -1,24 +0,0 @@
-#!/bin/bash
-if [[ $# -ne 1 ]]
-then
-    echo "Usage: nprocess"
-    exit -1
-fi
-
-rm -rf train-machine.row* *.model
-k=$1
-# make machine data
-cd ../../demo/regression/
-python mapfeat.py
-python mknfold.py machine.txt 1
-cd -
-
-# split the lib svm file into k subfiles
-python splitrows.py ../../demo/regression/machine.txt.train train-machine $k
-
-# run xgboost mpi
-mpirun -n $k ../../xgboost-mpi machine-row.conf dsplit=row num_round=3
-
-# run xgboost-mpi save model 0001, continue to run from existing model
-mpirun -n $k ../../xgboost-mpi machine-row.conf dsplit=row num_round=1
-mpirun -n $k ../../xgboost-mpi machine-row.conf dsplit=row num_round=2 model_in=0001.model

multi-node/row-split/map.sh

@@ -1,3 +0,0 @@
-# a simple script to simulate mapreduce mapper
-echo "cat $1$OMPI_COMM_WORLD_RANK | ${@:2}"
-cat $1$OMPI_COMM_WORLD_RANK | ${@:2}

multi-node/row-split/mushroom-row-mpi.sh

@@ -1,19 +0,0 @@
-#!/bin/bash
-if [[ $# -ne 1 ]]
-then
-    echo "Usage: nprocess"
-    exit -1
-fi
-
-rm -rf train.row* *.model
-k=$1
-
-# split the lib svm file into k subfiles
-python splitrows.py ../../demo/data/agaricus.txt.train train $k
-
-# run xgboost mpi
-mpirun -n $k ../../xgboost-mpi mushroom-row.conf dsplit=row nthread=1 
-
-# the model can be directly loaded by single machine xgboost solver, as usuall
-../../xgboost mushroom-row.conf task=dump model_in=0002.model fmap=../../demo/data/featmap.txt name_dump=dump.nice.$k.txt
-cat dump.nice.$k.txt

multi-node/row-split/mushroom-row.conf

@@ -1,35 +0,0 @@
-# General Parameters, see comment for each definition
-# choose the booster, can be gbtree or gblinear
-booster = gbtree
-# choose logistic regression loss function for binary classification
-objective = binary:logistic
-
-# Tree Booster Parameters
-# step size shrinkage
-eta = 1.0 
-# minimum loss reduction required to make a further partition
-gamma = 1.0 
-# minimum sum of instance weight(hessian) needed in a child
-min_child_weight = 1 
-# maximum depth of a tree
-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 
-use_buffer = 0
-
-# The path of training data %d is the wildcard for the rank of the data
-# The idea is each process take a feature matrix with subset of columns
-#
-data = "train.row%d" 
-
-# The path of validation data, used to monitor training process, here [test] sets name of the validation set
-eval[test] = "../../demo/data/agaricus.txt.test" 
-# evaluate on training data as well each round
-eval_train = 1
-
-# The path of test data, need to use full data of test, try not use it, or keep an subsampled version
-test:data = "../../demo/data/agaricus.txt.test"