scripts.utils.splitXY-dummy.dml Maven / Gradle / Ivy
Go to download
Show more of this group Show more artifacts with this name
Show all versions of systemml Show documentation
Show all versions of systemml Show documentation
Declarative Machine Learning
#-------------------------------------------------------------
#
# Licensed to the Apache Software Foundation (ASF) under one
# or more contributor license agreements. See the NOTICE file
# distributed with this work for additional information
# regarding copyright ownership. The ASF licenses this file
# to you under the Apache License, Version 2.0 (the
# "License"); you may not use this file except in compliance
# with the License. You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing,
# software distributed under the License is distributed on an
# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
# KIND, either express or implied. See the License for the
# specific language governing permissions and limitations
# under the License.
#
#-------------------------------------------------------------
# Utility script to split X into new X and Y, which can be used for machine learning
# algorithms with response variables. This script has the same functionality as splitXY.dml but also
# handles the case of dummycoded Y variables, where they may have multiple columns.
#
# Parameters:
# X : (input) filename of data matrix
# S : (input, default ncol(x) - N+1) starting index of dummycoding
# N : (input, default 1) number of features present (i.e. dummycoded columns)
# OX : (output) filename of output matrix with all columns except y
# OY : (output) filename of output matrix with y column
# ofmt : (default binary) format of OX and OY output matrix
#
# Example:
# hadoop jar SystemML.jar -f algorithms/utils/splitXY-dummy.dml -nvargs X="/tmp/X.mtx" S=4 N=3 OX=/tmp/OX.mtx OY=/tmp/OY.mtx ofmt=csv
#
ofmt = ifdef($ofmt, "binary")
X = read ($X)
N = ifdef($N, 1)
nc = ncol(X)
S = ifdef($S, nc-N+1)
if (S==1)
{
OX = X[,N+1:nc]
OY = X[,1:N]
}
else if (S == nc-N+1)
{
OX = X[,1:nc-N]
OY = X[,nc-N+1:nc]
}
else
{
OX1 = X[,1:S-1]
OX2 = X[,S+N:nc]
OX = cbind (OX1, OX2)
OY = X[,S:S+N-1]
}
# Write output
write (OX, $OX, format=ofmt)
write (OY, $OY, format=ofmt)