| #------------------------------------------------------------- |
| # |
| # 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. |
| # |
| # Parameters: |
| # X : (input) filename of data matrix |
| # y : (default ncol(X)) colIndex |
| # 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 SystemDS.jar -f algorithms/utils/splitXY.dml -nvargs X="/tmp/X.mtx" y=50 OX="/tmp/OX.mtx OY="/tmp/OY.mtx |
| # |
| |
| ofmt = ifdef($ofmt, "binary") |
| y = ifdef($y, ncol($X)) |
| |
| X = read ($X) |
| |
| if (y == 1) |
| { |
| OX = X[,y+1:ncol(X)] |
| OY = X[,y] |
| } |
| else if (y == ncol(X)) |
| { |
| OX = X[,1:y-1] |
| OY = X[,y] |
| } |
| else |
| { |
| OX1 = X[,1:y-1] |
| OX2 = X[,y+1:ncol(X)] |
| OX = cbind (OX1, OX2) |
| OY = X[,y] |
| } |
| |
| # Write output |
| write (OX, $OX, format=ofmt) |
| write (OY, $OY, format=ofmt) |
| |
| |