scripts/utils/generateData.dml

#-------------------------------------------------------------
#
# 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 generate random data for a matrix 
#
# Parameters:
#    R       : (input) number of rows for the generated matrix 
#    C	     : (input) number of columns for the generated matrix
#    S       : (input) sparsity of the data 
#    Min     : (input) minimum value of the data
#    Max     : (input) maximum value of the data
#    Pdf     : (input) probability distribution function for the data
#    Path    : (input) path on HDFS where the matrix will be stored
#
# Example:
#   hadoop jar SystemML.jar -f algorithms/utils/project.dml -nvargs X="/tmp/M.mtx" P="/tmp/P.mtx" o="/tmp/PX.mtx" 
#
# Assumptions:
# The order of colIDs in P is preserved. Order of columns in result is same as order of columns in P.
#      i.e. projecting columns 4 and 2 of X results in a matrix with columns 4 and 2.
# If P specifies the exclude list, then projected columns are order preserved.

numRows = ifdef($R, 5)
numCols = ifdef($C, 5)
sparsityParam = ifdef($S, 0.2)
minVal = ifdef($Min, 0)
maxVal = ifdef($Max, 10)
pdFunc = ifdef($Pdf, "uniform")
pathUse = ifdef($Path, "/user/bigr/randomData")

A = rand(rows=numRows, cols=numCols, sparsity=sparsityParam, min=minVal, max=maxVal, pdf="uniform");
write(A, pathUse, format="csv");