| #------------------------------------------------------------- |
| # |
| # 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. |
| # |
| #------------------------------------------------------------- |
| |
| # generates data to test linear regression |
| |
| # $1 is number of samples |
| # $2 is number of features (independent variables) |
| # $3 is maximum feature value (absolute value) |
| # $4 is maximum weight (absolute value) |
| # $5 is location to store generated weights |
| # $6 is location to store generated data |
| # $7 is location to store generated labels |
| # $8 is 0/1. 0 suppresses noise, 1 will add noise to Y |
| # $9 is b, 0 disables intercept |
| # $10 controls sparsity in the generated data |
| # $11 output format |
| |
| numSamples = $1 |
| numFeatures = $2 |
| maxFeatureValue = $3 |
| maxWeight = $4 |
| addNoise = $8 |
| b = $9 |
| fmt = $11 |
| |
| X = Rand(rows=numSamples, cols=numFeatures, min=-1, max=1, pdf="uniform", seed=0, sparsity=$10) |
| w = Rand(rows=numFeatures, cols=1, min=-1, max=1, pdf="uniform", seed=0) |
| X = X * maxFeatureValue |
| w = w * maxWeight |
| Y = X %*% w |
| |
| if( b != 0 ) { |
| b_mat = Rand(rows=1, cols=1, min=b, max=b, pdf="uniform") |
| w = rbind(w, t(b_mat)) |
| Y = Y + b |
| } |
| |
| noise = Rand(rows=numSamples, cols=1, pdf="normal", seed=0) |
| Y = Y + addNoise*noise |
| |
| write(w, $5, format=fmt) |
| write(X, $6, format=fmt) |
| write(Y, $7, format=fmt) |