src/test/scripts/applications/linear_regression/LinearRegression.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.
#
#-------------------------------------------------------------

# How to invoke this dml script LinearRegression.dml?
# Assume LR_HOME is set to the home of the dml script
# Assume input and output directories are on hdfs as INPUT_DIR and OUTPUT_DIR
# Assume rows = 50 and cols = 30 for v, eps = 0.00000001
# hadoop jar SystemDS.jar -f $LR_HOME/LinearRegression.dml -args "$INPUT_DIR/v" "$INPUT_DIR/y" 0.00000001 "$OUTPUT_DIR/w"

V = read($1);
y = read($2);

eps = $3;

r = -(t(V) %*% y);
p = -r;
norm_r2 = sum(r * r);
w = Rand(rows = ncol(V), cols = 1, min = 0, max = 0);

max_iteration = 3;
i = 0;
while(i < max_iteration) {
	q = ((t(V) %*% (V %*% p)) + eps  * p);
	alpha = norm_r2 / as.scalar(t(p) %*% q);
	w = w + alpha * p;
	old_norm_r2 = norm_r2;
	r = r + alpha * q;
	norm_r2 = sum(r * r);
	beta = norm_r2 / old_norm_r2;
	p = -r + beta * p;
	i = i + 1;
}

write(w, $4, format="text");