src/test/scripts/applications/parfor/parfor_naive-bayes2.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.
#
#-------------------------------------------------------------

D = read($1)
C = read($2)

# reading input args
numClasses = $3
laplace_correction = 1

numRows = nrow(D)
numFeatures = ncol(D)

# Compute conditionals

# Compute the feature counts for each class
classFeatureCounts = matrix(0, rows=numClasses, cols=numFeatures)
parfor (i in 1:numFeatures, opt=CONSTRAINED, mode=REMOTE_MR) {
  Col = D[,i]
  classFeatureCounts[,i] = aggregate(target=Col, groups=C, fn="sum")
}

# Compute the total feature count for each class 
# and add the number of features to this sum
# for subsequent regularization (Laplace's rule)
classSums = rowSums(classFeatureCounts) + numFeatures*laplace_correction

# Compute class conditional probabilities
repClassSums = classSums %*% matrix(1,rows=1,cols=numFeatures);
class_conditionals = (classFeatureCounts + laplace_correction) / repClassSums;

# Compute class priors
class_counts = aggregate(target=C, groups=C, fn="count")
class_prior = class_counts / numRows;

# write out the model
write(class_prior, $4, format="text");
write(class_conditionals, $5, format="text");