src/main/python/tests/source/source_02.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.
#
#-------------------------------------------------------------

func_01 = function() return(matrix[double] C){
    C = matrix(1,1,1)
}

func_02 = function(matrix[double] A)
    return(matrix[double] C){
    C = A %*% rand(rows=ncol(A), cols=1)
}


Preprocess = function(matrix[double] data) return(matrix[double] X){

    Fall = as.frame(data)

    # one hot encoding categorical column, other passthrough
    jspec = "{ ids:true, dummycode:[1] }"
    [X,M] = transformencode(target=Fall, spec=jspec)

    # clipping out of value ranges
    colSD = colSds(X)
    colMean = (colMeans(X))
    upperBound = colMean + 1.5 * colSD
    lowerBound = colMean - 1.5 * colSD
    outFilter = (X < lowerBound) | (X > upperBound)
    X = X - outFilter*X + outFilter*colMeans(X); 
    
    # normalization
    X = scale(X=X, center=TRUE, scale=TRUE);

}