scripts/builtin/imputeByMedian.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.
#
#-------------------------------------------------------------

# Related to [SYSTEMDS-2662] dependency function for cleaning pipelines

# impute the data by median value and if the feature is categorical then by mode value

# INPUT PARAMETERS:
# ---------------------------------------------------------------------------------------------
# NAME            TYPE    DEFAULT     MEANING
# ---------------------------------------------------------------------------------------------
# X               Double    ---        Data Matrix (Recoded Matrix for categorical features)
# mask           Double    ---        A 0/1 row vector for identifying numeric (0) and categorical features (1)
# ---------------------------------------------------------------------------------------------
 

#Output(s)
# ---------------------------------------------------------------------------------------------
# NAME                  TYPE    DEFAULT     MEANING
# ---------------------------------------------------------------------------------------------
# X               Double   ---        imputed dataset



m_imputeByMedian = function(Matrix[Double] X, Matrix[Double] mask)
return(Matrix[Double] X)
{

  nX = removeEmpty(target=X, margin="cols", select=(mask==0))
  cX = removeEmpty(target=X, margin="cols", select=mask)
  Mask_n = is.na(nX);  
  nX = replace(target=nX, pattern=NaN, replacement=0);
  cols = ncol(nX)
  #  median imputation
  colMedian = matrix(0, 1, cols)
  parfor(i in 1:cols, check=0)
    colMedian[1, i] = median(X[,i])
  X_n = nX + (Mask_n * colMedian)
  # mode imputation
  X_c = imputeByMode(cX)

  p = table(seq(1, ncol(nX)), removeEmpty(target=seq(1, ncol(mask)), margin="rows", 
    select=t(mask==0)), ncol(nX), ncol(X))
  q = table(seq(1, ncol(cX)), removeEmpty(target=seq(1, ncol(mask)), margin="rows", 
    select=t(mask)), ncol(cX), ncol(X))
  X = (X_n %*% p) + (X_c %*% q)
}