scripts/builtin/imputeByMode.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-2902] dependency function for cleaning pipelines

# impute the data by mode value 

# INPUT PARAMETERS:
# ---------------------------------------------------------------------------------------------
# NAME            TYPE    DEFAULT     MEANING
# ---------------------------------------------------------------------------------------------
# X               Double    ---        Data Matrix (Recoded Matrix for categorical features)
# ---------------------------------------------------------------------------------------------
 

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


m_imputeByMode = function(Matrix[Double] X)
return(Matrix[Double] X)
{

  Mask = is.na(X)
  X = replace(target=X, pattern=NaN, replacement=0)
  colMode = matrix(0, 1, ncol(X))
  for(i in 1: ncol(X)) {
    X_c = removeEmpty(target=X[, i], margin = "rows", select=(X[, i] < 1)==0)
    if(sum(X_c) == 0)
      colMode[1, i] = 1
    else {
      cat_counts = table(X_c, 1, nrow(X_c), 1);  # counts for each category
      colMode[1,i] = as.scalar(rowIndexMax(t(cat_counts))) # mode
    }
  }
  Mask = Mask * colMode
  X = X + Mask
}