blob: 32ff54ed84ff28c99ce105cac27faf9176c23f14 [file] [log] [blame]
#-------------------------------------------------------------
#
# 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.
#
#-------------------------------------------------------------
# impute the data by most frequent value (recoded data only)
# Related to [SYSTEMDS-2662] dependency function for cleaning pipelines
#
# INPUT:
# ------------------------------------------------------------------------------------
# X Data Matrix (Recoded Matrix for categorical features)
# imputationVector column mean vector
# ------------------------------------------------------------------------------------
#
# OUTPUT:
# -----------------------------------------------------------------------------------
# X imputed dataset
# -----------------------------------------------------------------------------------
m_imputeByModeApply = function(Matrix[Double] X, Matrix[Double] imputedVec)
return(Matrix[Double] X)
{
maskNA = is.na(X)
X = replace(target = X, pattern=NaN, replacement=0)
X = X + (maskNA * imputedVec)
}