scripts/builtin/smote.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.
#
#-------------------------------------------------------------


# Builtin function for handing class imbalance using Synthetic Minority Over-sampling Technique (SMOTE)
#
# INPUT PARAMETERS:
# ---------------------------------------------------------------------------------------------
# NAME            TYPE    DEFAULT     MEANING
# ---------------------------------------------------------------------------------------------
# X               Double   ---       Matrix of minority class samples 
# s               Integer   25       Amount of SMOTE (percentage of oversampling), integral multiple of 100
# k               Integer   1        Number of nearest neighbour
# ---------------------------------------------------------------------------------------------


#Output(s)
# ---------------------------------------------------------------------------------------------
# NAME            TYPE    DEFAULT     MEANING
# ---------------------------------------------------------------------------------------------
# Y               Double   ---       Matrix of (N/100)-1 * nrow(X) synthetic minority class samples 

m_smote = function(Matrix[Double] X, Integer s = 200, Integer k = 1, Boolean verbose = FALSE) 
return (Matrix[Double] Y) {

  if(s < 100 | (s%%100) != 0)
  {
    print("the number of samples should be an integral multiple of 100. Setting s = 100")
    s = 100
  }
  # matrix to keep the index of KNN for each minority sample
  knn_index = matrix(0,k,0)
  # find nearest neighbour
  for(i in 1:nrow(X))
  {
    knn = nn(X, X[i, ], k)
    knn_index = cbind(knn_index, knn)
  }
  
  # number of synthetic samples from each minority class sample
  iter = (s/100)-1
  # matrix to store synthetic samples
  synthetic_samples = matrix(0, 0, ncol(X))
  while(iter > 0)
  {
    # generate a random number
    # TODO avoid duplicate random numbers
    rand_index = as.integer(as.scalar(Rand(rows=1, cols=1, min=1, max=k)))
    # pick the random NN
    knn_sample = knn_index[rand_index,] 
    # generate sample    
    for(i in 1:ncol(knn_index))
    {
      index = as.scalar(knn_sample[1,i])
      X_diff = X[index,] - X[i, ]
      gap = as.scalar(Rand(rows=1, cols=1, min=0, max=1))
      X_sys = X[i, ] + (gap*X_diff)
      synthetic_samples = rbind(synthetic_samples, X_sys)
    }
    iter = iter - 1
  }

  Y = synthetic_samples
}
  


nn = function(Matrix[Double] X, Matrix[Double] instance, Integer k )
return (Matrix[Double] knn_)
{
  if(nrow(X) < k)
    stop("can not pick "+k+" nearest neighbours from "+nrow(X)+" total instances")

  # compute the euclidean distance
  diff = X - instance
  square_diff = diff^2
  distance = sqrt(rowSums(square_diff))
  sort_dist = order(target = distance, by = 1, decreasing= FALSE, index.return =  TRUE)
  knn_ = sort_dist[2:k+1,]
}