scripts/builtin/dbscanApply.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.
#
#-------------------------------------------------------------

# Implements the outlier detection/prediction algorithm using a DBScan model
#
# INPUT:
# ---------------------------------------------
# X              The input Matrix to do outlier detection on.
# clusterModel   Model of clusters to predict outliers against.
# eps            Maximum distance between two points for one to be considered reachable for the other.
# ---------------------------------------------
#
# OUTPUT:
# ----------------------------------------------
# outlierPoints   Predicted outliers
# ----------------------------------------------

m_dbscanApply = function (Matrix[Double] X, Matrix[Double] clusterModel, Double eps)
  return (Matrix[Double] cluster, Matrix[Double] outlierPoints)
{
  num_features_Xtest = ncol(X);
  num_rows_Xtest = nrow(X);
  num_features_model = ncol(clusterModel);
  num_rows_model = nrow(clusterModel);

  if(num_features_Xtest != num_features_model) {stop("DBSCAN Outlier: Stopping due to invalid inputs: features need to match");}
  if(eps < 0) { stop("DBSCAN Outlier: Stopping due to invalid inputs: Epsilon (eps) should be greater than 0"); }
  if(num_rows_model <= 0) { stop("DBSCAN Outlier: Stopping due to invalid inputs: Model is empty"); }
    
  Xall = rbind(clusterModel, X);
  neighbors = dist(Xall);
  neighbors = replace(target = neighbors, pattern = 0, replacement = 2.225e-307);
  neighbors = neighbors - diag(diag(neighbors));
  Xtest_dists = neighbors[(num_rows_model+1):nrow(Xall), 1:num_rows_model];
  withinEps = ((Xtest_dists <= eps) * (0 < Xtest_dists));
  outlierPoints = rowSums(withinEps) >= 1;
  cluster = removeEmpty(target=outlierPoints, margin="rows", select=outlierPoints)
}