blob: 1cf05b37be8a8b8496bb46b012b2b393e6f652ac [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.
#
#-------------------------------------------------------------
crossV = function(Matrix[double] X, Matrix[double] y, double lamda, Integer k) return (Matrix[double] R)
{
#create empty lists
dataset_X = list(); #empty list
dataset_y = list();
fs = ceil(nrow(X)/k);
off = fs - 1;
#devide X, y into lists of k matrices
for (i in seq(1, k)) {
dataset_X = append(dataset_X, X[i*fs-off : min(i*fs, nrow(X)),]);
dataset_y = append(dataset_y, y[i*fs-off : min(i*fs, nrow(y)),]);
}
beta_list = list();
#keep one fold for testing in each iteration
for (i in seq(1, k)) {
[tmpX, testX] = remove(dataset_X, i);
[tmpy, testy] = remove(dataset_y, i);
trainX = rbind(tmpX);
trainy = rbind(tmpy);
beta = SimlinRegDS(trainX, trainy, lamda, ncol(X));
beta_list = append(beta_list, beta);
}
R = cbind(beta_list);
}
SimlinRegDS = function(Matrix[Double] X, Matrix[Double] y, Double lamda, Integer N) return (Matrix[double] beta)
{
A = (t(X) %*% X) + diag(matrix(lamda, rows=N, cols=1));
b = t(X) %*% y;
beta = solve(A, b);
}
X = rand(rows=$1, cols=$2);
y = X %*% rand(rows=$2, cols=1);
R = crossV(X, y, 0.001, 7);
r = as.matrix(sum(R!=0));
write(r, $3);
#expected: "Result: $2*7