-
-
Notifications
You must be signed in to change notification settings - Fork 8.7k
/
DMatrixSuite.scala
200 lines (180 loc) · 6.05 KB
/
DMatrixSuite.scala
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
/*
Copyright (c) 2014-2023 by Contributors
Licensed 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.
*/
package ml.dmlc.xgboost4j.scala
import ml.dmlc.xgboost4j.java.DMatrix.SparseType
import java.util.Arrays
import scala.util.Random
import org.scalatest.funsuite.AnyFunSuite
import ml.dmlc.xgboost4j.java.{DMatrix => JDMatrix}
class DMatrixSuite extends AnyFunSuite {
test("create DMatrix from File") {
val dmat = new DMatrix("../../demo/data/agaricus.txt.test?format=libsvm")
// get label
val labels: Array[Float] = dmat.getLabel
// check length
assert(dmat.rowNum === labels.length)
// set weights
val weights: Array[Float] = Arrays.copyOf(labels, labels.length)
dmat.setWeight(weights)
val dweights: Array[Float] = dmat.getWeight
assert(weights === dweights)
}
test("create DMatrix from CSR") {
// create Matrix from csr format sparse Matrix and labels
/**
* sparse matrix
* 1 0 2 3 0
* 4 0 2 3 5
* 3 1 2 5 0
*/
val data = List[Float](1, 2, 3, 4, 2, 3, 5, 3, 1, 2, 5).toArray
val colIndex = List(0, 2, 3, 0, 2, 3, 4, 0, 1, 2, 3).toArray
val rowHeaders = List[Long](0, 3, 7, 11).toArray
val dmat1 = new DMatrix(rowHeaders, colIndex, data, JDMatrix.SparseType.CSR)
assert(dmat1.rowNum === 3)
val label1 = List[Float](1, 0, 1).toArray
dmat1.setLabel(label1)
val label2 = dmat1.getLabel
assert(label2 === label1)
val dmat2 = new DMatrix(rowHeaders, colIndex, data, JDMatrix.SparseType.CSR, 5, 1.0f, -1)
assert(dmat2.nonMissingNum === 9);
}
test("create DMatrix from CSREx") {
// create Matrix from csr format sparse Matrix and labels
/**
* sparse matrix
* 1 0 2 3 0
* 4 0 2 3 5
* 3 1 2 5 0
*/
val data = List[Float](1, 2, 3, 4, 2, 3, 5, 3, 1, 2, 5).toArray
val colIndex = List(0, 2, 3, 0, 2, 3, 4, 0, 1, 2, 3).toArray
val rowHeaders = List[Long](0, 3, 7, 11).toArray
val dmat1 = new DMatrix(rowHeaders, colIndex, data, JDMatrix.SparseType.CSR, 5)
assert(dmat1.rowNum === 3)
val label1 = List[Float](1, 0, 1).toArray
dmat1.setLabel(label1)
val label2 = dmat1.getLabel
assert(label2 === label1)
}
test("create DMatrix from CSC") {
// create Matrix from csc format sparse Matrix and labels
/**
* sparse matrix
* 1 0 2
* 3 0 4
* 0 2 3
* 5 3 1
* 2 5 0
*/
val data = List[Float](1, 3, 5, 2, 2, 3, 5, 2, 4, 3, 1).toArray
val rowIndex = List(0, 1, 3, 4, 2, 3, 4, 0, 1, 2, 3).toArray
val colHeaders = List[Long](0, 4, 7, 11).toArray
val dmat1 = new DMatrix(colHeaders, rowIndex, data, JDMatrix.SparseType.CSC)
assert(dmat1.rowNum === 5)
val label1 = List[Float](1, 0, 1, 1, 1).toArray
dmat1.setLabel(label1)
val label2 = dmat1.getLabel
assert(label2 === label1)
val dmat2 = new DMatrix(colHeaders, rowIndex, data, JDMatrix.SparseType.CSC, 5, 1.0f, -1)
assert(dmat2.nonMissingNum === 9);
}
test("create DMatrix from CSCEx") {
// create Matrix from csc format sparse Matrix and labels
/**
* sparse matrix
* 1 0 2
* 3 0 4
* 0 2 3
* 5 3 1
* 2 5 0
*/
val data = List[Float](1, 3, 5, 2, 2, 3, 5, 2, 4, 3, 1).toArray
val rowIndex = List(0, 1, 3, 4, 2, 3, 4, 0, 1, 2, 3).toArray
val colHeaders = List[Long](0, 4, 7, 11).toArray
val dmat1 = new DMatrix(colHeaders, rowIndex, data, JDMatrix.SparseType.CSC, 5)
assert(dmat1.rowNum === 5)
val label1 = List[Float](1, 0, 1, 1, 1).toArray
dmat1.setLabel(label1)
val label2 = dmat1.getLabel
assert(label2 === label1)
}
test("create DMatrix from DenseMatrix") {
val nrow = 10
val ncol = 5
val data0 = new Array[Float](nrow * ncol)
// put random nums
for (i <- data0.indices) {
data0(i) = Random.nextFloat()
}
// create label
val label0 = new Array[Float](nrow)
for (i <- label0.indices) {
label0(i) = Random.nextFloat()
}
val dmat0 = new DMatrix(data0, nrow, ncol, Float.NaN)
dmat0.setLabel(label0)
// check
assert(dmat0.rowNum === 10)
assert(dmat0.getLabel.length === 10)
// set weights for each instance
val weights = new Array[Float](nrow)
for (i <- weights.indices) {
weights(i) = Random.nextFloat()
}
dmat0.setWeight(weights)
assert(weights === dmat0.getWeight)
}
test("create DMatrix from DenseMatrix with missing value") {
val nrow = 10
val ncol = 5
val data0 = new Array[Float](nrow * ncol)
// put random nums
for (i <- data0.indices) {
if (i % 10 == 0) {
data0(i) = -0.1f
} else {
data0(i) = Random.nextFloat()
}
}
// create label
val label0 = new Array[Float](nrow)
for (i <- label0.indices) {
label0(i) = Random.nextFloat()
}
val dmat0 = new DMatrix(data0, nrow, ncol, -0.1f)
dmat0.setLabel(label0)
// check
assert(dmat0.rowNum === 10)
assert(dmat0.getLabel.length === 10)
}
test("create get data from DMatrix as BigDenseMatrix") {
// create Matrix from csr format sparse Matrix and labels
/**
* sparse matrix
* 1 0 2 3 0
* 4 0 2 3 5
* 3 1 2 5 0
*/
val data = Array[Float](1, 2, 3, 4, 2, 3, 5, 3, 1, 2, 5)
val colIndex = Array[Int](0, 2, 3, 0, 2, 3, 4, 0, 1, 2, 3)
val rowHeaders = Array[Long](0, 3, 7, 11)
val dmatrix = new DMatrix(rowHeaders, colIndex, data, SparseType.CSR, 5)
val denseMatrix = dmatrix.getData
assert(denseMatrix.get(0, 0) == 1.0f)
assert(denseMatrix.get(0, 3) == 3.0f)
assert(denseMatrix.get(1, 2) == 2.0f)
assert(denseMatrix.get(2, 3) == 5.0f)
assert(denseMatrix.get(2, 4) == 0.0f)
}
}