Hendrik/xgboost
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Check inf in data for all types of DMatrix. (#8911)

Browse Source
This commit is contained in:
Jiaming Yuan
2023-03-15 11:24:35 +08:00
committed by GitHub
parent 72e8331eab
commit f186c87cf9
11 changed files with 118 additions and 45 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
jvm-packages/xgboost4j-gpu/src/test/java/ml/dmlc/xgboost4j/gpu/java/BoosterTest.java
View File

@@ -84,9 +84,10 @@ public class BoosterTest {
};
try (Table tmpTable = Table.readCSV(schema, opts, new File(trainingDataPath))) {
ColumnVector[] df = new ColumnVector[12];
for (int i = 0; i < 12; ++i) {
df[i] = tmpTable.getColumn(i);
ColumnVector[] df = new ColumnVector[10];
// exclude the first two columns, they are label bounds and contain inf.
for (int i = 2; i < 12; ++i) {
df[i - 2] = tmpTable.getColumn(i);
}
try (Table X = new Table(df);) {
ColumnVector[] labels = new ColumnVector[1];

23
jvm-packages/xgboost4j-spark-gpu/src/test/scala/ml/dmlc/xgboost4j/scala/rapids/spark/GpuXGBoostClassifierSuite.scala
View File

@@ -21,7 +21,7 @@ import java.io.File
import ml.dmlc.xgboost4j.scala.spark.{XGBoostClassificationModel, XGBoostClassifier}
import org.apache.spark.ml.feature.VectorAssembler
import org.apache.spark.sql.functions.{col, udf}
import org.apache.spark.sql.functions.{col, udf, when}
import org.apache.spark.sql.types.{FloatType, StructField, StructType}
class GpuXGBoostClassifierSuite extends GpuTestSuite {
@@ -47,7 +47,8 @@ class GpuXGBoostClassifierSuite extends GpuTestSuite {
"num_round" -> 10, "num_workers" -> 1, "tree_method" -> "gpu_hist",
"features_cols" -> featureNames, "label_col" -> labelName)
val Array(originalDf, testDf) = spark.read.option("header", "true").schema(schema)
.csv(dataPath).randomSplit(Array(0.7, 0.3), seed = 1)
.csv(dataPath).withColumn("f2", when(col("f2").isin(Float.PositiveInfinity), 0))
.randomSplit(Array(0.7, 0.3), seed = 1)
// Get a model
val model = new XGBoostClassifier(xgbParam)
.fit(originalDf)
@@ -64,7 +65,8 @@ class GpuXGBoostClassifierSuite extends GpuTestSuite {
"num_round" -> 10, "num_workers" -> 1, "tree_method" -> "gpu_hist",
"features_cols" -> featureNames, "label_col" -> labelName)
val Array(originalDf, testDf) = spark.read.option("header", "true").schema(schema)
.csv(dataPath).randomSplit(Array(0.7, 0.3), seed = 1)
.csv(dataPath).withColumn("f2", when(col("f2").isin(Float.PositiveInfinity), 0))
.randomSplit(Array(0.7, 0.3), seed = 1)
val getWeightFromF1 = udf({ f1: Float => if (f1.toInt % 2 == 0) 1.0f else 0.001f })
val dfWithWeight = originalDf.withColumn("weight", getWeightFromF1(col("f1")))
@@ -87,7 +89,8 @@ class GpuXGBoostClassifierSuite extends GpuTestSuite {
val xgbParam = Map("eta" -> 0.1f, "max_depth" -> 2, "objective" -> "binary:logistic",
"num_round" -> 10, "num_workers" -> 1)
val Array(rawInput, testDf) = spark.read.option("header", "true").schema(schema)
.csv(dataPath).randomSplit(Array(0.7, 0.3), seed = 1)
.csv(dataPath).withColumn("f2", when(col("f2").isin(Float.PositiveInfinity), 0))
.randomSplit(Array(0.7, 0.3), seed = 1)
val classifier = new XGBoostClassifier(xgbParam)
.setFeaturesCol(featureNames)
@@ -122,7 +125,8 @@ class GpuXGBoostClassifierSuite extends GpuTestSuite {
val xgbParam = Map("eta" -> 0.1f, "max_depth" -> 2, "objective" -> "binary:logistic",
"num_round" -> 10, "num_workers" -> 1)
val Array(rawInput, _) = spark.read.option("header", "true").schema(schema)
.csv(dataPath).randomSplit(Array(0.7, 0.3), seed = 1)
.csv(dataPath).withColumn("f2", when(col("f2").isin(Float.PositiveInfinity), 0))
.randomSplit(Array(0.7, 0.3), seed = 1)
val vectorAssembler = new VectorAssembler()
.setHandleInvalid("keep")
@@ -144,7 +148,8 @@ class GpuXGBoostClassifierSuite extends GpuTestSuite {
// transform on GPU
withGpuSparkSession() { spark =>
val Array(_, testDf) = spark.read.option("header", "true").schema(schema)
.csv(dataPath).randomSplit(Array(0.7, 0.3), seed = 1)
.csv(dataPath).withColumn("f2", when(col("f2").isin(Float.PositiveInfinity), 0))
.randomSplit(Array(0.7, 0.3), seed = 1)
// Since CPU model does not know the information about the features cols that GPU transform
// pipeline requires. End user needs to setFeaturesCol(features: Array[String]) in the model
@@ -174,7 +179,8 @@ class GpuXGBoostClassifierSuite extends GpuTestSuite {
val xgbParam = Map("eta" -> 0.1f, "max_depth" -> 2, "objective" -> "binary:logistic",
"num_round" -> 10, "num_workers" -> 1)
val Array(rawInput, _) = spark.read.option("header", "true").schema(schema)
.csv(dataPath).randomSplit(Array(0.7, 0.3), seed = 1)
.csv(dataPath).withColumn("f2", when(col("f2").isin(Float.PositiveInfinity), 0))
.randomSplit(Array(0.7, 0.3), seed = 1)
val classifier = new XGBoostClassifier(xgbParam)
.setFeaturesCol(featureNames)
@@ -190,7 +196,8 @@ class GpuXGBoostClassifierSuite extends GpuTestSuite {
// transform on CPU
withCpuSparkSession() { spark =>
val Array(_, rawInput) = spark.read.option("header", "true").schema(schema)
.csv(dataPath).randomSplit(Array(0.7, 0.3), seed = 1)
.csv(dataPath).withColumn("f2", when(col("f2").isin(Float.PositiveInfinity), 0))
.randomSplit(Array(0.7, 0.3), seed = 1)
val featureColName = "feature_col"
val vectorAssembler = new VectorAssembler()