[jira] [Updated] (SPARK-19449) Inconsistent results between ml package RandomForestClassificationModel and mllib package RandomForestModel
[
https://issues.apache.org/jira/browse/SPARK-19449?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Aseem Bansal updated SPARK-19449:
-
Description:
I worked on some code to convert ml package RandomForestClassificationModel to
mllib package RandomForestModel. It was needed because we need to make
predictions on the order of ms. I found that the results are inconsistent
although the underlying DecisionTreeModel are exactly the same. So the behavior
between the 2 implementations is inconsistent which should not be the case.
The below code can be used to reproduce the issue. Can run this as a simple
Java app as long as you have spark dependencies set up properly.
{noformat}
import org.apache.spark.ml.Transformer;
import org.apache.spark.ml.classification.*;
import org.apache.spark.ml.linalg.*;
import org.apache.spark.ml.regression.RandomForestRegressionModel;
import org.apache.spark.mllib.linalg.DenseVector;
import org.apache.spark.mllib.linalg.Vector;
import org.apache.spark.mllib.tree.configuration.Algo;
import org.apache.spark.mllib.tree.model.DecisionTreeModel;
import org.apache.spark.mllib.tree.model.RandomForestModel;
import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Row;
import org.apache.spark.sql.RowFactory;
import org.apache.spark.sql.SparkSession;
import org.apache.spark.sql.types.DataTypes;
import org.apache.spark.sql.types.Metadata;
import org.apache.spark.sql.types.StructField;
import org.apache.spark.sql.types.StructType;
import scala.Enumeration;
import java.util.ArrayList;
import java.util.List;
import java.util.Random;
abstract class Predictor {
abstract double predict(Vector vector);
}
public class MainConvertModels {
public static final int seed = 42;
public static void main(String[] args) {
int numRows = 1000;
int numFeatures = 3;
int numClasses = 2;
double trainFraction = 0.8;
double testFraction = 0.2;
SparkSession spark = SparkSession.builder()
.appName("conversion app")
.master("local")
.getOrCreate();
Dataset data = getDummyData(spark, numRows, numFeatures,
numClasses);
Dataset[] splits = data.randomSplit(new double[]{trainFraction,
testFraction}, seed);
Dataset trainingData = splits[0];
Dataset testData = splits[1];
testData.cache();
List labels = getLabels(testData);
List features = getFeatures(testData);
DecisionTreeClassifier classifier1 = new DecisionTreeClassifier();
DecisionTreeClassificationModel model1 = classifier1.fit(trainingData);
final DecisionTreeModel convertedModel1 =
convertDecisionTreeModel(model1, Algo.Classification());
RandomForestClassifier classifier = new RandomForestClassifier();
RandomForestClassificationModel model2 = classifier.fit(trainingData);
final RandomForestModel convertedModel2 =
convertRandomForestModel(model2);
System.out.println(
"** DecisionTreeClassifier\n" +
"** Original **" + getInfo(model1, testData) + "\n" +
"** New **" + getInfo(new Predictor() {
double predict(Vector vector) {return
convertedModel1.predict(vector);}
}, labels, features) + "\n" +
"\n" +
"** RandomForestClassifier\n" +
"** Original **" + getInfo(model2, testData) + "\n" +
"** New **" + getInfo(new Predictor() {double
predict(Vector vector) {return convertedModel2.predict(vector);}}, labels,
features) + "\n" +
"\n" +
"");
}
static Dataset getDummyData(SparkSession spark, int numberRows, int
numberFeatures, int labelUpperBound) {
StructType schema = new StructType(new StructField[]{
new StructField("label", DataTypes.DoubleType, false,
Metadata.empty()),
new StructField("features", new VectorUDT(), false,
Metadata.empty())
});
double[][] vectors = prepareData(numberRows, numberFeatures);
Random random = new Random(seed);
List dataTest = new ArrayList<>();
for (double[] vector : vectors) {
double label = (double) random.nextInt(2);
dataTest.add(RowFactory.create(label, Vectors.dense(vector)));
}
return spark.createDataFrame(dataTest, schema);
}
static double[][] prepareData(int numRows, int numFeatures) {
Random random = new Random(seed);
double[][] result = new double[numRows][numFeatures];
for (int row = 0; row < numRows; row++) {
for (int feature = 0; feature < numFeatures; feature++) {
result[row][feature] = random.nextDouble();
}
}
return result;
}
static
[jira] [Updated] (SPARK-19449) Inconsistent results between ml package RandomForestClassificationModel and mllib package RandomForestModel
[
https://issues.apache.org/jira/browse/SPARK-19449?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Aseem Bansal updated SPARK-19449:
-
Description:
I worked on some code to convert ml package RandomForestClassificationModel to
mllib package RandomForestModel. It was needed because we need to make
predictions on the order of ms. I found that the results are inconsistent
although the underlying DecisionTreeModel are exactly the same.
The below code can be used to reproduce the issue. Can run this as a simple
Java app as long as you have spark dependencies set up properly.
{noformat}
import org.apache.spark.ml.Transformer;
import org.apache.spark.ml.classification.*;
import org.apache.spark.ml.linalg.*;
import org.apache.spark.ml.regression.RandomForestRegressionModel;
import org.apache.spark.mllib.linalg.DenseVector;
import org.apache.spark.mllib.linalg.Vector;
import org.apache.spark.mllib.tree.configuration.Algo;
import org.apache.spark.mllib.tree.model.DecisionTreeModel;
import org.apache.spark.mllib.tree.model.RandomForestModel;
import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Row;
import org.apache.spark.sql.RowFactory;
import org.apache.spark.sql.SparkSession;
import org.apache.spark.sql.types.DataTypes;
import org.apache.spark.sql.types.Metadata;
import org.apache.spark.sql.types.StructField;
import org.apache.spark.sql.types.StructType;
import scala.Enumeration;
import java.util.ArrayList;
import java.util.List;
import java.util.Random;
abstract class Predictor {
abstract double predict(Vector vector);
}
public class MainConvertModels {
public static final int seed = 42;
public static void main(String[] args) {
int numRows = 1000;
int numFeatures = 3;
int numClasses = 2;
double trainFraction = 0.8;
double testFraction = 0.2;
SparkSession spark = SparkSession.builder()
.appName("conversion app")
.master("local")
.getOrCreate();
//Dataset data = getData(spark, "libsvm",
"/opt/spark2/data/mllib/sample_libsvm_data.txt");
Dataset data = getDummyData(spark, numRows, numFeatures,
numClasses);
Dataset[] splits = data.randomSplit(new double[]{trainFraction,
testFraction}, seed);
Dataset trainingData = splits[0];
Dataset testData = splits[1];
testData.cache();
List labels = getLabels(testData);
List features = getFeatures(testData);
DecisionTreeClassifier classifier1 = new DecisionTreeClassifier();
DecisionTreeClassificationModel model1 = classifier1.fit(trainingData);
final DecisionTreeModel convertedModel1 =
convertDecisionTreeModel(model1, Algo.Classification());
RandomForestClassifier classifier = new RandomForestClassifier();
RandomForestClassificationModel model2 = classifier.fit(trainingData);
final RandomForestModel convertedModel2 =
convertRandomForestModel(model2);
LogisticRegression lr = new LogisticRegression();
LogisticRegressionModel model3 = lr.fit(trainingData);
final org.apache.spark.mllib.classification.LogisticRegressionModel
convertedModel3 = convertLogisticRegressionModel(model3);
System.out.println(
"** DecisionTreeClassifier\n" +
"** Original **" + getInfo(model1, testData) + "\n" +
"** New **" + getInfo(new Predictor() {
double predict(Vector vector) {return
convertedModel1.predict(vector);}
}, labels, features) + "\n" +
"\n" +
"** RandomForestClassifier\n" +
"** Original **" + getInfo(model2, testData) + "\n" +
"** New **" + getInfo(new Predictor() {double
predict(Vector vector) {return convertedModel2.predict(vector);}}, labels,
features) + "\n" +
"\n" +
"** LogisticRegression\n" +
"** Original **" + getInfo(model3, testData) + "\n" +
"** New **" + getInfo(new Predictor() {double
predict(Vector vector) { return convertedModel3.predict(vector);}}, labels,
features) + "\n" +
"");
}
static Dataset getData(SparkSession spark, String format, String
location) {
return spark.read()
.format(format)
.load(location);
}
static Dataset getDummyData(SparkSession spark, int numberRows, int
numberFeatures, int labelUpperBound) {
StructType schema = new StructType(new StructField[]{
new StructField("label", DataTypes.DoubleType, false,
Metadata.empty()),
new StructField("features", new VectorUDT(), false,
Metadata.empty())
});
double[][] vectors = prepareData(numberRows, numberFeatures);
[jira] [Updated] (SPARK-19449) Inconsistent results between ml package RandomForestClassificationModel and mllib package RandomForestModel
[
https://issues.apache.org/jira/browse/SPARK-19449?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Aseem Bansal updated SPARK-19449:
-
Description:
I worked on some code to convert ml package RandomForestClassificationModel to
mllib package RandomForestModel. It was needed because we need to make
predictions on the order of ms. I found that the results are inconsistent
although the underlying DecisionTreeModel are exactly the same. So the behavior
between the 2 implementations is inconsistent which should not be the case.
The below code can be used to reproduce the issue. Can run this as a simple
Java app as long as you have spark dependencies set up properly.
{noformat}
import org.apache.spark.ml.Transformer;
import org.apache.spark.ml.classification.*;
import org.apache.spark.ml.linalg.*;
import org.apache.spark.ml.regression.RandomForestRegressionModel;
import org.apache.spark.mllib.linalg.DenseVector;
import org.apache.spark.mllib.linalg.Vector;
import org.apache.spark.mllib.tree.configuration.Algo;
import org.apache.spark.mllib.tree.model.DecisionTreeModel;
import org.apache.spark.mllib.tree.model.RandomForestModel;
import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Row;
import org.apache.spark.sql.RowFactory;
import org.apache.spark.sql.SparkSession;
import org.apache.spark.sql.types.DataTypes;
import org.apache.spark.sql.types.Metadata;
import org.apache.spark.sql.types.StructField;
import org.apache.spark.sql.types.StructType;
import scala.Enumeration;
import java.util.ArrayList;
import java.util.List;
import java.util.Random;
abstract class Predictor {
abstract double predict(Vector vector);
}
public class MainConvertModels {
public static final int seed = 42;
public static void main(String[] args) {
int numRows = 1000;
int numFeatures = 3;
int numClasses = 2;
double trainFraction = 0.8;
double testFraction = 0.2;
SparkSession spark = SparkSession.builder()
.appName("conversion app")
.master("local")
.getOrCreate();
//Dataset data = getData(spark, "libsvm",
"/opt/spark2/data/mllib/sample_libsvm_data.txt");
Dataset data = getDummyData(spark, numRows, numFeatures,
numClasses);
Dataset[] splits = data.randomSplit(new double[]{trainFraction,
testFraction}, seed);
Dataset trainingData = splits[0];
Dataset testData = splits[1];
testData.cache();
List labels = getLabels(testData);
List features = getFeatures(testData);
DecisionTreeClassifier classifier1 = new DecisionTreeClassifier();
DecisionTreeClassificationModel model1 = classifier1.fit(trainingData);
final DecisionTreeModel convertedModel1 =
convertDecisionTreeModel(model1, Algo.Classification());
RandomForestClassifier classifier = new RandomForestClassifier();
RandomForestClassificationModel model2 = classifier.fit(trainingData);
final RandomForestModel convertedModel2 =
convertRandomForestModel(model2);
LogisticRegression lr = new LogisticRegression();
LogisticRegressionModel model3 = lr.fit(trainingData);
final org.apache.spark.mllib.classification.LogisticRegressionModel
convertedModel3 = convertLogisticRegressionModel(model3);
System.out.println(
"** DecisionTreeClassifier\n" +
"** Original **" + getInfo(model1, testData) + "\n" +
"** New **" + getInfo(new Predictor() {
double predict(Vector vector) {return
convertedModel1.predict(vector);}
}, labels, features) + "\n" +
"\n" +
"** RandomForestClassifier\n" +
"** Original **" + getInfo(model2, testData) + "\n" +
"** New **" + getInfo(new Predictor() {double
predict(Vector vector) {return convertedModel2.predict(vector);}}, labels,
features) + "\n" +
"\n" +
"** LogisticRegression\n" +
"** Original **" + getInfo(model3, testData) + "\n" +
"** New **" + getInfo(new Predictor() {double
predict(Vector vector) { return convertedModel3.predict(vector);}}, labels,
features) + "\n" +
"");
}
static Dataset getData(SparkSession spark, String format, String
location) {
return spark.read()
.format(format)
.load(location);
}
static Dataset getDummyData(SparkSession spark, int numberRows, int
numberFeatures, int labelUpperBound) {
StructType schema = new StructType(new StructField[]{
new StructField("label", DataTypes.DoubleType, false,
Metadata.empty()),
new StructField("features", new VectorUDT(), false,
