軟件版本：
CDH:5.8.0 , CDH-hadoop :2.6.0 ; CDH-spark :1.6.0
目標：
使用Spark 加載PMML文件到模型，並使用Spark平臺進行預測（這裏測試使用的是Spark on YARN的方式）。
具體小目標：
1. 參考https://github.com/jpmml/jpmml-spark 實現，能運行簡單例子；
2. 直接讀取HDFS上面的輸入數據文件，使用PMML生成的模型進行預測；
（第1點和第2點的不一樣的地方體現在輸入數據的構造上，可以參看下面的代碼）
具體步驟：
1. 準備原始數據，原始數據包括PMML文件，以及測試數據；分別如下：
<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
<PMML version="4.2" xmlns="http://www.dmg.org/PMML-4_2">
<Header description="linear SVM">
<Application name="Apache Spark MLlib"/>
<Timestamp>2016-11-16T22:17:47</Timestamp>
</Header>
<DataDictionary numberOfFields="4">
<DataField name="field_0" optype="continuous" dataType="double"/>
<DataField name="field_1" optype="continuous" dataType="double"/>
<DataField name="field_2" optype="continuous" dataType="double"/>
<DataField name="target" optype="categorical" dataType="string"/>
</DataDictionary>
<RegressionModel modelName="linear SVM" functionName="classification" normalizationMethod="none">
<MiningSchema>
<MiningField name="field_0" usageType="active"/>
<MiningField name="field_1" usageType="active"/>
<MiningField name="field_2" usageType="active"/>
<MiningField name="target" usageType="target"/>
</MiningSchema>
<RegressionTable intercept="0.0" targetCategory="1">
<NumericPredictor name="field_0" coefficient="-0.36682158807862086"/>
<NumericPredictor name="field_1" coefficient="3.8787681305811765"/>
<NumericPredictor name="field_2" coefficient="-1.6134308474471166"/>
</RegressionTable>
<RegressionTable intercept="0.0" targetCategory="0"/>
</RegressionModel>
</PMML>
輸入測試數據，如下：
field_0,field_1,field_2
98,97,96
1,2,72. 把https://github.com/jpmml/jpmml-spark工程下載到本地，並添加如下代碼：
package org.jpmml.spark;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.ml.Transformer;
import org.apache.spark.sql.*;
import org.jpmml.evaluator.Evaluator;
public class SVMEvaluationSparkExample {
static
public void main(String... args) throws Exception {
if(args.length != 3){
System.err.println("Usage: java " + SVMEvaluationSparkExample.class.getName() + " <PMML file> <Input file> <Output directory>");
System.exit(-1);
}
/**
* 根據pmml文件，構建模型
*/
FileSystem fs = FileSystem.get(new Configuration());
Evaluator evaluator = EvaluatorUtil.createEvaluator(fs.open(new Path(args[0])));
TransformerBuilder modelBuilder = new TransformerBuilder(evaluator)
.withTargetCols()
.withOutputCols()
.exploded(true);
Transformer transformer = modelBuilder.build();
/**
* 利用DataFrameReader從原始數據中構造 DataFrame對象
* 需要原始數據包含列名
*/
SparkConf conf = new SparkConf();
try(JavaSparkContext sparkContext = new JavaSparkContext(conf)){
SQLContext sqlContext = new SQLContext(sparkContext);
DataFrameReader reader = sqlContext.read()
.format("com.databricks.spark.csv")
.option("header", "true")
.option("inferSchema", "true");
DataFrame dataFrame = reader.load(args[1]);// 輸入數據需要包含列名
/**
* 使用模型進行預測
*/
dataFrame = transformer.transform(dataFrame);
/**
* 寫入數據
*/
DataFrameWriter writer = dataFrame.write()
.format("com.databricks.spark.csv")
.option("header", "true");
writer.save(args[2]);
}
}
}注意裏面在構造數據的時候.option("header","true")是一定要加的，原因如下：1）原始數據中確實有列名；2）如果這裏不加，那麼將讀取不到列名的相關信息，將不能和模型中的列名對應；（當然，下面有其他方法處理這種情況）。
3. 上傳測試數據以及pmml文件到HDFS，進行測試，代碼如下：
spark-submit --master yarn --class org.jpmml.spark.SVMEvaluationSparkExample /opt/tmp/example-1.0-SNAPSHOT.jar hdfs://quickstart.cloudera:8020/tmp/svm/part-00000 sample_test_data.txt sample_out00查看結果：
根據輸出的結果，也可以看出預測結果是對的。
4. 如何實現小目標2呢？
編寫代碼：
/*
* Copyright (c) 2015 Villu Ruusmann
*
* This file is part of JPMML-Spark
*
* JPMML-Spark is free software: you can redistribute it and/or modify
* it under the terms of the GNU Affero General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* JPMML-Spark is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU Affero General Public License for more details.
*
* You should have received a copy of the GNU Affero General Public License
* along with JPMML-Spark. If not, see <http://www.gnu.org/licenses/>.
*/
package org.jpmml.spark;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.api.java.function.Function;
import org.apache.spark.ml.Transformer;
import org.apache.spark.sql.*;
import org.apache.spark.sql.types.DataTypes;
import org.apache.spark.sql.types.StructField;
import org.apache.spark.sql.types.StructType;
import org.dmg.pmml.FieldName;
import org.jpmml.evaluator.Evaluator;
import java.util.ArrayList;
import java.util.List;
//import org.jpmml.evaluator.FieldValue;
public class EvaluationSparkExample {
static
public void main(String... args) throws Exception {
if(args.length != 3){
System.err.println("Usage: java " + EvaluationSparkExample.class.getName() + " <PMML file> <Input file> <Output directory>");
System.exit(-1);
}
/**
* 構造模型
*/
FileSystem fs = FileSystem.get(new Configuration());
Evaluator evaluator = EvaluatorUtil.createEvaluator(fs.open(new Path(args[0])));
TransformerBuilder modelBuilder = new TransformerBuilder(evaluator)
.withTargetCols()
.withOutputCols()
.exploded(true);
Transformer transformer = modelBuilder.build();
/**
* 構造列名,schema
*/
List<StructField> fields = new ArrayList<>();
for (FieldName fieldName: evaluator.getActiveFields()) {
fields.add(DataTypes.createStructField(fieldName.getValue(), DataTypes.StringType, true));
}
StructType schema = DataTypes.createStructType(fields);
/**
* 原始數據構造成DataFrame
*/
SparkConf conf = new SparkConf();
final String splitter = ",";
try(JavaSparkContext sparkContext = new JavaSparkContext(conf)){
JavaRDD<Row> data = sparkContext.textFile(args[1]).map(new Function<String, Row>() {
@Override
public Row call(String line) throws Exception {
String[] lineArr = line.split(splitter,-1);
return RowFactory.create(lineArr);
}
});
SQLContext sqlContext = new SQLContext(sparkContext);
DataFrame dataFrame = sqlContext.createDataFrame(data, schema);
/**
* 預測，並生成新的DataFrame
*/
dataFrame = transformer.transform(dataFrame);
/**
* 把評估後的數據寫入HDFS，不要寫入列名
*/
DataFrameWriter writer = dataFrame.write()
.format("com.databricks.spark.csv");
writer.save(args[2]);
}
}
}
其調用代碼如下所示：
spark-submit --master yarn --class org.jpmml.spark.EvaluationSparkExample /opt/tmp/example-1.0-SNAPSHOT.jar hdfs://quickstart.cloudera:8020/tmp/svm/part-00000 sample_test_data1.txt sample_out02分享，成長，快樂
轉載請註明blog地址：http://blog.csdn.net/fansy1990