Я использую maven с scala архетипом. Я получаю эту ошибку:
"значение $не является членом StringContext"
Я уже пытался добавить несколько вещей в pom.xml, но ничего не получилось очень хорошо...
Мой код:
import org.apache.spark.ml.evaluation.RegressionEvaluator
import org.apache.spark.ml.regression.LinearRegression
import org.apache.spark.ml.tuning.{ParamGridBuilder, TrainValidationSplit}
// To see less warnings
import org.apache.log4j._
Logger.getLogger("org").setLevel(Level.ERROR)
// Start a simple Spark Session
import org.apache.spark.sql.SparkSession
val spark = SparkSession.builder().getOrCreate()
// Prepare training and test data.
val data = spark.read.option("header","true").option("inferSchema","true").format("csv").load("USA_Housing.csv")
// Check out the Data
data.printSchema()
// See an example of what the data looks like
// by printing out a Row
val colnames = data.columns
val firstrow = data.head(1)(0)
println("\n")
println("Example Data Row")
for(ind <- Range(1,colnames.length)){
println(colnames(ind))
println(firstrow(ind))
println("\n")
}
////////////////////////////////////////////////////
//// Setting Up DataFrame for Machine Learning ////
//////////////////////////////////////////////////
// A few things we need to do before Spark can accept the data!
// It needs to be in the form of two columns
// ("label","features")
// This will allow us to join multiple feature columns
// into a single column of an array of feautre values
import org.apache.spark.ml.feature.VectorAssembler
import org.apache.spark.ml.linalg.Vectors
// Rename Price to label column for naming convention.
// Grab only numerical columns from the data
val df = data.select(data("Price").as("label"),$"Avg Area Income",$"Avg Area House Age",$"Avg Area Number of Rooms",$"Area Population")
// An assembler converts the input values to a vector
// A vector is what the ML algorithm reads to train a model
// Set the input columns from which we are supposed to read the values
// Set the name of the column where the vector will be stored
val assembler = new VectorAssembler().setInputCols(Array("Avg Area Income","Avg Area House Age","Avg Area Number of Rooms","Area Population")).setOutputCol("features")
// Use the assembler to transform our DataFrame to the two columns
val output = assembler.transform(df).select($"label",$"features")
// Create a Linear Regression Model object
val lr = new LinearRegression()
// Fit the model to the data
// Note: Later we will see why we should split
// the data first, but for now we will fit to all the data.
val lrModel = lr.fit(output)
// Print the coefficients and intercept for linear regression
println(s"Coefficients: ${lrModel.coefficients} Intercept: ${lrModel.intercept}")
// Summarize the model over the training set and print out some metrics!
// Explore this in the spark-shell for more methods to call
val trainingSummary = lrModel.summary
println(s"numIterations: ${trainingSummary.totalIterations}")
println(s"objectiveHistory: ${trainingSummary.objectiveHistory.toList}")
trainingSummary.residuals.show()
println(s"RMSE: ${trainingSummary.rootMeanSquaredError}")
println(s"MSE: ${trainingSummary.meanSquaredError}")
println(s"r2: ${trainingSummary.r2}")
и мой pom.xml:
<project xmlns="http://maven.apache.org/POM/4.0.0"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/maven-v4_0_0.xsd">
<modelVersion>4.0.0</modelVersion>
<groupId>test</groupId>
<artifactId>outrotest</artifactId>
<version>1.0-SNAPSHOT</version>
<name>${project.artifactId}</name>
<description>My wonderfull scala app</description>
<inceptionYear>2015</inceptionYear>
<licenses>
<license>
<name>My License</name>
<url>http://....</url>
<distribution>repo</distribution>
</license>
</licenses>
<properties>
<maven.compiler.source>1.6</maven.compiler.source>
<maven.compiler.target>1.6</maven.compiler.target>
<encoding>UTF-8</encoding>
<scala.version>2.11.5</scala.version>
<scala.compat.version>2.11</scala.compat.version>
</properties>
<dependencies>
<dependency>
<groupId>org.scala-lang</groupId>
<artifactId>scala-library</artifactId>
<version>${scala.version}</version>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-mllib_2.11</artifactId>
<version>2.0.1</version>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-core_2.11</artifactId>
<version>2.0.1</version>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-sql_2.11</artifactId>
<version>2.0.2</version>
</dependency>
<dependency>
<groupId>com.databricks</groupId>
<artifactId>spark-csv_2.11</artifactId>
<version>1.5.0</version>
</dependency>
<!-- Test -->
<dependency>
<groupId>junit</groupId>
<artifactId>junit</artifactId>
<version>4.11</version>
<scope>test</scope>
</dependency>
<dependency>
<groupId>org.specs2</groupId>
<artifactId>specs2-junit_${scala.compat.version}</artifactId>
<version>2.4.16</version>
<scope>test</scope>
</dependency>
<dependency>
<groupId>org.specs2</groupId>
<artifactId>specs2-core_${scala.compat.version}</artifactId>
<version>2.4.16</version>
<scope>test</scope>
</dependency>
<dependency>
<groupId>org.scalatest</groupId>
<artifactId>scalatest_${scala.compat.version}</artifactId>
<version>2.2.4</version>
<scope>test</scope>
</dependency>
</dependencies>
<build>
<sourceDirectory>src/main/scala</sourceDirectory>
<testSourceDirectory>src/test/scala</testSourceDirectory>
<plugins>
<plugin>
<!-- see http://davidb.github.com/scala-maven-plugin -->
<groupId>net.alchim31.maven</groupId>
<artifactId>scala-maven-plugin</artifactId>
<version>3.2.0</version>
<executions>
<execution>
<goals>
<goal>compile</goal>
<goal>testCompile</goal>
</goals>
<configuration>
<args>
<!--<arg>-make:transitive</arg>-->
<arg>-dependencyfile</arg>
<arg>${project.build.directory}/.scala_dependencies</arg>
</args>
</configuration>
</execution>
</executions>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-surefire-plugin</artifactId>
<version>2.18.1</version>
<configuration>
<useFile>false</useFile>
<disableXmlReport>true</disableXmlReport>
<!-- If you have classpath issue like NoDefClassError,... -->
<!-- useManifestOnlyJar>false</useManifestOnlyJar -->
<includes>
<include>**/*Test.*</include>
<include>**/*Suite.*</include>
</includes>
</configuration>
</plugin>
</plugins>
</build>
</project>
Я понятия не имею, как это исправить. Кто-нибудь знает?