如何解决将文件转换为余弦相似度的字符串
我有两个 csv 文件,其中包含 userId、MovieId、tags.tags 列包含喜剧领域的电影类型。我需要喜剧和喜剧相关标签之间的相似性。我想将文件转换为字符串来计算余弦相似性。
val lines = scala.io.source.fromFile("file:///usr/local/spark/dataset/algorithm3/comedy").getLines.mkString
val lines2=scala.io.source.fromFile("file:///usr/local/spark/dataset/algorithm3/funny").getLines().mkString("\n")
import java.nio.file.Files
import java.nio.file.Paths
val result=textCosine(lines,lines2)
println("The cosine similarity score: "+result)
}
/**
* Modular length of the vector
* @param vec
*/
def module(vec:Vector[Double]): Double ={
// math.sqrt( vec.map(x=>x*x).sum )
math.sqrt(vec.map(math.pow(_,2)).sum)
}
/**
* Find the inner product of two vectors
* @param v1
* @param v2
*/
def innerProduct(v1:Vector[Double],v2:Vector[Double]): Double ={
val listBuffer=ListBuffer[Double]()
for(i<- 0 until v1.length; j<- 0 until v2.length;if i==j){
if(i==j){
listBuffer.append( v1(i)*v2(j) )
}
}
listBuffer.sum
}
/**
* Find the cosine of two vectors
* @param v1
* @param v2
*/
def cosvec(v1:Vector[Double],v2:Vector[Double]):Double ={
val cos=innerProduct(v1,v2) / (module(v1)* module(v2))
if (cos <= 1) cos else 1.0
}
def textCosine(lines:String,lines2:String):Double={
val set=mutable.Set[Char]() //Count all words in two sentences
lines.foreach(set +=_)
lines2.foreach(set +=_)
println(set)
val ints1: Vector[Double] = set.toList.sorted.map(ch => {
lines.count(s => s == ch).todouble
}).toVector
println("===ints1: "+ints1)
val ints2: Vector[Double] = set.toList.sorted.map(ch => {
lines2.count(s => s == ch).todouble
}).toVector
println("===ints2: "+ints2)
cosvec(ints1,ints2)
}
}
但是出现这个错误
Exception in thread "main" java.io.FileNotFoundException: file:/usr/local/spark/dataset/algorithm3/comedy (No such file or directory)
at java.io.FileInputStream.open0(Native Method)
at java.io.FileInputStream.open(FileInputStream.java:195)
at java.io.FileInputStream.<init>(FileInputStream.java:138)
我该如何解决?
版权声明:本文内容由互联网用户自发贡献,该文观点与技术仅代表作者本人。本站仅提供信息存储空间服务,不拥有所有权,不承担相关法律责任。如发现本站有涉嫌侵权/违法违规的内容, 请发送邮件至 dio@foxmail.com 举报,一经查实,本站将立刻删除。