[Case Study]Logistic Regression using Python, Scala and Java

是 否 +2 论坛币

k人 参与回答

经管之家送您一份

应届毕业生专属福利!

求职就业群

赵安豆老师微信：zhaoandou666

经管之家联合CDA

送您一个全额奖学金名额~ !

立即领取

感谢您参与论坛问题回答

经管之家送您两个论坛币！

+2 论坛币

Python

1. points = spark.textFile(...).map(parsePoint).cache()
   
2. w = numpy.random.ranf(size = D) # current separating plane
   
3. for i in range(ITERATIONS):
   
4.     gradient = points.map(
   
5.         lambda p: (1 / (1 + exp(-p.y*(w.dot(p.x)))) - 1) * p.y * p.x
   
6.     ).reduce(lambda a, b: a + b)
   
7.     w -= gradient
   
8. print "Final separating plane: %s" % w

复制代码

Scala

1. val points = spark.textFile(...).map(parsePoint).cache()
   
2. var w = Vector.random(D) // current separating plane
   
3. for (i <- 1 to ITERATIONS) {
   
4.   val gradient = points.map(p =>
   
5.     (1 / (1 + exp(-p.y*(w dot p.x))) - 1) * p.y * p.x
   
6.   ).reduce(_ + _)
   
7.   w -= gradient
   
8. }
   
9. println("Final separating plane: " + w)

复制代码

Java

1. class ComputeGradient extends Function<DataPoint, Vector> {
   
2.   private Vector w;
   
3.   ComputeGradient(Vector w) { this.w = w; }
   
4.   public Vector call(DataPoint p) {
   
5.     return p.x.times(p.y * (1 / (1 + Math.exp(w.dot(p.x))) - 1));
   
6.   }
   
7. }
   
8. 
   
9. JavaRDD<DataPoint> points = spark.textFile(...).map(new ParsePoint()).cache();
   
10. Vector w = Vector.random(D); // current separating plane
    
11. for (int i = 0; i < ITERATIONS; i++) {
    
12.   Vector gradient = points.map(new ComputeGradient(w)).reduce(new AddVectors());
    
13.   w = w.subtract(gradient);
    
14. }
    
15. System.out.println("Final separating plane: " + w);

复制代码

扫码加我 拉你入群

请注明：姓名-公司-职位

以便审核进群资格，未注明则拒绝

分享0 收藏0 回帖

关键词：regression Case study regressio logistic regress Java