使用spark mllib识别LED数字

来源：互联网发布：线切割编程基础知识编辑：程序博客网时间：2024/06/05 18:12

最近在学习spark mllib，突然有个想法，能否利用mllib来识别LED数字呢？

说干就干，先在纸上画出了0-9的LED显示，然后教儿子怎么把每个数字转成一个向量：

我和儿子共同完成的LED数字

然后准备一个文本文件labeled-points.txt：

(0,[1,1,1,0,1,1,1])(1,[0,0,1,0,0,1,0])(2,[1,0,1,1,1,0,1])(3,[1,0,1,1,0,1,1])(4,[0,1,1,1,0,1,0])(5,[1,1,0,1,0,1,1])(6,[1,1,0,1,1,1,1])(7,[1,0,1,0,0,1,0])(8,[1,1,1,1,1,1,1])(9,[1,1,1,1,0,1,1])

这个应该是个分类问题，选用LogisticRegressionWithLBFGS：

import org.apache.spark.SparkContextimport org.apache.spark.mllib.classification.{LogisticRegressionWithLBFGS, LogisticRegressionModel}import org.apache.spark.mllib.evaluation.MulticlassMetricsimport org.apache.spark.mllib.regression.LabeledPointimport org.apache.spark.mllib.linalg.Vectorsimport org.apache.spark.mllib.util.MLUtilsval data = MLUtils.loadLabeledPoints(sc,"file:///labeled-points.txt")val model = new LogisticRegressionWithLBFGS().setNumClasses(10).run(data)

最后随便拿出一个数字，让它来猜猜：

model.predict(Vectors.dense(Array(1.0,1.0,0.0,1.0,1.0,1.0,1.0)))res24: Double = 6.0

怎么样？还是不错的吧~~~
这个model的权重好像很多：

scala> model.weightsres29: org.apache.spark.mllib.linalg.Vector = [-30.68420353263392,-13.819117851407729,20.27517376062209,-17.878063796956003,-8.641455334351308,30.780101010826108,-17.243132942967932,11.509783689282543,-14.900033352764835,11.684427660291847,12.07060530601555,17.31310120498649,-59.232219286895614,11.386593790510851,5.090436073435982,-25.983226739036247,3.8562537560950205,10.30603523382833,-14.356520662249086,-0.8387336591993536,9.557546094038313,-31.853702036193578,14.47383139964512,8.794502062134377,13.95757471451068,-9.84270147539397,8.893604711671909,-20.982818493822286,6.522677078631281,10.241387441753627,-40.12363598646755,8.698186733644015,-17.906199015916943,3.8333204609982374,8.050490292724493,2.3703073829997034,7.401912395339493,-46.95213122452467,9.951675789189242,19.38502076196...

真的很累啊^_^

0 0