假期学习14

今天原来是情人节，但想到情侣不能约会，就超级开心，也成功的做完了全部的实验项目，收获很大，对新的语言有了一定的了解。

下面是实验的部分代码:

scala> val labelIndexer = new 
StringIndexer().setInputCol("label").setOutputCol("indexedLabel").fit(result)
labelIndexer: org.apache.spark.ml.feature.StringIndexerModel = strIdx_6721796011c5
scala> labelIndexer.labels.foreach(println)
<=50K
>50K
 
scala> val featureIndexer = new 
VectorIndexer().setInputCol("pcaFeatures").setOutputCol("indexedFeatures").fit(result)
featureIndexer: org.apache.spark.ml.feature.VectorIndexerModel = vecIdx_7b6672933fc3
scala> println(featureIndexer.numFeatures)
3
 
scala> val labelConverter = new 
IndexToString().setInputCol("prediction").setOutputCol("predictedLabel").setLabels(labelIndexer.
labels)
labelConverter: org.apache.spark.ml.feature.IndexToString = idxToStr_d0c9321aaaa9
scala> val lr = new 
LogisticRegression().setLabelCol("indexedLabel").setFeaturesCol("indexedFeatures").setMaxIter(
100)
lr: org.apache.spark.ml.classification.LogisticRegression = logreg_06812b41b118
 
scala> val lrPipeline = new Pipeline().setStages(Array(labelIndexer, featureIndexer, lr, 
labelConverter))
lrPipeline: org.apache.spark.ml.Pipeline = pipeline_b6b87b6e8cd5
scala> val lrPipelineModel = lrPipeline.fit(result)
lrPipelineModel: org.apache.spark.ml.PipelineModel = pipeline_b6b87b6e8cd5
scala> val lrModel = lrPipelineModel.stages(2).asInstanceOf[LogisticRegressionModel]
lrModel: org.apache.spark.ml.classification.LogisticRegressionModel = logreg_06812b41b118
scala> println("Coefficients: " + lrModel.coefficientMatrix+"Intercept: 
"+lrModel.interceptVector+"numClasses: "+lrModel.numClasses+"numFeatures: 
"+lrModel.numFeatures)
Coefficients: -1.9828586428133616E-7 -3.5090924715811705E-4 -8.451506276498941E-4 
Intercept: [-1.4525982557843347]numClasses: 2numFeatures: 3
 
scala> val lrPredictions = lrPipelineModel.transform(testdata)
lrPredictions: org.apache.spark.sql.DataFrame = [features: vector, label: string ... 7 more fields]
scala> val evaluator = new 
MulticlassClassificationEvaluator().setLabelCol("indexedLabel").setPredictionCol("prediction")
evaluator: org.apache.spark.ml.evaluation.MulticlassClassificationEvaluator = 
mcEval_38ac5c14fa2a
scala> val lrAccuracy = evaluator.evaluate(lrPredictions)
lrAccuracy: Double = 0.7764235163053484
scala> println("Test Error = " + (1.0 - lrAccuracy))
Test Error = 0.22357648369465155