我正在尝试在Scala Spark中实现一些代码,其中我有一个多类Logistic回归模型,并且该模型生成系数矩阵。
这是代码-
val training = spark.read.format("libsvm").load("data/mllib/sample_multiclass_classification_data.txt")
training.show(false)
+-----+-----------------------------------------------------------+
|label|features |
+-----+-----------------------------------------------------------+
|1.0 |(4,[0,1,2,3],[-0.222222,0.5,-0.762712,-0.833333]) |
|1.0 |(4,[-0.555556,0.25,-0.864407,-0.916667]) |
|1.0 |(4,[-0.722222,-0.166667,-0.833333]) |
|1.0 |(4,0.166667,-0.694915,-0.916667]) |
|0.0 |(4,[0.166667,-0.416667,0.457627,0.5]) |
|1.0 |(4,[-0.833333,-0.916667]) |
|2.0 |(4,[-1.32455E-7,0.220339,0.0833333]) |
|2.0 |(4,-0.333333,0.0169491,-4.03573E-8])|
|1.0 |(4,[-0.5,0.75,-0.830508,-1.0]) |
|0.0 |(4,[0.611111,0.694915,0.416667]) |
|0.0 |(4,[0.222222,0.423729,0.583333]) |
|1.0 |(4,-1.0]) |
|1.0 |(4,-0.916667]) |
|2.0 |(4,0.0508474,-4.03573E-8]) |
|2.0 |(4,[-0.0555556,-0.833333,-0.25]) |
|2.0 |(4,[-0.166667,-0.0169491,-0.0833333]) |
|1.0 |(4,[-0.944444,-0.898305,[-0.277778,-0.583333,-0.166667]) |
|0.0 |(4,[0.111111,0.38983,0.166667]) |
|2.0 |(4,0.0847457,-0.0833333]) |
+-----+-----------------------------------------------------------+
我要为其拟合模型的3个标签。
scala> training.select("label").distinct.show
+-----+
|label|
+-----+
| 0.0|
| 1.0|
| 2.0|
+-----+
拟合Logistic回归模型
import org.apache.spark.ml.classification.LogisticRegression
val lr = new LogisticRegression().setMaxIter(10).setRegParam(0.3).setElasticNetParam(0.8)
// Fit the model
val lrModel = lr.fit(training)
现在,当我尝试查看系数矩阵时,它给了我一个具有3行(3个标签)和4列(4个输入功能)的矩阵
scala> lrModel.coefficientMatrix.toDense
res13: org.apache.spark.ml.linalg.DenseMatrix =
0.0 0.0 0.0 0.3176483191238039
0.0 0.0 -0.7803943459681859 -0.3769611423403096
0.0 0.0 0.0 0.0
这是每个标签的截距-
scala> lrModel.interceptVector
res15: org.apache.spark.ml.linalg.Vector = [0.05165231659832854,-0.12391224990853622,0.07225993331020768]
我想使用系数矩阵和截距矢量创建特征重要性火花数据帧,以得到最终的最终数据帧,如下所示-
label feature name coefficient intercept
0 0 0 0.051
0 1 0 0.051
0 2 0 0.051
0 3 0.3176 0.051
1 0 0 -0.123
1 1 0 -0.123
1 2 -0.78 -0.123
1 3 -0.37 -0.123
2 0 0 0.072
2 1 0 0.072
2 2 0 0.072
2 3 0 0.072
每个要素的每个标签都有一个系数,因此输出中的总记录为labels * features
,即3 * 4 = 12
我希望此过程是动态的,可以将其包装在一个函数中,以便可以将其重新用于任何数量的功能和标签。
我正在从这里读取数据-https://github.com/apache/spark/blob/master/data/mllib/sample_multiclass_classification_data.txt