贝叶斯定理便是基于下述贝叶斯公式：

P(B|A)随着P(B)和P(A|B)的增长而增长，随着P(A)的增长而减少，即如果A独立于B时被观察到的可能性越大，那么A对B的支持度越小

朴素贝叶斯 

朴素贝叶斯算法是假设各个特征之间相互独立,使用贝叶斯公式进行分类的。请参考：https://blog.csdn.net/amds123/article/details/70173402 

spark NavieBayes 官方示例代码如下：

import org.apache.spark.ml.classification.NaiveBayes
import org.apache.spark.ml.evaluation.MulticlassClassificationEvaluator
import org.apache.spark.sql.SparkSession

object NavieBayesDemo {
  def main(args: Array[String]): Unit = {
    val spark = SparkSession
      .builder
      .appName("NavieBayesDemo").master("local")
      .config("spark.sql.warehouse.dir", "C:\\study\\sparktest")
      .getOrCreate()
    // Load the data stored in LIBSVM format as a DataFrame.
    val dataset=spark.read.format("libsvm").load("data/mllib/sample_libsvm_data.txt")
    // Split the data into training and test sets (30% held out for testing)
    val Array(tranningData,testData)=dataset.randomSplit(Array(0.7,0.3),seed = 1234L)

    // Train a NavieBayes model
    val model = new NaiveBayes().fit(tranningData)
    // Select example rows to display.
    val predictions=model.transform(testData)
    predictions.show()

    // Select (prediction, true label) and compute test error
    val evaluator = new MulticlassClassificationEvaluator()
      .setLabelCol("label")
      .setPredictionCol("prediction")
      .setMetricName("accuracy")
    val accuracy = evaluator.evaluate(predictions)
    println(s"Test set accuracy = $accuracy")

    spark.stop()
  }
}

运行结果如下：

Test set accuracy = 1.0