离群值的查找及处理 构造数据 # 导包 from pyspark import SparkContext from pyspark.sql.session import SparkSession # 连接 sc = SparkContext.getOrCreate() spark = SparkSession(sc) # 生成数据 df_outliers = spark.createDataFrame([ (1, 144.5, 5.9, 33,), (2, 167.2, 5.4, 45,), (3, 124.1, 5.5