spark常用代码集合（一）

• 1、读写CSV文件
• 2、修改数据类型
• 3、删除重复的列

val df1 = spark.read.csv("hdfs://106.12.48.46:9000/sparktest/服创大赛-原始数据.csv").toDF("timestamp","imsi","lac_id","cell_id","phone","timestamp1","tmp0","tmp1","nid","npid")

df1.select(df1("timestamp").cast("int"))

df1.dropDuplicates()