在pyspark中将yyyymmdd转换为MM-dd-yyyy格式

2 回答

• 2

  from datetime import datetime
  from pyspark.sql.functions import col,udf
  from pyspark.sql.types import DateType
  
  
  rdd = sc.parallelize(['20161231', '20140102', '20151201', '20161124'])
  df1 = sqlContext.createDataFrame(rdd, ['old_col'])
  
  //UDF to convert string to date
  func =  udf (lambda x: datetime.strptime(x, '%Y%M%d'), DateType())
  
  df = df1.withColumn('new_col', date_format(func(col('old_col')), 'MM-dd-yyy'))
  
  df.show()
  

  回复于 2024-04-25T06:59:32+08:00
• 0

  这也有效：

  from datetime import datetime
  from pyspark.sql.functions import col,udf,unix_timestamp
  from pyspark.sql.types import DateType
  
  
  func =  udf(lambda x: datetime.strptime(str(x), '%m%d%y'), DateType())
  
  df2 = df.withColumn('date', func(col('InvcDate')))
  

  回复于 2024-04-25T06:59:32+08:00