我希望將嵌套的 json 分解為 CSV 文件。希望將嵌套的 json 解析為行和列。
from pyspark.sql import SparkSession
from pyspark.sql import SQLContext
from pyspark.sql.types import *
from pyspark.sql import functions as F
from pyspark.sql import Row
df=spark.read.option("multiline","true").json("sample1.json")
df.printSchema()
root
|-- pid: struct (nullable = true)
| |-- Body: struct (nullable = true)
| | |-- Vendor: struct (nullable = true)
| | | |-- RC: struct (nullable = true)
| | | | |-- Updated_From_Date: string (nullable = true)
| | | | |-- Updated_To_Date: string (nullable = true)
| | | |-- RD: struct (nullable = true)
| | | | |-- Supplier: struct (nullable = true)
| | | | | |-- Supplier_Data: struct (nullable = true)
| | | | | | |-- Days: long (nullable = true)
| | | | | | |-- Reference: struct (nullable = true)
| | | | | | | |-- ID: array (nullable = true)
| | | | | | | | |-- element: string (containsNull = true)
| | | | | | |-- Expected: long (nullable = true)
| | | | | | |-- Payments: long (nullable = true)
| | | | | | |-- Approval: struct (nullable = true)
| | | | | | | |-- ID: array (nullable = true)
| | | | | | | | |-- element: string (containsNull = true)
| | | | | | |-- Areas_Changed: struct (nullable = true)
| | | | | | | |-- Alternate_Names: long (nullable = true)
| | | | | | | |-- Attachments: long (nullable = true)
| | | | | | | |-- Classifications: long (nullable = true)
| | | | | | | |-- Contact_Information: long (nullable = true)
我的代碼：
df2=(df.select(F.explode("pid").alias('pid'))
.select('pid.*')
.select(F.explode('Body').alias('Body'))
.select('Body.*')
.select((F.explode('Vendor').alias('Vendor'))
.select('Vendor.*')
.select((F.explode('RC').alias('RC'))
.select('RC.*'))))
錯誤：AnalysisException：由於數據類型不匹配而無法解析“explode(pid)”：函數explode的輸入應該是數組或映射類型，而不是struct<Body:struct< .....
如何解析為結構字段。任何幫助都感激不盡 ：）
您explode只能在地圖或數組類型上使用函數。要訪問 strcut 類型，只需使用.運算符。
假設您想在 RC 和 RD 下獲取列，則代碼語法應如下所示。
df.select("pid.Body.Vendor.RC.*", "pid.Body.Vendor.RD.*")
本文收集自互联网，转载请注明来源。
如有侵权，请联系 [email protected] 删除。
我来说两句