[Spark] Pyspark dataframe 안의 List 처리하는 방법

data = {
    'parent': [{
        'id': 'id_1',
	    'category': 'category_1',
    }, {
        'id': 'id_2',
	    'category': 'category_2',
    }]
}

df = spark.createDataFrame([data])
df.printSchema()
df.show(truncate=False)

df = df.select(explode(df.parent))

df.printSchema()
df.show(truncate=False)

root
 |-- parent: array (nullable = true)
 |    |-- element: map (containsNull = true)
 |    |    |-- key: string
 |    |    |-- value: string (valueContainsNull = true)

+----------------------------------------------------------------------------+
|parent                                                                      |
+----------------------------------------------------------------------------+
|[{category -> category_1, id -> id_1}, {category -> category_2, id -> id_2}]|
+----------------------------------------------------------------------------+

root
 |-- col: map (nullable = true)
 |    |-- key: string
 |    |-- value: string (valueContainsNull = true)

+------------------------------------+
|col                                 |
+------------------------------------+
|{category -> category_1, id -> id_1}|
|{category -> category_2, id -> id_2}|
+------------------------------------+