How to create a list json using Pyspark? - python-3.x

Question

I am trying to create a json file with below structure using Pyspark.
Target Output:
[{
"Loaded_data": [{
"Loaded_numeric_columns": ["id", "val"],
"Loaded_category_columns": ["name", "branch"]
}],
"enriched_data": [{
"enriched_category_columns": ["country__4"],
"enriched_index_columns": ["id__1", "val__3"]
}]
}]
I could able to create list for each section . Please refer below code. I kind of stuck here, could you please help.
Sample data:
input_data=spark.read.csv("/tmp/test234.csv",header=True, inferSchema=True)
def is_numeric(data_type):
return data_type not in ('date', 'string', 'boolean')
def is_nonnumeric(data_type):
return data_type in ('string')
sub="__"
Loaded_numeric_columns = [name for name, data_type in input_data.dtypes if is_numeric(data_type) and (sub not in name)]
print Loaded_numeric_columns
Loaded_category_columns = [name for name, data_type in input_data.dtypes if is_nonnumeric(data_type) and (sub not in name)]
print Loaded_category_columns
enriched_category_columns = [name for name, data_type in input_data.dtypes if is_nonnumeric(data_type) and (sub in name)]
print enriched_category_columns
enriched_index_columns = [name for name, data_type in input_data.dtypes if is_numeric(data_type) and (sub in name)]
print enriched_index_columns

Answer 1

You can just create the new column type with struct and array :
from pyspark.sql import functions as F
df.show()
+---+-----+-------+------+----------+-----+-------+
| id| val| name|branch|country__4|id__1| val__3|
+---+-----+-------+------+----------+-----+-------+
| 1|67.87|Shankar| a| 1|67.87|Shankar|
+---+-----+-------+------+----------+-----+-------+
df.select(
F.struct(
F.array(F.col("id"), F.col("val")).alias("Loaded_numeric_columns"),
F.array(F.col("name"), F.col("branch")).alias("Loaded_category_columns"),
).alias("Loaded_data"),
F.struct(
F.array(F.col("country__4")).alias("enriched_category_columns"),
F.array(F.col("id__1"), F.col("val__3")).alias("enriched_index_columns"),
).alias("enriched_data"),
).printSchema()
root
|-- Loaded_data: struct (nullable = false)
| |-- Loaded_numeric_columns: array (nullable = false)
| | |-- element: double (containsNull = true)
| |-- Loaded_category_columns: array (nullable = false)
| | |-- element: string (containsNull = true)
|-- enriched_data: struct (nullable = false)
| |-- enriched_category_columns: array (nullable = false)
| | |-- element: long (containsNull = true)
| |-- enriched_index_columns: array (nullable = false)
| | |-- element: string (containsNull = true)