{
"test_id": "sample",
"pyspark_version": "3.5",
"generated_at": "2025-10-27T14:26:14.431642",
"input_data": [
{
"id": 1,
"name": "Alice",
"age": 25,
"salary": 50000.0,
"department": "IT"
},
{
"id": 2,
"name": "Bob",
"age": 30,
"salary": 60000.0,
"department": "HR"
},
{
"id": 3,
"name": "Charlie",
"age": 35,
"salary": 70000.0,
"department": "IT"
},
{
"id": 4,
"name": "David",
"age": 40,
"salary": 80000.0,
"department": "Finance"
}
],
"operation": "DataFrame operation: sample",
"expected_output": {
"schema": {
"field_count": 5,
"field_names": [
"age",
"department",
"id",
"name",
"salary"
],
"field_types": [
"long",
"string",
"long",
"string",
"double"
],
"fields": [
{
"name": "age",
"type": "long",
"nullable": true
},
{
"name": "department",
"type": "string",
"nullable": true
},
{
"name": "id",
"type": "long",
"nullable": true
},
{
"name": "name",
"type": "string",
"nullable": true
},
{
"name": "salary",
"type": "double",
"nullable": true
}
]
},
"data": [
{
"age": 25,
"department": "IT",
"id": 1,
"name": "Alice",
"salary": 50000.0
},
{
"age": 35,
"department": "IT",
"id": 3,
"name": "Charlie",
"salary": 70000.0
}
],
"row_count": 2
}
}