{
"test_id": "hash",
"pyspark_version": "3.5",
"generated_at": "2025-10-27T14:13:29.209172",
"input_data": [
{
"id": 1,
"name": "Alice",
"text": "Hello World"
},
{
"id": 2,
"name": "Bob",
"text": "Test"
},
{
"id": 3,
"name": "Charlie",
"text": "Python"
}
],
"operation": "DataFrame operation: hash",
"expected_output": {
"schema": {
"field_count": 1,
"field_names": [
"hash(name)"
],
"field_types": [
"integer"
],
"fields": [
{
"name": "hash(name)",
"type": "integer",
"nullable": false
}
]
},
"data": [
{
"hash(name)": -1597477876
},
{
"hash(name)": 549595493
},
{
"hash(name)": 906014075
}
],
"row_count": 3
}
}