Big data & Spark

import random

# Generate a deterministic mock broadcast of a small lookup table
# with 5 keys and random integer values (seeded for reproducibility)

data = {
    "sensor_a": 22,
    "sensor_b": 87,
    "sensor_c": 43,
    "sensor_d": 65,
    "sensor_e": 31,
}

# Simulate a broadcast to subscribers by iterating and p…

from collections import defaultdict

class MockUDAF:
    """A minimal mock of a User-Defined Aggregate Function.

    Simulates aggregate lifecycle: initialize, update per row,
    and finalize the result.
    """

    def __init__(self):
        self._buffer = defaultdict(int)

    def initialize(self):
        """Re…