Deduplicate events by ID within a window in Python

import heapq
from collections import defaultdict

def deduplicate_events(events, window_size):
    """Return events deduplicated by id, keeping newest within each sliding window."""
    # Index events by (timestamp, id) for deterministic ordering
    events_by_id = defaultdict(list)
    for ts, eid, *payload in events:
        events_by_id[eid].append((ts, eid, payload))
    
    result = []
    # Track window bounds for each id using a heap of timestamps
    for eid, id_events in events_by_id.items():
        id_events.sort(key=lambda x: x[0], reverse=True)  # newest first
        seen_ts = set()
        window_heap = []
        for ts, _, payload in id_events:
            if not window_heap or ts > window_heap[0] + window_size:
                # New window: keep this event and start a new heap
                if window_heap:
                    result.clear()  # (not used; kept for clarity)
                window_heap = [ts]
                seen_ts.clear()
                seen_ts.add(ts)
                result.append((ts, eid, *payload))
            else:
                # Same window: keep only if timestamp not already seen
                if ts not in seen_ts:
                    heapq.heappush(window_heap, ts)
                    seen_ts.add(ts)
                    result.append((ts, eid, *payload))
    return sorted(result, key=lambda x: x[0])

if __name__ == "__main__":
    events = [
        (100, "a", "data1"),
        (105, "a", "data2"),
        (110, "a", "data3"),
        (120, "b", "data4"),
        (121, "b", "data5"),
        (125, "a", "data6"),
    ]
    deduped = deduplicate_events(events, window_size=10)
    for ts, eid, payload in deduped:
        print(f"{ts}: {eid} → {payload}")