egutierrez
63a9cb5273
Datascience: aggregate_by_group, deduplicate_entities/relations, detect_drift, diff_entities/relations, extract_entities/relations_llm, hotness_score, melt, merge_graphs, pivot, build_entity/relation_schema_prompt. Finance: avellaneda_stoikov_quotes, generate_gbm_prices, generate_taker_order, hawkes_intensity + módulo finance.py. Cybersecurity: envelope_encrypt/decrypt + módulo cybersecurity.py. Pipelines: extraction_pipeline, monte_carlo_market, run_market_sim. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
83 lines
2.8 KiB
Python
83 lines
2.8 KiB
Python
"""diff_relations — compara dos snapshots de relaciones con key compuesta."""
|
|
|
|
|
|
def diff_relations(
|
|
before: list[dict],
|
|
after: list[dict],
|
|
key: tuple[str, str, str] = ("source_id", "target_id", "relation_type"),
|
|
ignore_fields: list[str] | None = None,
|
|
compare_fields: list[str] | None = None,
|
|
) -> dict:
|
|
"""Compara relaciones entre dos snapshots usando key compuesta.
|
|
|
|
Las relaciones se identifican por (source_id, target_id, relation_type)
|
|
porque no tienen un ID unico propio. Detecta relaciones añadidas,
|
|
eliminadas y modificadas (mismo source/target/type, distinta metadata).
|
|
|
|
Args:
|
|
before: Lista de relaciones del snapshot anterior.
|
|
after: Lista de relaciones del snapshot posterior.
|
|
key: Tupla de campos que forman la key compuesta.
|
|
Default ("source_id", "target_id", "relation_type").
|
|
ignore_fields: Campos a excluir de la comparacion.
|
|
Default ["created_at", "updated_at"].
|
|
compare_fields: Si se da, solo compara estos campos.
|
|
|
|
Returns:
|
|
Dict con keys: added, removed, modified, unchanged, summary.
|
|
modified contiene lista de {"key": str, "changes": {"field": {"old": ..., "new": ...}}}.
|
|
"""
|
|
if ignore_fields is None:
|
|
ignore_fields = ["created_at", "updated_at"]
|
|
|
|
def make_key(rel: dict) -> str:
|
|
return "|".join(str(rel.get(k, "")) for k in key)
|
|
|
|
before_map = {make_key(r): r for r in before}
|
|
after_map = {make_key(r): r for r in after}
|
|
|
|
before_keys = set(before_map.keys())
|
|
after_keys = set(after_map.keys())
|
|
|
|
added = [after_map[k] for k in after_keys - before_keys]
|
|
removed = [before_map[k] for k in before_keys - after_keys]
|
|
|
|
modified = []
|
|
unchanged = 0
|
|
|
|
for k in before_keys & after_keys:
|
|
b = before_map[k]
|
|
a = after_map[k]
|
|
|
|
if compare_fields is not None:
|
|
fields_to_check = compare_fields
|
|
else:
|
|
all_fields = set(b.keys()) | set(a.keys())
|
|
key_set = set(key)
|
|
fields_to_check = [f for f in all_fields if f not in ignore_fields and f not in key_set]
|
|
|
|
changes = {}
|
|
for field in fields_to_check:
|
|
old_val = b.get(field)
|
|
new_val = a.get(field)
|
|
if old_val != new_val:
|
|
changes[field] = {"old": old_val, "new": new_val}
|
|
|
|
if changes:
|
|
modified.append({"key": k, "changes": changes})
|
|
else:
|
|
unchanged += 1
|
|
|
|
n_added = len(added)
|
|
n_removed = len(removed)
|
|
n_modified = len(modified)
|
|
summary = f"{n_added} added, {n_removed} removed, {n_modified} modified, {unchanged} unchanged"
|
|
|
|
return {
|
|
"added": added,
|
|
"removed": removed,
|
|
"modified": modified,
|
|
"unchanged": unchanged,
|
|
"summary": summary,
|
|
}
|