feat: funciones Python datascience, finance, cybersecurity y pipelines

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>
2026-04-05 17:11:32 +02:00
parent 25a392df48
commit 63a9cb5273
62 changed files with 5376 additions and 0 deletions
@@ -0,0 +1,77 @@
+"""diff_entities — compara dos snapshots de entities detectando cambios campo a campo."""
+
+
+def diff_entities(
+    before: list[dict],
+    after: list[dict],
+    key: str = "id",
+    ignore_fields: list[str] | None = None,
+    compare_fields: list[str] | None = None,
+) -> dict:
+    """Compara dos snapshots de entities y devuelve diferencias campo a campo.
+
+    Detecta entities añadidas, eliminadas, modificadas e inalteradas.
+    Ignora campos de metadata temporal por defecto (created_at, updated_at).
+
+    Args:
+        before: Lista de entities del snapshot anterior.
+        after: Lista de entities del snapshot posterior.
+        key: Campo que identifica unicamente cada entity. Default "id".
+        ignore_fields: Campos a excluir de la comparacion.
+                       Default ["created_at", "updated_at"].
+        compare_fields: Si se da, solo compara estos campos (tiene prioridad
+                        sobre ignore_fields).
+
+    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"]
+
+    before_map = {str(e[key]): e for e in before if key in e}
+    after_map = {str(e[key]): e for e in after if key in e}
+
+    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())
+            fields_to_check = [f for f in all_fields if f not in ignore_fields and f != key]
+
+        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,
+    }