init: pruebas_jupyter analysis from fn_registry

2026-04-06 00:57:00 +02:00
commit b63e145953
15 changed files with 3094 additions and 0 deletions
@@ -0,0 +1,40 @@
+# JUPYTER HABILITADO EN ESTE ANALISIS
+
+## Reglas OBLIGATORIAS para Claude
+
+### 1. CODIGO INMUTABLE — NUNCA MODIFICAR CELDAS EXISTENTES
+- **PROHIBIDO** usar NotebookEdit para reemplazar celdas existentes
+- **SIEMPRE** anadir celdas NUEVAS al final del notebook
+- Si hay un error en una celda, crear celda nueva con la correccion
+- El historial de trabajo debe quedar intacto para trazabilidad
+
+### 2. PROGRAMACION FUNCIONAL OBLIGATORIA
+- **Funciones puras**: sin efectos secundarios, mismo input -> mismo output
+- **Inmutabilidad**: nunca mutar datos, crear copias transformadas
+- **Composicion**: funciones pequenas que se combinan
+- Preferir: `map`, `filter`, `reduce`, list comprehensions
+- Evitar: loops con mutacion, `global`, modificar argumentos in-place
+
+### 3. SIEMPRE usar MCP jupyter para ejecutar codigo Python
+- Las ejecuciones se ven en tiempo real en Jupyter Lab del usuario
+- Compartimos variables y estado del kernel
+- **NUNCA usar bash para ejecutar Python en este analisis**
+
+### 4. Verificar Jupyter activo ANTES de ejecutar
+- Si no esta activo: pedir al usuario que ejecute `./run-jupyter-lab.sh`
+
+### 5. Gestion de notebooks
+- Notebooks en la carpeta `notebooks/` o subcarpetas
+- Si un notebook tiene >50 celdas, crear uno nuevo
+- Nombrar descriptivamente: `01_exploracion.ipynb`, `02_limpieza.ipynb`
+
+### 6. Gestion de Python
+- **SIEMPRE usar `uv`** para gestionar dependencias
+- Anadir paquetes con `uv add nombre_paquete`
+
+### 7. Acceso al fn_registry
+- `FN_REGISTRY_ROOT` apunta a la raiz del registry
+- Para importar funciones Python: `sys.path.insert(0, os.path.join(os.environ["FN_REGISTRY_ROOT"], "python", "functions"))`
+- Para consultar registry.db: `sqlite3` o `import sqlite3` con la ruta `$FN_REGISTRY_ROOT/registry.db`
+
+
@@ -0,0 +1,83 @@
+"""
+fn_registry kernel startup
+Autoconfigura acceso al registry en cada notebook.
+Generado por write_jupyter_registry_kernel (fn_registry).
+"""
+import os
+import sys
+import sqlite3
+from pathlib import Path
+
+# ── FN_REGISTRY_ROOT ────────────────────────────────────────
+FN_REGISTRY_ROOT = Path("/home/lucas/fn_registry")
+os.environ["FN_REGISTRY_ROOT"] = str(FN_REGISTRY_ROOT)
+
+# ── sys.path: importar funciones Python del registry ────────
+_python_functions = FN_REGISTRY_ROOT / "python" / "functions"
+for _domain in sorted(_python_functions.iterdir()) if _python_functions.exists() else []:
+    if _domain.is_dir() and not _domain.name.startswith("_"):
+        _path = str(_domain)
+        if _path not in sys.path:
+            sys.path.insert(0, _path)
+
+# Tambien el directorio padre para imports por dominio: from core import filter_list
+_pf = str(_python_functions)
+if _pf not in sys.path:
+    sys.path.insert(0, _pf)
+
+# ── fn_query: consultar registry.db desde el notebook ───────
+_REGISTRY_DB = FN_REGISTRY_ROOT / "registry.db"
+
+def fn_query(sql, params=()):
+    """Ejecuta una consulta SQL sobre registry.db y retorna las filas.
+
+    Ejemplos:
+        fn_query("SELECT id, description FROM functions WHERE domain = ?", ("finance",))
+        fn_query("SELECT id FROM functions_fts WHERE functions_fts MATCH ?", ("slice*",))
+    """
+    if not _REGISTRY_DB.exists():
+        raise FileNotFoundError(f"registry.db no encontrado en {_REGISTRY_DB}")
+    con = sqlite3.connect(str(_REGISTRY_DB))
+    con.row_factory = sqlite3.Row
+    try:
+        rows = con.execute(sql, params).fetchall()
+        return [dict(r) for r in rows]
+    finally:
+        con.close()
+
+def fn_search(term):
+    """Busca funciones y tipos en el registry por nombre o descripcion.
+
+    Ejemplo:
+        fn_search("slice")
+        fn_search("finance")
+    """
+    fts_term = f"name:{term}* OR description:{term}*"
+    functions = fn_query(
+        "SELECT id, kind, purity, lang, description FROM functions "
+        "WHERE id IN (SELECT id FROM functions_fts WHERE functions_fts MATCH ?) "
+        "ORDER BY name", (fts_term,)
+    )
+    types = fn_query(
+        "SELECT id, algebraic, lang, description FROM types "
+        "WHERE id IN (SELECT id FROM types_fts WHERE types_fts MATCH ?) "
+        "ORDER BY name", (fts_term,)
+    )
+    return {"functions": functions, "types": types}
+
+def fn_code(function_id):
+    """Retorna el codigo fuente de una funcion del registry.
+
+    Ejemplo:
+        print(fn_code("filter_list_py_core"))
+    """
+    rows = fn_query("SELECT code FROM functions WHERE id = ?", (function_id,))
+    if not rows:
+        raise KeyError(f"Funcion no encontrada: {function_id}")
+    return rows[0]["code"]
+
+# ── Mensaje de bienvenida ───────────────────────────────────
+print(f"fn_registry conectado: {FN_REGISTRY_ROOT}")
+print(f"  registry.db: {'OK' if _REGISTRY_DB.exists() else 'NO ENCONTRADO'}")
+print(f"  Python functions: {_pf}")
+print(f"  Helpers: fn_query(), fn_search(), fn_code()")
@@ -0,0 +1 @@
+8889
@@ -0,0 +1,7 @@
+{
+  "7797bfb7-3715-4278-af72-e58efc1a1ba5": {
+    "version": "2.3.0",
+    "created_at": "2026-04-02T14:52:18.179611+00:00",
+    "document_version": "2.0.0"
+  }
+}
@@ -0,0 +1,12 @@
+{
+  "mcpServers": {
+    "jupyter": {
+      "command": "/home/lucas/fn_registry/analysis/pruebas_jupyter/.venv/bin/python",
+      "args": ["-m", "jupyter_mcp_server.server"],
+      "env": {
+        "SERVER_URL": "http://localhost:8889",
+        "TOKEN": ""
+      }
+    }
+  }
+}
@@ -0,0 +1 @@
+3.13
@@ -0,0 +1,6 @@
+def main():
+    print("Hello from pruebas-jupyter!")
+
+
+if __name__ == "__main__":
+    main()
@@ -0,0 +1,72 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "intro",
+   "metadata": {},
+   "source": [
+    "# Test de ejecucion remota\n",
+    "Verificar comportamiento de [*] y outputs incrementales"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "cell-quick",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print('hello world')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "cell-sleep",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import time\n",
+    "for i in range(5):\n",
+    "    print(f'Step {i+1}/5')\n",
+    "    time.sleep(2)\n",
+    "print('Done!')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "cell-progress",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import time, sys\n",
+    "for i in range(10):\n",
+    "    print(f'Progress: {(i+1)*10}%', flush=True)\n",
+    "    time.sleep(1)\n",
+    "print('Finished!')"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.13.7"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
@@ -0,0 +1,201 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "intro",
+   "metadata": {},
+   "source": [
+    "# Test de ejecucion remota\n",
+    "Verificar comportamiento de [*] y outputs incrementales"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "cell-quick",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "hello world\n"
+     ]
+    }
+   ],
+   "source": [
+    "print('hello world')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "cell-sleep",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Step 1/5\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Step 2/5\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Step 3/5\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Step 4/5\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Step 5/5\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Done!\n"
+     ]
+    }
+   ],
+   "source": [
+    "import time\n",
+    "for i in range(5):\n",
+    "    print(f'Step {i+1}/5')\n",
+    "    time.sleep(2)\n",
+    "print('Done!')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "cell-progress",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Progress: 10%\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Progress: 20%\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Progress: 30%\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Progress: 40%\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Progress: 50%\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Progress: 60%\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Progress: 70%\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Progress: 80%\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Progress: 90%\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Progress: 100%\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Finished!\n"
+     ]
+    }
+   ],
+   "source": [
+    "import time, sys\n",
+    "for i in range(10):\n",
+    "    print(f'Progress: {(i+1)*10}%', flush=True)\n",
+    "    time.sleep(1)\n",
+    "print('Finished!')"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.13.7"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
@@ -0,0 +1,15 @@
+[project]
+name = "pruebas-jupyter"
+version = "0.1.0"
+description = "Add your description here"
+readme = "README.md"
+requires-python = ">=3.13"
+dependencies = [
+    "jupyter>=1.1.1",
+    "jupyter-collaboration>=4.3.0",
+    "jupyter-mcp-server>=0.4.0",
+    "jupyterlab>=4.5.6",
+    "matplotlib>=3.10.8",
+    "numpy>=2.4.4",
+    "pandas>=3.0.2",
+]
@@ -0,0 +1,45 @@
+#!/bin/bash
+# Jupyter Lab — modo colaborativo con autodeteccion de puerto
+# Generado por write_jupyter_launcher (fn_registry)
+
+find_free_port() {
+    for port in 8888 8889 8890 8891 8892 8893 8894 8895 8896 8897 8898 8899; do
+        if ! ss -tln 2>/dev/null | grep -q ":${port} " && \
+           ! lsof -i:"$port" >/dev/null 2>&1; then
+            echo $port
+            return
+        fi
+    done
+    echo 8888
+}
+
+PORT=${1:-$(find_free_port)}
+cd "$(dirname "$0")"
+
+echo $PORT > .jupyter-port
+
+source .venv/bin/activate 2>/dev/null || true
+
+if ! python -c "import jupyter_collaboration" 2>/dev/null; then
+    echo "ERROR: jupyter-collaboration no esta instalado"
+    echo "Instala con: uv add jupyter-collaboration"
+    exit 1
+fi
+
+echo "════════════════════════════════════════════════"
+echo "  Jupyter Lab + Colaboracion en puerto $PORT"
+echo "════════════════════════════════════════════════"
+echo ""
+echo "  Abre: http://localhost:$PORT"
+echo "  Ctrl+C para detener"
+echo ""
+
+jupyter lab \
+    --port=$PORT \
+    --no-browser \
+    --ServerApp.token='' \
+    --ServerApp.password='' \
+    --ServerApp.disable_check_xsrf=True \
+    --ServerApp.allow_origin='*' \
+    --ServerApp.root_dir="$(pwd)" \
+    --collaborative
@@ -0,0 +1,62 @@
+"""Test: ejecutar celda en thread para que Y.js sincronice en tiempo real."""
+
+import asyncio
+import json
+import sys
+from functools import partial
+from urllib.request import Request, urlopen
+
+from jupyter_kernel_client import KernelClient
+from jupyter_nbmodel_client import NbModelClient, get_jupyter_notebook_websocket_url
+
+
+def _api_get(url, token=""):
+    headers = {"Accept": "application/json"}
+    if token:
+        headers["Authorization"] = f"token {token}"
+    req = Request(url, headers=headers)
+    with urlopen(req, timeout=5) as resp:
+        return json.loads(resp.read())
+
+
+def _resolve_kernel_id(server_url, token, notebook_path):
+    sessions = _api_get(f"{server_url}/api/sessions", token) or []
+    for s in sessions:
+        nb = s.get("notebook", s.get("path", {}))
+        p = nb.get("path", nb) if isinstance(nb, dict) else str(nb)
+        if p == notebook_path:
+            return s.get("kernel", {}).get("id")
+    return None
+
+
+async def execute_realtime(notebook_path, cell_index, server_url="http://localhost:8889", token=""):
+    ws_url = get_jupyter_notebook_websocket_url(server_url, notebook_path, token or None)
+    kernel_id = _resolve_kernel_id(server_url, token, notebook_path)
+    me = _api_get(f"{server_url}/api/me", token)
+    username = me.get("identity", {}).get("display_name", "Anonymous") if me else "Anonymous"
+
+    async with NbModelClient(ws_url, username=username) as nb:
+        await nb.wait_until_synced()
+
+        with KernelClient(server_url=server_url, token=token, kernel_id=kernel_id) as kernel:
+            # KEY FIX: run blocking execute_cell in a thread so the event loop
+            # keeps running and Y.js can sync outputs to the browser in real-time
+            loop = asyncio.get_event_loop()
+            result = await loop.run_in_executor(
+                None,
+                partial(nb.execute_cell, cell_index, kernel),
+            )
+
+        # Give Y.js a moment to flush final state
+        await asyncio.sleep(2)
+
+    return result
+
+
+if __name__ == "__main__":
+    notebook = sys.argv[1] if len(sys.argv) > 1 else "notebooks/01_test_sleep.ipynb"
+    cell = int(sys.argv[2]) if len(sys.argv) > 2 else 3
+
+    print(f"Executing cell {cell} of {notebook} (watch your browser!)...")
+    result = asyncio.run(execute_realtime(notebook, cell))
+    print(json.dumps(result, ensure_ascii=False, indent=2))