Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
|
@@ -1,13 +1,13 @@
|
|
| 1 |
"""
|
| 2 |
-
CÓDIGO COMPLETO Y CORREGIDO - VERSIÓN 7.
|
| 3 |
-
- MEJORA MAYOR: Se ha
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
|
| 8 |
-
|
| 9 |
-
|
| 10 |
-
|
| 11 |
"""
|
| 12 |
|
| 13 |
import gradio as gr
|
|
@@ -16,14 +16,21 @@ import pandas as pd
|
|
| 16 |
import json
|
| 17 |
import tempfile
|
| 18 |
import os
|
|
|
|
| 19 |
from datetime import datetime
|
| 20 |
import plotly.graph_objects as go
|
| 21 |
import logging
|
| 22 |
import numpy as np
|
|
|
|
| 23 |
|
| 24 |
# --- CONFIGURACIÓN Y CLIENTES ---
|
| 25 |
-
logging.basicConfig(level=logging.INFO)
|
| 26 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 27 |
|
| 28 |
try: biotech_client = Client("C2MV/BiotechU4"); logger.info("✅ Cliente BiotechU4 inicializado.")
|
| 29 |
except: biotech_client = None
|
|
@@ -35,12 +42,9 @@ except: analysis_client = None
|
|
| 35 |
# ============================================================================
|
| 36 |
|
| 37 |
class LoggingAgent:
|
| 38 |
-
"""Agente 4: Registra todas las acciones para transparencia total."""
|
| 39 |
def __init__(self): self.log_entries, self.start_time = [], datetime.now(); logger.info("🕵️ LoggingAgent activado.")
|
| 40 |
def register(self, agent_name, action, details=""):
|
| 41 |
-
entry = f"**{datetime.now().strftime('%H:%M:%S')} | {agent_name}:** {action}"
|
| 42 |
-
if details: entry += f"\n> *Detalles: {details}*"
|
| 43 |
-
self.log_entries.append(entry)
|
| 44 |
def get_report(self):
|
| 45 |
if not self.log_entries: return "### 🕵️ Informe de Actividad\n\nNo se registraron actividades."
|
| 46 |
return "### 🕵️ Informe de Actividad de Agentes\n\n---\n\n" + "\n\n---\n\n".join(self.log_entries) + f"\n\n---\n\n**Tiempo total: {(datetime.now() - self.start_time).total_seconds():.2f} s.**"
|
|
@@ -48,7 +52,6 @@ class LoggingAgent:
|
|
| 48 |
|
| 49 |
|
| 50 |
class StructureValidationAgent:
|
| 51 |
-
"""Agente 1: Valida la estructura del archivo y el formato de laboratorio."""
|
| 52 |
def __init__(self, log_agent: LoggingAgent): self.log_agent = log_agent
|
| 53 |
def validate(self, file_obj):
|
| 54 |
try:
|
|
@@ -60,6 +63,51 @@ class StructureValidationAgent:
|
|
| 60 |
return True, "Formato de archivo básico validado."
|
| 61 |
|
| 62 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 63 |
class ModelSelectionAgent:
|
| 64 |
"""Agente 3 (CON FALLBACK CONFIGURABLE): Identifica los mejores modelos, con un plan B personalizable."""
|
| 65 |
def __init__(self, log_agent: LoggingAgent): self.log_agent = log_agent
|
|
@@ -70,15 +118,15 @@ class ModelSelectionAgent:
|
|
| 70 |
if str(col).lower() == name.lower(): return col
|
| 71 |
return None
|
| 72 |
|
| 73 |
-
def identify_best_models(self, results_df, component, r2_threshold, rmse_threshold,
|
| 74 |
self.log_agent.register("ModelSelectionAgent", f"Iniciando identificación para: '{component}'.")
|
| 75 |
|
| 76 |
-
# 1. Normalizar
|
| 77 |
model_col = self._find_column(results_df.columns, ['model', 'modelo'])
|
| 78 |
if not model_col: return [], "Error: No se encontró la columna de nombres de modelos ('Model')."
|
| 79 |
df_norm = results_df.rename(columns={model_col: 'Model'})
|
| 80 |
|
| 81 |
-
# 2. Identificar
|
| 82 |
r2_target_col, rmse_target_col = None, None
|
| 83 |
if component != 'all':
|
| 84 |
r2_target_col = self._find_column(df_norm.columns, [f'r2_{component}'])
|
|
@@ -98,49 +146,45 @@ class ModelSelectionAgent:
|
|
| 98 |
model_performance = df_norm.groupby('Model').agg({r2_target_col: 'mean', rmse_target_col: 'mean'}).reset_index()
|
| 99 |
|
| 100 |
# 4. Intento 1: Filtrado Estricto
|
| 101 |
-
good_models_df = model_performance[
|
| 102 |
-
(model_performance[r2_target_col] >= r2_threshold) &
|
| 103 |
-
(model_performance[rmse_target_col] <= rmse_threshold)
|
| 104 |
-
]
|
| 105 |
|
| 106 |
if not good_models_df.empty:
|
| 107 |
best_models_list = sorted([str(model).lower() for model in good_models_df['Model'].tolist()])
|
| 108 |
reasoning = f"Agente identificó **{len(best_models_list)}** modelo(s) que cumplen tus criterios: `{', '.join(best_models_list)}`."
|
| 109 |
-
self.log_agent.register("ModelSelectionAgent", "Éxito en filtrado primario.", reasoning)
|
| 110 |
return best_models_list, reasoning
|
| 111 |
else:
|
| 112 |
-
# 5. Intento 2: Plan B - Ranking Estratégico
|
| 113 |
-
self.log_agent.register("ModelSelectionAgent", "Filtro primario falló. Activando fallback: '
|
| 114 |
|
| 115 |
-
|
| 116 |
-
|
| 117 |
-
|
| 118 |
-
|
| 119 |
-
|
| 120 |
-
|
| 121 |
-
|
| 122 |
-
|
| 123 |
-
|
| 124 |
-
|
| 125 |
-
#
|
| 126 |
-
|
|
|
|
|
|
|
| 127 |
top_n_df = sorted_performance.head(top_n)
|
| 128 |
-
|
| 129 |
-
if top_n_df.empty:
|
| 130 |
-
return [], "No se encontraron modelos para realizar el ranking del Plan B."
|
| 131 |
|
| 132 |
best_models_list = sorted([str(model).lower() for model in top_n_df['Model'].tolist()])
|
| 133 |
reasoning = (f"**Advertencia:** Ningún modelo cumplió con los criterios iniciales.\n\n"
|
| 134 |
f"Como plan B, el agente ha seleccionado los **Top {len(best_models_list)}** modelos con el mejor **{metric_name} promedio**: `{', '.join(best_models_list)}`.")
|
| 135 |
-
self.log_agent.register("ModelSelectionAgent", "Fallback completado.", reasoning)
|
| 136 |
return best_models_list, reasoning
|
| 137 |
|
| 138 |
# --- INICIALIZACIÓN DE AGENTES GLOBALES ---
|
| 139 |
-
log_agent = LoggingAgent(); validation_agent = StructureValidationAgent(log_agent)
|
|
|
|
|
|
|
| 140 |
|
| 141 |
-
# --- FUNCIONES
|
| 142 |
-
def create_dummy_plot(title="Esperando resultados..."
|
| 143 |
-
fig = go.Figure(go.Scatter(x=[], y=[])); fig.update_layout(title=title, template="plotly_white", height=500, annotations=[dict(text=
|
| 144 |
return fig
|
| 145 |
|
| 146 |
def detect_experiments(file_obj):
|
|
@@ -151,71 +195,64 @@ def detect_experiments(file_obj):
|
|
| 151 |
return gr.update(choices=exp_names, value=exp_names, interactive=True)
|
| 152 |
except Exception as e: return gr.update(choices=[], value=[], interactive=False, placeholder=f"Error: {e}")
|
| 153 |
|
| 154 |
-
#
|
| 155 |
def run_base_analysis(file, models, exp_names_selected, component, use_de, maxfev, progress=gr.Progress()):
|
| 156 |
log_agent.clear(); progress(0, desc="🚀 Iniciando Análisis Base...")
|
| 157 |
if not file or not models or not exp_names_selected:
|
| 158 |
return create_dummy_plot(), None, "❌ Por favor, sube un archivo y selecciona modelos/experimentos.", gr.update(interactive=False), {}, None, None, log_agent.get_report()
|
| 159 |
-
|
| 160 |
log_agent.register("Pipeline (Etapa 1)", "Iniciando Análisis Base."); progress(0.2, desc="Validando archivo...")
|
| 161 |
is_valid, msg = validation_agent.validate(file)
|
| 162 |
if not is_valid: return create_dummy_plot(), None, msg, gr.update(interactive=False), {}, None, None, log_agent.get_report()
|
| 163 |
-
|
| 164 |
progress(0.5, desc="Ejecutando análisis biotecnológico...");
|
| 165 |
if not biotech_client: return create_dummy_plot(), None, "❌ Cliente BiotechU4 no disponible.", gr.update(interactive=False), {}, None, None, log_agent.get_report()
|
| 166 |
-
|
| 167 |
try:
|
| 168 |
-
exp_names_str = ",".join(exp_names_selected)
|
| 169 |
-
models_lower = [str(m).lower() for m in models]
|
| 170 |
plot_info, df_data, status = biotech_client.predict(file=handle_file(file.name), models=models_lower, component=component, use_de=use_de, maxfev=maxfev, exp_names=exp_names_str, api_name="/run_analysis_wrapper")
|
| 171 |
if "Error" in status: raise Exception(status)
|
| 172 |
except Exception as e:
|
| 173 |
return create_dummy_plot(), None, f"❌ Error en Análisis Base: {e}", gr.update(interactive=False), {}, None, None, log_agent.get_report()
|
| 174 |
-
|
| 175 |
progress(1, desc="🎉 Análisis Base Completado")
|
| 176 |
-
final_status =
|
| 177 |
results_df_obj = {'data': df_data['data'], 'headers': df_data['headers']}
|
| 178 |
fig = go.Figure(json.loads(plot_info['plot'])) if plot_info and 'plot' in plot_info else create_dummy_plot()
|
| 179 |
-
original_params = {'
|
| 180 |
-
|
| 181 |
return fig, df_data, final_status, gr.update(interactive=True), results_df_obj, file.name, original_params, log_agent.get_report()
|
| 182 |
|
| 183 |
-
# --- ETAPA 2: REFINAMIENTO Y REPORTE IA ---
|
| 184 |
-
def refine_and_generate_report(baseline_results, file_path, original_params, r2_threshold, rmse_threshold,
|
| 185 |
-
progress(0, desc="🚀 Iniciando Refinamiento con IA..."); log_agent.register("Pipeline (Etapa 2)", "Iniciando Refinamiento
|
| 186 |
if not baseline_results or not file_path or not original_params:
|
| 187 |
return gr.update(), None, None, None, "❌ No hay resultados base para refinar.", None, log_agent.get_report()
|
| 188 |
|
| 189 |
-
progress(0.1, desc="Agente
|
|
|
|
|
|
|
|
|
|
|
|
|
| 190 |
results_df = pd.DataFrame(baseline_results['data'], columns=baseline_results['headers'])
|
| 191 |
-
best_models, reasoning = model_selection_agent.identify_best_models(results_df, original_params['component'], r2_threshold, rmse_threshold,
|
| 192 |
|
| 193 |
if not best_models:
|
| 194 |
return gr.update(), baseline_results, None, None, f"🤖 Análisis del Agente:\n{reasoning}", None, log_agent.get_report()
|
| 195 |
|
| 196 |
-
progress(0.
|
| 197 |
try:
|
| 198 |
exp_names_str = ",".join(original_params['exp_names'])
|
| 199 |
-
final_plot_info, final_df_data, final_status = biotech_client.predict(
|
| 200 |
-
file=handle_file(file_path), models=best_models, component=original_params['component'], use_de=original_params['use_de'],
|
| 201 |
-
maxfev=original_params['maxfev'], exp_names=exp_names_str, api_name="/run_analysis_wrapper"
|
| 202 |
-
)
|
| 203 |
if "Error" in final_status: raise Exception(final_status)
|
| 204 |
-
log_agent.register("BiotechU4 Client", "Re-análisis final completado.", f"Modelos usados: {best_models}")
|
| 205 |
except Exception as e:
|
| 206 |
return gr.update(), None, None, None, f"❌ Error en el re-análisis final: {e}", None, log_agent.get_report()
|
| 207 |
|
| 208 |
-
progress(0.6, desc="
|
| 209 |
try:
|
| 210 |
final_results_df = pd.DataFrame(final_df_data['data'], columns=final_df_data['headers'])
|
| 211 |
with tempfile.NamedTemporaryFile(mode='w+', suffix='.csv', delete=False, encoding='utf-8') as temp_f:
|
| 212 |
final_results_df.to_csv(temp_f.name, index=False); temp_csv_file = temp_f.name
|
| 213 |
-
|
| 214 |
current_analysis_client = analysis_client
|
| 215 |
if use_personal_key and personal_api_key: current_analysis_client = Client("C2MV/Project-HF-2025-2", hf_token=personal_api_key)
|
| 216 |
chunk_update_dict = current_analysis_client.predict(files=[handle_file(temp_csv_file)], api_name="/update_chunk_column_selector")
|
| 217 |
selected_chunk_column = chunk_update_dict['choices'][0][0]
|
| 218 |
-
result = current_analysis_client.predict(files=[handle_file(temp_csv_file)], chunk_column=selected_chunk_column, qwen_model=ia_model, detail_level=detail_level, language=language, additional_specs=
|
| 219 |
_, analysis_report, implementation_code, token_usage = result
|
| 220 |
except Exception as e:
|
| 221 |
return gr.update(), final_df_data, None, None, f"❌ Error generando informe IA: {e}", None, log_agent.get_report()
|
|
@@ -230,10 +267,9 @@ def refine_and_generate_report(baseline_results, file_path, original_params, r2_
|
|
| 230 |
|
| 231 |
final_status = f"✅ Refinamiento y reporte completados.\n{reasoning}\nInforme IA generado con {token_usage}."
|
| 232 |
final_fig = go.Figure(json.loads(final_plot_info['plot'])) if final_plot_info and 'plot' in final_plot_info else create_dummy_plot()
|
| 233 |
-
|
| 234 |
return final_fig, final_df_data, analysis_report, implementation_code, final_status, final_report_path, log_agent.get_report()
|
| 235 |
|
| 236 |
-
#
|
| 237 |
def create_dummy_excel_file():
|
| 238 |
examples_dir = "examples"; os.makedirs(examples_dir, exist_ok=True); file_path = os.path.join(examples_dir, "archivo.xlsx")
|
| 239 |
if not os.path.exists(file_path):
|
|
@@ -254,82 +290,65 @@ theme = gr.themes.Soft(primary_hue="blue", secondary_hue="indigo", neutral_hue="
|
|
| 254 |
if __name__ == "__main__":
|
| 255 |
create_dummy_excel_file()
|
| 256 |
with gr.Blocks(theme=theme, title="BioTech Analysis & Report Generator") as demo:
|
| 257 |
-
gr.Markdown("# 🧬 BioTech Analysis & Report Generator v7.
|
| 258 |
gr.Markdown("### Un pipeline inteligente de dos etapas: Análisis Base y Refinamiento con IA.")
|
| 259 |
baseline_results_state = gr.State(value=None); file_path_state = gr.State(value=None); original_params_state = gr.State(value=None)
|
| 260 |
-
|
| 261 |
with gr.Row():
|
| 262 |
with gr.Column(scale=1):
|
| 263 |
gr.Markdown("### 1. Carga y Configuración del Análisis Base")
|
| 264 |
-
file_input = gr.File(label="📁 Archivo de Datos
|
| 265 |
-
gr.
|
| 266 |
-
|
| 267 |
-
models_input = gr.CheckboxGroup(choices=BIOTECH_MODELS, value=BIOTECH_MODELS, label="📊 Modelos a Evaluar", info="Selecciona todos los modelos para una evaluación completa.")
|
| 268 |
component_input = gr.Dropdown(['all', 'biomass', 'substrate', 'product'], value='all', label="📈 Componente a Analizar/Filtrar")
|
| 269 |
-
with gr.Accordion("Parámetros Avanzados
|
| 270 |
use_de_input = gr.Checkbox(label="🧮 Usar Evolución Diferencial", value=False)
|
| 271 |
maxfev_input = gr.Slider(label="🔄 Máx. Iteraciones", minimum=10000, maximum=100000, value=50000, step=1000)
|
| 272 |
run_base_analysis_btn = gr.Button("1. Ejecutar Análisis Base", variant="secondary")
|
| 273 |
|
| 274 |
with gr.Group():
|
| 275 |
gr.Markdown("### 2. Refinamiento con IA")
|
| 276 |
-
gr.Markdown("#### Criterios de Selección Primarios")
|
| 277 |
-
r2_threshold_slider = gr.Slider(minimum=0.0, maximum=0.99, value=0.
|
| 278 |
-
rmse_threshold_input = gr.Number(value=
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 279 |
|
| 280 |
-
# --- NUEVOS CONTROLES PARA EL PLAN B ---
|
| 281 |
-
gr.Markdown("#### Criterios de Selección Avanzada (Plan B)")
|
| 282 |
-
ranking_metric_input = gr.Radio(
|
| 283 |
-
choices=["R² (más alto es mejor)", "RMSE (más bajo es mejor)"],
|
| 284 |
-
value="R² (más alto es mejor)",
|
| 285 |
-
label="Métrica de Ranking",
|
| 286 |
-
info="Si ningún modelo cumple los criterios primarios, se usará esta métrica para elegir los mejores."
|
| 287 |
-
)
|
| 288 |
-
top_n_input = gr.Slider(
|
| 289 |
-
minimum=1, maximum=5, value=3, step=1,
|
| 290 |
-
label="Top N Modelos a Seleccionar",
|
| 291 |
-
info="Número de modelos a seleccionar en el Plan B."
|
| 292 |
-
)
|
| 293 |
-
|
| 294 |
with gr.Accordion("Parámetros del Informe de IA Final", open=False):
|
| 295 |
ia_model_input = gr.Dropdown(choices=IA_MODELS, value=IA_MODELS[0], label="🤖 Modelo de IA para Informe")
|
| 296 |
detail_level_input = gr.Radio(['detailed', 'summarized'], value='detailed', label="📋 Nivel de Detalle")
|
| 297 |
language_input = gr.Dropdown(['es', 'en'], value='es', label="🌐 Idioma")
|
| 298 |
-
max_output_tokens_input = gr.Slider(minimum=1000, maximum=32000, value=
|
| 299 |
-
additional_specs_input = gr.Textbox(label="📝 Especificaciones Adicionales", lines=2)
|
| 300 |
use_personal_key_input = gr.Checkbox(label="Usar Token HF Personal", value=False)
|
| 301 |
personal_api_key_input = gr.Textbox(label="Token HF", type="password", visible=False)
|
| 302 |
refine_with_ia_btn = gr.Button("2. 🤖 Aplicar Filtro y Generar Informe IA", variant="primary", interactive=False)
|
| 303 |
-
|
| 304 |
with gr.Column(scale=2):
|
| 305 |
gr.Markdown("### 3. Resultados")
|
| 306 |
-
status_output = gr.Textbox(label="📊 Registro de Estado
|
| 307 |
with gr.Tabs():
|
| 308 |
with gr.TabItem("📊 Visualización"): plot_output = gr.Plot()
|
| 309 |
with gr.TabItem("📋 Tabla de Modelado"): table_output = gr.Dataframe()
|
| 310 |
-
with gr.TabItem("📝 Informe IA"): analysis_output = gr.Markdown("El informe
|
| 311 |
with gr.TabItem("💻 Código"): code_output = gr.Code(language="python")
|
| 312 |
-
with gr.TabItem("🕵️ Registro de Agentes
|
| 313 |
-
download_link_markdown = gr.Markdown("*El enlace de descarga aparecerá
|
| 314 |
-
report_output = gr.File(label="📥 Descargar Informe
|
| 315 |
report_path_state = gr.State(value=None)
|
| 316 |
|
| 317 |
-
# --- Lógica de la UI ---
|
| 318 |
file_input.upload(fn=detect_experiments, inputs=file_input, outputs=exp_names_input)
|
| 319 |
use_personal_key_input.change(lambda x: gr.update(visible=x), inputs=use_personal_key_input, outputs=personal_api_key_input)
|
| 320 |
-
|
| 321 |
run_base_analysis_btn.click(
|
| 322 |
fn=run_base_analysis,
|
| 323 |
inputs=[file_input, models_input, exp_names_input, component_input, use_de_input, maxfev_input],
|
| 324 |
outputs=[plot_output, table_output, status_output, refine_with_ia_btn, baseline_results_state, file_path_state, original_params_state, agent_log_output]
|
| 325 |
)
|
| 326 |
-
|
| 327 |
refine_with_ia_btn.click(
|
| 328 |
fn=refine_and_generate_report,
|
| 329 |
-
inputs=[baseline_results_state, file_path_state, original_params_state, r2_threshold_slider, rmse_threshold_input,
|
| 330 |
outputs=[plot_output, table_output, analysis_output, code_output, status_output, report_path_state, agent_log_output]
|
| 331 |
)
|
| 332 |
-
|
| 333 |
def update_dl_link(path):
|
| 334 |
if path and os.path.exists(path): return f"**¡Informe listo!** 👉 [**Descargar '{os.path.basename(path)}'**](/file={path})"
|
| 335 |
return "*No se generó ningún archivo para descargar.*"
|
|
|
|
| 1 |
"""
|
| 2 |
+
CÓDIGO COMPLETO Y CORREGIDO - VERSIÓN 7.8 (Agente de Instrucciones de Lenguaje Natural)
|
| 3 |
+
- MEJORA MAYOR: Se ha creado un nuevo `InstructionParsingAgent` que interpreta las instrucciones
|
| 4 |
+
en lenguaje natural del usuario desde el cuadro de "Especificaciones Adicionales".
|
| 5 |
+
- FUNCIONALIDAD AVANZADA: El usuario puede especificar qué métricas usar (R2, RMSE, o ambas) y
|
| 6 |
+
cuántos "Top N" modelos seleccionar, simplemente escribiéndolo.
|
| 7 |
+
- MODELSELECTIONAGENT MEJORADO: La lógica del "Plan B" ahora es dinámica y se basa en las
|
| 8 |
+
instrucciones parseadas, calculando un score combinado si se especifican múltiples métricas.
|
| 9 |
+
- UI SIMPLIFICADA: Se han eliminado los controles estáticos de ranking, reemplazados por el
|
| 10 |
+
cuadro de texto de instrucciones, haciendo la interfaz más limpia y potente.
|
| 11 |
"""
|
| 12 |
|
| 13 |
import gradio as gr
|
|
|
|
| 16 |
import json
|
| 17 |
import tempfile
|
| 18 |
import os
|
| 19 |
+
import re
|
| 20 |
from datetime import datetime
|
| 21 |
import plotly.graph_objects as go
|
| 22 |
import logging
|
| 23 |
import numpy as np
|
| 24 |
+
from smolagents import CodeAgent, InferenceClientModel
|
| 25 |
|
| 26 |
# --- CONFIGURACIÓN Y CLIENTES ---
|
| 27 |
+
logging.basicConfig(level=logging.INFO); logger = logging.getLogger(__name__)
|
| 28 |
+
|
| 29 |
+
# --- INICIALIZACIÓN DE MODELO PARA AGENTES ---
|
| 30 |
+
try:
|
| 31 |
+
hf_engine = InferenceClientModel(model_id="deepseek-ai/DeepSeek-V2-Lite-Instruct")
|
| 32 |
+
logger.info("✅ Modelo de lenguaje (DeepSeek-V2-Lite) inicializado para agentes.")
|
| 33 |
+
except Exception: hf_engine = None; logger.error("❌ No se pudo inicializar el modelo de lenguaje para agentes.")
|
| 34 |
|
| 35 |
try: biotech_client = Client("C2MV/BiotechU4"); logger.info("✅ Cliente BiotechU4 inicializado.")
|
| 36 |
except: biotech_client = None
|
|
|
|
| 42 |
# ============================================================================
|
| 43 |
|
| 44 |
class LoggingAgent:
|
|
|
|
| 45 |
def __init__(self): self.log_entries, self.start_time = [], datetime.now(); logger.info("🕵️ LoggingAgent activado.")
|
| 46 |
def register(self, agent_name, action, details=""):
|
| 47 |
+
entry = f"**{datetime.now().strftime('%H:%M:%S')} | {agent_name}:** {action}"; self.log_entries.append(entry + (f"\n> *Detalles: {details}*" if details else ""))
|
|
|
|
|
|
|
| 48 |
def get_report(self):
|
| 49 |
if not self.log_entries: return "### 🕵️ Informe de Actividad\n\nNo se registraron actividades."
|
| 50 |
return "### 🕵️ Informe de Actividad de Agentes\n\n---\n\n" + "\n\n---\n\n".join(self.log_entries) + f"\n\n---\n\n**Tiempo total: {(datetime.now() - self.start_time).total_seconds():.2f} s.**"
|
|
|
|
| 52 |
|
| 53 |
|
| 54 |
class StructureValidationAgent:
|
|
|
|
| 55 |
def __init__(self, log_agent: LoggingAgent): self.log_agent = log_agent
|
| 56 |
def validate(self, file_obj):
|
| 57 |
try:
|
|
|
|
| 63 |
return True, "Formato de archivo básico validado."
|
| 64 |
|
| 65 |
|
| 66 |
+
class InstructionParsingAgent:
|
| 67 |
+
"""Agente que convierte el lenguaje natural del usuario en un plan de acción estructurado."""
|
| 68 |
+
def __init__(self, log_agent: LoggingAgent, llm_engine):
|
| 69 |
+
self.log_agent = log_agent
|
| 70 |
+
self.agent = CodeAgent(tools=[], model=llm_engine) if llm_engine else None
|
| 71 |
+
|
| 72 |
+
def parse(self, text: str):
|
| 73 |
+
default_instructions = {'metrics': ['R2'], 'top_n': 3}
|
| 74 |
+
if not self.agent:
|
| 75 |
+
self.log_agent.register("InstructionParsingAgent", "LLM no disponible, usando defaults.")
|
| 76 |
+
return default_instructions
|
| 77 |
+
|
| 78 |
+
prompt = f"""
|
| 79 |
+
Analyze the user's instruction for a data analysis task. Extract the metrics they want to use for ranking and the number of top models to select.
|
| 80 |
+
The possible metrics are "R2", "RMSE".
|
| 81 |
+
Your output MUST be ONLY a valid JSON object with two keys: "metrics" (a list of strings) and "top_n" (an integer).
|
| 82 |
+
|
| 83 |
+
- If the user mentions "R2" or "R-cuadrado", include "R2" in the metrics list.
|
| 84 |
+
- If the user mentions "RMSE", include "RMSE" in the metrics list.
|
| 85 |
+
- If the user mentions a number like "top 3", "los 2 mejores", or just a digit, set "top_n" to that number.
|
| 86 |
+
- If no metrics are mentioned, default to ["R2"].
|
| 87 |
+
- If no number is mentioned, default to 3.
|
| 88 |
+
|
| 89 |
+
Example 1: "Usa el promedio de R2 y RMSE y elige el top 2" -> {{"metrics": ["R2", "RMSE"], "top_n": 2}}
|
| 90 |
+
Example 2: "dame los 3 mejores modelos segun el menor RMSE" -> {{"metrics": ["RMSE"], "top_n": 3}}
|
| 91 |
+
Example 3: "el mejor R2" -> {{"metrics": ["R2"], "top_n": 1}}
|
| 92 |
+
Example 4: "analizar los datos" -> {{"metrics": ["R2"], "top_n": 3}}
|
| 93 |
+
|
| 94 |
+
User instruction: "{text}"
|
| 95 |
+
JSON Output:
|
| 96 |
+
"""
|
| 97 |
+
try:
|
| 98 |
+
response_str = self.agent.run(prompt)
|
| 99 |
+
json_str = response_str[response_str.find('{'):response_str.rfind('}')+1]
|
| 100 |
+
instructions = json.loads(json_str)
|
| 101 |
+
# Validar que el formato es correcto
|
| 102 |
+
if 'metrics' not in instructions or 'top_n' not in instructions:
|
| 103 |
+
raise ValueError("JSON de salida no contiene las claves esperadas.")
|
| 104 |
+
self.log_agent.register("InstructionParsingAgent", "Instrucciones del usuario parseadas con éxito.")
|
| 105 |
+
return instructions
|
| 106 |
+
except Exception as e:
|
| 107 |
+
self.log_agent.register("InstructionParsingAgent", "Error parseando instrucciones, usando defaults.", f"Error: {e}")
|
| 108 |
+
return default_instructions
|
| 109 |
+
|
| 110 |
+
|
| 111 |
class ModelSelectionAgent:
|
| 112 |
"""Agente 3 (CON FALLBACK CONFIGURABLE): Identifica los mejores modelos, con un plan B personalizable."""
|
| 113 |
def __init__(self, log_agent: LoggingAgent): self.log_agent = log_agent
|
|
|
|
| 118 |
if str(col).lower() == name.lower(): return col
|
| 119 |
return None
|
| 120 |
|
| 121 |
+
def identify_best_models(self, results_df, component, r2_threshold, rmse_threshold, instructions: dict):
|
| 122 |
self.log_agent.register("ModelSelectionAgent", f"Iniciando identificación para: '{component}'.")
|
| 123 |
|
| 124 |
+
# 1. Normalizar columna del Modelo
|
| 125 |
model_col = self._find_column(results_df.columns, ['model', 'modelo'])
|
| 126 |
if not model_col: return [], "Error: No se encontró la columna de nombres de modelos ('Model')."
|
| 127 |
df_norm = results_df.rename(columns={model_col: 'Model'})
|
| 128 |
|
| 129 |
+
# 2. Identificar columnas de métricas
|
| 130 |
r2_target_col, rmse_target_col = None, None
|
| 131 |
if component != 'all':
|
| 132 |
r2_target_col = self._find_column(df_norm.columns, [f'r2_{component}'])
|
|
|
|
| 146 |
model_performance = df_norm.groupby('Model').agg({r2_target_col: 'mean', rmse_target_col: 'mean'}).reset_index()
|
| 147 |
|
| 148 |
# 4. Intento 1: Filtrado Estricto
|
| 149 |
+
good_models_df = model_performance[(model_performance[r2_target_col] >= r2_threshold) & (model_performance[rmse_target_col] <= rmse_threshold)]
|
|
|
|
|
|
|
|
|
|
| 150 |
|
| 151 |
if not good_models_df.empty:
|
| 152 |
best_models_list = sorted([str(model).lower() for model in good_models_df['Model'].tolist()])
|
| 153 |
reasoning = f"Agente identificó **{len(best_models_list)}** modelo(s) que cumplen tus criterios: `{', '.join(best_models_list)}`."
|
|
|
|
| 154 |
return best_models_list, reasoning
|
| 155 |
else:
|
| 156 |
+
# 5. Intento 2: Plan B - Ranking Estratégico basado en instrucciones
|
| 157 |
+
self.log_agent.register("ModelSelectionAgent", "Filtro primario falló. Activando fallback: 'Ranking por Instrucciones'.", f"Plan: {instructions}")
|
| 158 |
|
| 159 |
+
use_r2 = 'R2' in instructions['metrics']
|
| 160 |
+
use_rmse = 'RMSE' in instructions['metrics']
|
| 161 |
+
top_n = instructions['top_n']
|
| 162 |
+
|
| 163 |
+
# Calcular el score de rendimiento
|
| 164 |
+
if use_r2 and use_rmse:
|
| 165 |
+
model_performance['Score'] = model_performance[r2_target_col] / (model_performance[rmse_target_col] + 1e-9)
|
| 166 |
+
sort_col, ascending, metric_name = 'Score', False, "R²/RMSE combinado"
|
| 167 |
+
elif use_rmse:
|
| 168 |
+
sort_col, ascending, metric_name = rmse_target_col, True, "RMSE"
|
| 169 |
+
else: # Por defecto R2
|
| 170 |
+
sort_col, ascending, metric_name = r2_target_col, False, "R²"
|
| 171 |
+
|
| 172 |
+
sorted_performance = model_performance.sort_values(by=sort_col, ascending=ascending)
|
| 173 |
top_n_df = sorted_performance.head(top_n)
|
|
|
|
|
|
|
|
|
|
| 174 |
|
| 175 |
best_models_list = sorted([str(model).lower() for model in top_n_df['Model'].tolist()])
|
| 176 |
reasoning = (f"**Advertencia:** Ningún modelo cumplió con los criterios iniciales.\n\n"
|
| 177 |
f"Como plan B, el agente ha seleccionado los **Top {len(best_models_list)}** modelos con el mejor **{metric_name} promedio**: `{', '.join(best_models_list)}`.")
|
|
|
|
| 178 |
return best_models_list, reasoning
|
| 179 |
|
| 180 |
# --- INICIALIZACIÓN DE AGENTES GLOBALES ---
|
| 181 |
+
log_agent = LoggingAgent(); validation_agent = StructureValidationAgent(log_agent)
|
| 182 |
+
instruction_parser_agent = InstructionParsingAgent(log_agent, hf_engine)
|
| 183 |
+
model_selection_agent = ModelSelectionAgent(log_agent)
|
| 184 |
|
| 185 |
+
# --- FUNCIONES DEL PIPELINE ---
|
| 186 |
+
def create_dummy_plot(title="Esperando resultados..."):
|
| 187 |
+
fig = go.Figure(go.Scatter(x=[], y=[])); fig.update_layout(title=title, template="plotly_white", height=500, annotations=[dict(text="Sube un archivo y ejecuta", showarrow=False)])
|
| 188 |
return fig
|
| 189 |
|
| 190 |
def detect_experiments(file_obj):
|
|
|
|
| 195 |
return gr.update(choices=exp_names, value=exp_names, interactive=True)
|
| 196 |
except Exception as e: return gr.update(choices=[], value=[], interactive=False, placeholder=f"Error: {e}")
|
| 197 |
|
| 198 |
+
# ... (ETAPA 1: run_base_analysis - sin cambios) ...
|
| 199 |
def run_base_analysis(file, models, exp_names_selected, component, use_de, maxfev, progress=gr.Progress()):
|
| 200 |
log_agent.clear(); progress(0, desc="🚀 Iniciando Análisis Base...")
|
| 201 |
if not file or not models or not exp_names_selected:
|
| 202 |
return create_dummy_plot(), None, "❌ Por favor, sube un archivo y selecciona modelos/experimentos.", gr.update(interactive=False), {}, None, None, log_agent.get_report()
|
|
|
|
| 203 |
log_agent.register("Pipeline (Etapa 1)", "Iniciando Análisis Base."); progress(0.2, desc="Validando archivo...")
|
| 204 |
is_valid, msg = validation_agent.validate(file)
|
| 205 |
if not is_valid: return create_dummy_plot(), None, msg, gr.update(interactive=False), {}, None, None, log_agent.get_report()
|
|
|
|
| 206 |
progress(0.5, desc="Ejecutando análisis biotecnológico...");
|
| 207 |
if not biotech_client: return create_dummy_plot(), None, "❌ Cliente BiotechU4 no disponible.", gr.update(interactive=False), {}, None, None, log_agent.get_report()
|
|
|
|
| 208 |
try:
|
| 209 |
+
exp_names_str = ",".join(exp_names_selected); models_lower = [str(m).lower() for m in models]
|
|
|
|
| 210 |
plot_info, df_data, status = biotech_client.predict(file=handle_file(file.name), models=models_lower, component=component, use_de=use_de, maxfev=maxfev, exp_names=exp_names_str, api_name="/run_analysis_wrapper")
|
| 211 |
if "Error" in status: raise Exception(status)
|
| 212 |
except Exception as e:
|
| 213 |
return create_dummy_plot(), None, f"❌ Error en Análisis Base: {e}", gr.update(interactive=False), {}, None, None, log_agent.get_report()
|
|
|
|
| 214 |
progress(1, desc="🎉 Análisis Base Completado")
|
| 215 |
+
final_status = "✅ Análisis Base completado. \n➡️ Ahora puedes aplicar el filtro de IA y generar el informe final."
|
| 216 |
results_df_obj = {'data': df_data['data'], 'headers': df_data['headers']}
|
| 217 |
fig = go.Figure(json.loads(plot_info['plot'])) if plot_info and 'plot' in plot_info else create_dummy_plot()
|
| 218 |
+
original_params = {'exp_names': exp_names_selected, 'component': component, 'use_de': use_de, 'maxfev': maxfev}
|
|
|
|
| 219 |
return fig, df_data, final_status, gr.update(interactive=True), results_df_obj, file.name, original_params, log_agent.get_report()
|
| 220 |
|
| 221 |
+
# --- ETAPA 2: REFINAMIENTO Y REPORTE IA (ACTUALIZADA) ---
|
| 222 |
+
def refine_and_generate_report(baseline_results, file_path, original_params, r2_threshold, rmse_threshold, instructions_text, ia_model, detail_level, language, max_output_tokens, use_personal_key, personal_api_key, progress=gr.Progress()):
|
| 223 |
+
progress(0, desc="🚀 Iniciando Refinamiento con IA..."); log_agent.register("Pipeline (Etapa 2)", "Iniciando Refinamiento.")
|
| 224 |
if not baseline_results or not file_path or not original_params:
|
| 225 |
return gr.update(), None, None, None, "❌ No hay resultados base para refinar.", None, log_agent.get_report()
|
| 226 |
|
| 227 |
+
progress(0.1, desc="Agente de Parseo interpretando instrucciones...")
|
| 228 |
+
instructions = instruction_parser_agent.parse(instructions_text)
|
| 229 |
+
log_agent.register("InstructionParsingAgent", "Instrucciones interpretadas.", f"Plan: {instructions}")
|
| 230 |
+
|
| 231 |
+
progress(0.2, desc="Agente de Selección identificando mejores modelos...")
|
| 232 |
results_df = pd.DataFrame(baseline_results['data'], columns=baseline_results['headers'])
|
| 233 |
+
best_models, reasoning = model_selection_agent.identify_best_models(results_df, original_params['component'], r2_threshold, rmse_threshold, instructions)
|
| 234 |
|
| 235 |
if not best_models:
|
| 236 |
return gr.update(), baseline_results, None, None, f"🤖 Análisis del Agente:\n{reasoning}", None, log_agent.get_report()
|
| 237 |
|
| 238 |
+
progress(0.4, desc="Re-ejecutando análisis con los mejores modelos...");
|
| 239 |
try:
|
| 240 |
exp_names_str = ",".join(original_params['exp_names'])
|
| 241 |
+
final_plot_info, final_df_data, final_status = biotech_client.predict(file=handle_file(file_path), models=best_models, component=original_params['component'], use_de=original_params['use_de'], maxfev=original_params['maxfev'], exp_names=exp_names_str, api_name="/run_analysis_wrapper")
|
|
|
|
|
|
|
|
|
|
| 242 |
if "Error" in final_status: raise Exception(final_status)
|
|
|
|
| 243 |
except Exception as e:
|
| 244 |
return gr.update(), None, None, None, f"❌ Error en el re-análisis final: {e}", None, log_agent.get_report()
|
| 245 |
|
| 246 |
+
progress(0.6, desc="Generando informe IA..."); temp_csv_file = None
|
| 247 |
try:
|
| 248 |
final_results_df = pd.DataFrame(final_df_data['data'], columns=final_df_data['headers'])
|
| 249 |
with tempfile.NamedTemporaryFile(mode='w+', suffix='.csv', delete=False, encoding='utf-8') as temp_f:
|
| 250 |
final_results_df.to_csv(temp_f.name, index=False); temp_csv_file = temp_f.name
|
|
|
|
| 251 |
current_analysis_client = analysis_client
|
| 252 |
if use_personal_key and personal_api_key: current_analysis_client = Client("C2MV/Project-HF-2025-2", hf_token=personal_api_key)
|
| 253 |
chunk_update_dict = current_analysis_client.predict(files=[handle_file(temp_csv_file)], api_name="/update_chunk_column_selector")
|
| 254 |
selected_chunk_column = chunk_update_dict['choices'][0][0]
|
| 255 |
+
result = current_analysis_client.predict(files=[handle_file(temp_csv_file)], chunk_column=selected_chunk_column, qwen_model=ia_model, detail_level=detail_level, language=language, additional_specs="", max_output_tokens=max_output_tokens, api_name="/process_files_and_analyze")
|
| 256 |
_, analysis_report, implementation_code, token_usage = result
|
| 257 |
except Exception as e:
|
| 258 |
return gr.update(), final_df_data, None, None, f"❌ Error generando informe IA: {e}", None, log_agent.get_report()
|
|
|
|
| 267 |
|
| 268 |
final_status = f"✅ Refinamiento y reporte completados.\n{reasoning}\nInforme IA generado con {token_usage}."
|
| 269 |
final_fig = go.Figure(json.loads(final_plot_info['plot'])) if final_plot_info and 'plot' in final_plot_info else create_dummy_plot()
|
|
|
|
| 270 |
return final_fig, final_df_data, analysis_report, implementation_code, final_status, final_report_path, log_agent.get_report()
|
| 271 |
|
| 272 |
+
# ... (create_dummy_excel_file y constantes sin cambios) ...
|
| 273 |
def create_dummy_excel_file():
|
| 274 |
examples_dir = "examples"; os.makedirs(examples_dir, exist_ok=True); file_path = os.path.join(examples_dir, "archivo.xlsx")
|
| 275 |
if not os.path.exists(file_path):
|
|
|
|
| 290 |
if __name__ == "__main__":
|
| 291 |
create_dummy_excel_file()
|
| 292 |
with gr.Blocks(theme=theme, title="BioTech Analysis & Report Generator") as demo:
|
| 293 |
+
gr.Markdown("# 🧬 BioTech Analysis & Report Generator v7.8")
|
| 294 |
gr.Markdown("### Un pipeline inteligente de dos etapas: Análisis Base y Refinamiento con IA.")
|
| 295 |
baseline_results_state = gr.State(value=None); file_path_state = gr.State(value=None); original_params_state = gr.State(value=None)
|
|
|
|
| 296 |
with gr.Row():
|
| 297 |
with gr.Column(scale=1):
|
| 298 |
gr.Markdown("### 1. Carga y Configuración del Análisis Base")
|
| 299 |
+
file_input = gr.File(label="📁 Archivo de Datos", file_types=[".xlsx", ".xls"]); gr.Examples(examples=["examples/archivo.xlsx"], inputs=[file_input])
|
| 300 |
+
exp_names_input = gr.CheckboxGroup(label="🔬 Experimentos a Analizar", interactive=False)
|
| 301 |
+
models_input = gr.CheckboxGroup(choices=BIOTECH_MODELS, value=BIOTECH_MODELS, label="📊 Modelos a Evaluar")
|
|
|
|
| 302 |
component_input = gr.Dropdown(['all', 'biomass', 'substrate', 'product'], value='all', label="📈 Componente a Analizar/Filtrar")
|
| 303 |
+
with gr.Accordion("Parámetros Avanzados", open=False):
|
| 304 |
use_de_input = gr.Checkbox(label="🧮 Usar Evolución Diferencial", value=False)
|
| 305 |
maxfev_input = gr.Slider(label="🔄 Máx. Iteraciones", minimum=10000, maximum=100000, value=50000, step=1000)
|
| 306 |
run_base_analysis_btn = gr.Button("1. Ejecutar Análisis Base", variant="secondary")
|
| 307 |
|
| 308 |
with gr.Group():
|
| 309 |
gr.Markdown("### 2. Refinamiento con IA")
|
| 310 |
+
gr.Markdown("#### Criterios de Selección Primarios (Filtro Estricto)")
|
| 311 |
+
r2_threshold_slider = gr.Slider(minimum=0.0, maximum=0.99, value=0.9, step=0.01, label="R² Mínimo")
|
| 312 |
+
rmse_threshold_input = gr.Number(value=0.5, label="RMSE Máximo")
|
| 313 |
+
|
| 314 |
+
# --- NUEVO INPUT DE INSTRUCCIONES ---
|
| 315 |
+
additional_specs_input = gr.Textbox(label="📝 Instrucciones para Selección Avanzada (Plan B)",
|
| 316 |
+
placeholder="Ej: Usa R2 y RMSE y dame el top 2",
|
| 317 |
+
info="Si ningún modelo cumple los criterios de arriba, el agente seguirá estas instrucciones.")
|
| 318 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 319 |
with gr.Accordion("Parámetros del Informe de IA Final", open=False):
|
| 320 |
ia_model_input = gr.Dropdown(choices=IA_MODELS, value=IA_MODELS[0], label="🤖 Modelo de IA para Informe")
|
| 321 |
detail_level_input = gr.Radio(['detailed', 'summarized'], value='detailed', label="📋 Nivel de Detalle")
|
| 322 |
language_input = gr.Dropdown(['es', 'en'], value='es', label="🌐 Idioma")
|
| 323 |
+
max_output_tokens_input = gr.Slider(minimum=1000, maximum=32000, value=8000, step=100, label="🔢 Máx. Tokens")
|
|
|
|
| 324 |
use_personal_key_input = gr.Checkbox(label="Usar Token HF Personal", value=False)
|
| 325 |
personal_api_key_input = gr.Textbox(label="Token HF", type="password", visible=False)
|
| 326 |
refine_with_ia_btn = gr.Button("2. 🤖 Aplicar Filtro y Generar Informe IA", variant="primary", interactive=False)
|
|
|
|
| 327 |
with gr.Column(scale=2):
|
| 328 |
gr.Markdown("### 3. Resultados")
|
| 329 |
+
status_output = gr.Textbox(label="📊 Registro de Estado", lines=5, interactive=False)
|
| 330 |
with gr.Tabs():
|
| 331 |
with gr.TabItem("📊 Visualización"): plot_output = gr.Plot()
|
| 332 |
with gr.TabItem("📋 Tabla de Modelado"): table_output = gr.Dataframe()
|
| 333 |
+
with gr.TabItem("📝 Informe IA"): analysis_output = gr.Markdown("El informe aparecerá aquí.")
|
| 334 |
with gr.TabItem("💻 Código"): code_output = gr.Code(language="python")
|
| 335 |
+
with gr.TabItem("🕵️ Registro de Agentes"): agent_log_output = gr.Markdown()
|
| 336 |
+
download_link_markdown = gr.Markdown("*El enlace de descarga aparecerá aquí.*")
|
| 337 |
+
report_output = gr.File(label="📥 Descargar Informe", interactive=False)
|
| 338 |
report_path_state = gr.State(value=None)
|
| 339 |
|
|
|
|
| 340 |
file_input.upload(fn=detect_experiments, inputs=file_input, outputs=exp_names_input)
|
| 341 |
use_personal_key_input.change(lambda x: gr.update(visible=x), inputs=use_personal_key_input, outputs=personal_api_key_input)
|
|
|
|
| 342 |
run_base_analysis_btn.click(
|
| 343 |
fn=run_base_analysis,
|
| 344 |
inputs=[file_input, models_input, exp_names_input, component_input, use_de_input, maxfev_input],
|
| 345 |
outputs=[plot_output, table_output, status_output, refine_with_ia_btn, baseline_results_state, file_path_state, original_params_state, agent_log_output]
|
| 346 |
)
|
|
|
|
| 347 |
refine_with_ia_btn.click(
|
| 348 |
fn=refine_and_generate_report,
|
| 349 |
+
inputs=[baseline_results_state, file_path_state, original_params_state, r2_threshold_slider, rmse_threshold_input, additional_specs_input, ia_model_input, detail_level_input, language_input, max_output_tokens_input, use_personal_key_input, personal_api_key_input],
|
| 350 |
outputs=[plot_output, table_output, analysis_output, code_output, status_output, report_path_state, agent_log_output]
|
| 351 |
)
|
|
|
|
| 352 |
def update_dl_link(path):
|
| 353 |
if path and os.path.exists(path): return f"**¡Informe listo!** 👉 [**Descargar '{os.path.basename(path)}'**](/file={path})"
|
| 354 |
return "*No se generó ningún archivo para descargar.*"
|