interface.py

# interface.py

from models import BioprocessModel
import io
from PIL import Image
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from sympy import symbols, sympify, lambdify
import copy
from config import DEVICE, MODEL_PATH, MAX_LENGTH, TEMPERATURE
from decorators import spaces

# Configuración del dispositivo
device = DEVICE

# Cargar el modelo
model_path = MODEL_PATH  # Reemplaza con la ruta real de tu modelo
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path)
# No movemos el modelo al dispositivo aquí

@spaces.GPU(duration=100)
def generate_analysis(prompt, max_length=MAX_LENGTH, device=None):
    try:
        if device is None:
            device = torch.device('cpu')
        if next(model.parameters()).device != device:
            model.to(device)
        input_ids = tokenizer.encode(prompt, return_tensors='pt').to(device)
        max_gen_length = min(max_length + input_ids.size(1), model.config.max_position_embeddings)

        generated_ids = model.generate(
            input_ids=input_ids,
            max_length=max_gen_length,
            temperature=TEMPERATURE,
            num_return_sequences=1,
            no_repeat_ngram_size=2,
            early_stopping=True
        )

        output_text = tokenizer.decode(generated_ids[0], skip_special_tokens=True)
        analysis = output_text[len(prompt):].strip()
        return analysis
    except Exception as e:
        return f"Ocurrió un error durante el análisis: {e}"

@spaces.GPU(duration=100)
def parse_bounds(bounds_str, num_params):
    try:
        bounds = eval(f"[{bounds_str}]")
        if len(bounds) != num_params:
            raise ValueError
        lower_bounds = [b[0] for b in bounds]
        upper_bounds = [b[1] for b in bounds]
        return lower_bounds, upper_bounds
    except:
        lower_bounds = [-np.inf] * num_params
        upper_bounds = [np.inf] * num_params
        return lower_bounds, upper_bounds

@spaces.GPU(duration=100)
def process_and_plot(
    file,
    biomass_eq1, biomass_eq2, biomass_eq3,
    biomass_param1, biomass_param2, biomass_param3,
    biomass_bound1, biomass_bound2, biomass_bound3,
    substrate_eq1, substrate_eq2, substrate_eq3,
    substrate_param1, substrate_param2, substrate_param3,
    substrate_bound1, substrate_bound2, substrate_bound3,
    product_eq1, product_eq2, product_eq3,
    product_param1, product_param2, product_param3,
    product_bound1, product_bound2, product_bound3,
    legend_position,
    show_legend,
    show_params,
    biomass_eq_count,
    substrate_eq_count,
    product_eq_count
):
    # Verificar que las columnas requeridas estén presentes en el archivo Excel
    df = pd.read_excel(file.name)
    expected_columns = ['Tiempo', 'Biomasa', 'Sustrato', 'Producto']  # Nombres en español
    for col in expected_columns:
        if col not in df.columns:
            raise KeyError(f"La columna esperada '{col}' no se encuentra en el archivo Excel.")

    # Asignación de datos desde las columnas en español
    time = df['Tiempo'].values  # Columna de tiempo
    biomass_data = df['Biomasa'].values  # Columna de biomasa
    substrate_data = df['Sustrato'].values  # Columna de sustrato
    product_data = df['Producto'].values  # Columna de producto

    # Convierte los contadores a enteros
    biomass_eq_count = int(biomass_eq_count)
    substrate_eq_count = int(substrate_eq_count)
    product_eq_count = int(product_eq_count)

    # Recolecta las ecuaciones, parámetros y límites según los contadores
    biomass_eqs = [biomass_eq1, biomass_eq2, biomass_eq3][:biomass_eq_count]
    biomass_params = [biomass_param1, biomass_param2, biomass_param3][:biomass_eq_count]
    biomass_bounds = [biomass_bound1, biomass_bound2, biomass_bound3][:biomass_eq_count]

    substrate_eqs = [substrate_eq1, substrate_eq2, substrate_eq3][:substrate_eq_count]
    substrate_params = [substrate_param1, substrate_param2, substrate_param3][:substrate_eq_count]
    substrate_bounds = [substrate_bound1, substrate_bound2, substrate_bound3][:substrate_eq_count]

    product_eqs = [product_eq1, product_eq2, product_eq3][:product_eq_count]
    product_params = [product_param1, product_param2, product_param3][:product_eq_count]
    product_bounds = [product_bound1, product_bound2, product_bound3][:product_eq_count]

    biomass_results = []
    substrate_results = []
    product_results = []

    # Ajusta los modelos de Biomasa
    for i in range(len(biomass_eqs)):
        equation = biomass_eqs[i]
        params_str = biomass_params[i]
        bounds_str = biomass_bounds[i]

        model = BioprocessModel()
        model.set_model('biomass', equation, params_str)

        params = [param.strip() for param in params_str.split(',')]
        lower_bounds, upper_bounds = parse_bounds(bounds_str, len(params))

        y_pred = model.fit_model(
            'biomass', time, biomass_data,
            bounds=(lower_bounds, upper_bounds)
        )
        biomass_results.append({
            'model': copy.deepcopy(model),
            'y_pred': y_pred,
            'equation': equation
        })

    # Usa el primer modelo de biomasa para X(t)
    biomass_model = biomass_results[0]['model']
    X_t_func = biomass_model.models['biomass']['function']
    biomass_params_values = list(biomass_model.params['biomass'].values())

    # Ajusta los modelos de Sustrato
    for i in range(len(substrate_eqs)):
        equation = substrate_eqs[i]
        params_str = substrate_params[i]
        bounds_str = substrate_bounds[i]

        model = BioprocessModel()

        t_symbol = symbols('t')
        expr_substrate = sympify(equation)
        substrate_params_symbols = symbols([param.strip() for param in params_str.split(',')])
        substrate_func_expr = expr_substrate.subs('X(t)', X_t_func(t_symbol, *biomass_params_values))
        substrate_func = lambdify(
            (t_symbol, *substrate_params_symbols),
            substrate_func_expr,
            'numpy'
        )
        model.models['substrate'] = {
            'function': substrate_func,
            'params': [param.strip() for param in params_str.split(',')]
        }

        params = model.models['substrate']['params']
        lower_bounds, upper_bounds = parse_bounds(bounds_str, len(params))

        y_pred = model.fit_model(
            'substrate', time, substrate_data,
            bounds=(lower_bounds, upper_bounds)
        )
        substrate_results.append({
            'model': copy.deepcopy(model),
            'y_pred': y_pred,
            'equation': equation
        })

    # Ajusta los modelos de Producto
    for i in range(len(product_eqs)):
        equation = product_eqs[i]
        params_str = product_params[i]
        bounds_str = product_bounds[i]

        model = BioprocessModel()

        t_symbol = symbols('t')
        expr_product = sympify(equation)
        product_params_symbols = symbols([param.strip() for param in params_str.split(',')])
        product_func_expr = expr_product.subs('X(t)', X_t_func(t_symbol, *biomass_params_values))
        product_func = lambdify(
            (t_symbol, *product_params_symbols),
            product_func_expr,
            'numpy'
        )
        model.models['product'] = {
            'function': product_func,
            'params': [param.strip() for param in params_str.split(',')]
        }

        params = model.models['product']['params']
        lower_bounds, upper_bounds = parse_bounds(bounds_str, len(params))

        y_pred = model.fit_model(
            'product', time, product_data,
            bounds=(lower_bounds, upper_bounds)
        )
        product_results.append({
            'model': copy.deepcopy(model),
            'y_pred': y_pred,
            'equation': equation
        })

    # Genera las gráficas
    fig, axs = plt.subplots(3, 1, figsize=(10, 15))

    # Gráfica de Biomasa
    axs[0].plot(time, biomass_data, 'o', label='Datos de Biomasa')
    for i, result in enumerate(biomass_results):
        axs[0].plot(time, result['y_pred'], '-', label=f'Modelo de Biomasa {i+1}')
    axs[0].set_xlabel('Tiempo')
    axs[0].set_ylabel('Biomasa')
    if show_legend:
        axs[0].legend(loc=legend_position)

    # Gráfica de Sustrato
    axs[1].plot(time, substrate_data, 'o', label='Datos de Sustrato')
    for i, result in enumerate(substrate_results):
        axs[1].plot(time, result['y_pred'], '-', label=f'Modelo de Sustrato {i+1}')
    axs[1].set_xlabel('Tiempo')
    axs[1].set_ylabel('Sustrato')
    if show_legend:
        axs[1].legend(loc=legend_position)

    # Gráfica de Producto
    axs[2].plot(time, product_data, 'o', label='Datos de Producto')
    for i, result in enumerate(product_results):
        axs[2].plot(time, result['y_pred'], '-', label=f'Modelo de Producto {i+1}')
    axs[2].set_xlabel('Tiempo')
    axs[2].set_ylabel('Producto')
    if show_legend:
        axs[2].legend(loc=legend_position)

    plt.tight_layout()
    buf = io.BytesIO()
    plt.savefig(buf, format='png')
    buf.seek(0)
    image = Image.open(buf)

    all_results = {
        'biomass_models': [],
        'substrate_models': [],
        'product_models': []
    }

    for i, result in enumerate(biomass_results):
        model_info = {
            'model_number': i + 1,
            'equation': result['equation'],
            'parameters': result['model'].params['biomass'],
            'R2': result['model'].r2['biomass'],
            'RMSE': result['model'].rmse['biomass']
        }
        all_results['biomass_models'].append(model_info)

    for i, result in enumerate(substrate_results):
        model_info = {
            'model_number': i + 1,
            'equation': result['equation'],
            'parameters': result['model'].params['substrate'],
            'R2': result['model'].r2['substrate'],
            'RMSE': result['model'].rmse['substrate']
        }
        all_results['substrate_models'].append(model_info)

    for i, result in enumerate(product_results):
        model_info = {
            'model_number': i + 1,
            'equation': result['equation'],
            'parameters': result['model'].params['product'],
            'R2': result['model'].r2['product'],
            'RMSE': result['model'].rmse['product']
        }
        all_results['product_models'].append(model_info)

    results_text = "Resultados Experimentales:\n\n"

    results_text += "Modelos de Biomasa:\n"
    for model_info in all_results['biomass_models']:
        results_text += f"""
Modelo {model_info['model_number']}:
Ecuación: {model_info['equation']}
Parámetros: {model_info['parameters']}
R²: {model_info['R2']:.4f}
RMSE: {model_info['RMSE']:.4f}
"""

    results_text += "\nModelos de Sustrato:\n"
    for model_info in all_results['substrate_models']:
        results_text += f"""
Modelo {model_info['model_number']}:
Ecuación: {model_info['equation']}
Parámetros: {model_info['parameters']}
R²: {model_info['R2']:.4f}
RMSE: {model_info['RMSE']:.4f}
"""

    results_text += "\nModelos de Producto:\n"
    for model_info in all_results['product_models']:
        results_text += f"""
Modelo {model_info['model_number']}:
Ecuación: {model_info['equation']}
Parámetros: {model_info['parameters']}
R²: {model_info['R2']:.4f}
RMSE: {model_info['RMSE']:.4f}
"""

    prompt = f"""
Eres un experto en modelado de bioprocesos.

Analiza los siguientes resultados experimentales y proporciona un veredicto sobre la calidad de los modelos, sugiriendo mejoras si es necesario.

{results_text}

Tu análisis debe ser detallado y profesional.
"""
    analysis = generate_analysis(prompt)

    return [image], analysis