# app.py
import gradio as gr
import joblib
import pandas as pd
import numpy as np
import os
from sklearn.preprocessing import StandardScaler, OneHotEncoder 
from sklearn.impute import SimpleImputer
from sklearn.compose import ColumnTransformer
from sklearn.pipeline import Pipeline
from sklearn.ensemble import RandomForestClassifier

# --- CORRECCIÓN: Listas hardcodeadas para la interfaz ---
UFC_LOCATIONS = [
    'Las Vegas, NV', 'Rio de Janeiro, Brazil', 'Abu Dhabi, UAE',
    'London, England', 'New York, NY', 'Otros'
]

# --- 1. Cargar objetos serializados ---
model = None
preprocessor = None
model_columns = []
try:
    model = joblib.load(os.path.join(os.path.dirname(__file__), 'model.pkl'))
    preprocessor = joblib.load(os.path.join(os.path.dirname(__file__), 'preprocessor.pkl'))
    model_columns = joblib.load(os.path.join(os.path.dirname(__file__), 'model_columns.pkl'))
except Exception as e:
    print(f"Error al cargar artefactos: {e}")

# --- 2. Función de Predicción (Ganador) ---
# Los argumentos de entrada son las estadísticas brutas.
def predict_winner(F1_KD, F2_KD, F1_STR, F2_STR, F1_TD, F2_TD, F1_SUB, F2_SUB, Round, 
                   F1_acc, F2_acc, KD_diff, STR_diff, TD_diff, SUB_diff, Location, 
                   wc_B, wc_C, wc_F, wc_Fl, wc_H, wc_LH, wc_L, wc_M, wc_O, wc_SH, wc_W, 
                   wc_WB, wc_WF, wc_WFl, wc_WS):

    if model is None or preprocessor is None:
        return "ERROR", "Fallo al cargar modelo. Revisa el log de versiones de Scikit-learn."

    # 1. Crear el DataFrame de entrada
    input_data = pd.DataFrame({
        'Fighter_1_KD': [F1_KD], 'Fighter_2_KD': [F2_KD], 'Fighter_1_STR': [F1_STR], 'Fighter_2_STR': [F2_STR],
        'Fighter_1_TD': [F1_TD], 'Fighter_2_TD': [F2_TD], 'Fighter_1_SUB': [F1_SUB], 'Fighter_2_SUB': [F2_SUB],
        'Round': [Round], 'Fighter_1_accuracy': [F1_acc], 'Fighter_2_accuracy': [F2_acc],
        'KD_diff': [KD_diff], 'STR_diff': [STR_diff], 'TD_diff': [TD_diff], 'SUB_diff': [SUB_diff],
        'Location': [Location],
        'weight_class_Bantamweight': [wc_B], 'weight_class_Catch Weight': [wc_C], 'weight_class_Featherweight': [wc_F],
        'weight_class_Flyweight': [wc_Fl], 'weight_class_Heavyweight': [wc_H], 'weight_class_Light Heavyweight': [wc_LH],
        'weight_class_Lightweight': [wc_L], 'weight_class_Middleweight': [wc_M], 'weight_class_Open Weight': [wc_O],
        'weight_class_Super Heavyweight': [wc_SH], 'weight_class_Welterweight': [wc_W], 
        "weight_class_Women's Bantamweight": [wc_WB], "weight_class_Women's Featherweight": [wc_WF], 
        "weight_class_Women's Flyweight": [wc_WFl], "weight_class_Women's Strawweight": [wc_WS]
    })
    
    # 2. Preprocesamiento: Utilizar el ColumnTransformer ajustado.
    X_processed = preprocessor.transform(input_data)
    X_final = pd.DataFrame(X_processed, columns=model_columns)
    
    # 3. Predicción
    # P(F1 Gana) = P(Clase 1)
    proba_f1_wins = model.predict_proba(X_final)[0][1] 
    
    # 4. Formato de Salida
    if proba_f1_wins >= 0.50:
        winner = "PELEADOR 1 (Predicción)"
        confidence_percent = f"{proba_f1_wins*100:.2f}%"
    else:
        winner = "PELEADOR 2 (Predicción)"
        # La confianza es 1 - P(F1 Gana)
        confidence_percent = f"{(1 - proba_f1_wins)*100:.2f}%"
        
    return winner, confidence_percent

# --- 3. Creación de la Interfaz Gradio ---
inputs = [
    gr.Slider(0, 5, value=1, step=1, label="KD P1"), gr.Slider(0, 5, value=0, step=1, label="KD P2"),
    gr.Slider(0, 300, value=70, label="STR P1"), gr.Slider(0, 300, value=50, label="STR P2"),
    gr.Slider(0, 20, value=5, label="TD P1"), gr.Slider(0, 20, value=2, label="TD P2"),
    gr.Slider(0, 5, value=0, step=1, label="SUB P1"), gr.Slider(0, 5, value=0, step=1, label="SUB P2"),
    gr.Slider(1, 5, value=3, step=1, label="Ronda actual (Round)"),
    gr.Slider(0, 1, value=0.4, label="Precisión STR P1 (F1_acc)"), gr.Slider(0, 1, value=0.3, label="Precisión STR P2 (F2_acc)"),
    gr.Slider(-5, 5, value=1, label="Diferencia de KD"), gr.Slider(-300, 300, value=20, label="Diferencia de STR"),
    gr.Slider(-20, 20, value=3, label="Diferencia de TD"), gr.Slider(-5, 5, value=0, label="Diferencia de SUB"),
    gr.Dropdown(UFC_LOCATIONS, value='Las Vegas, NV', label="Ubicación"),
    gr.Checkbox(value=True, label="weight_class_Lightweight (wc_L)"), gr.Checkbox(value=False, label="weight_class_Bantamweight (wc_B)"), 
    gr.Checkbox(value=False, label="weight_class_Catch Weight (wc_C)"), gr.Checkbox(value=False, label="weight_class_Featherweight (wc_F)"),
    gr.Checkbox(value=False, label="weight_class_Flyweight (wc_Fl)"), gr.Checkbox(value=False, label="weight_class_Heavyweight (wc_H)"),
    gr.Checkbox(value=False, label="weight_class_Light Heavyweight (wc_LH)"), gr.Checkbox(value=False, label="weight_class_Middleweight (wc_M)"),
    gr.Checkbox(value=False, label="weight_class_Open Weight (wc_O)"), gr.Checkbox(value=False, label="weight_class_Super Heavyweight (wc_SH)"),
    gr.Checkbox(value=False, label="weight_class_Welterweight (wc_W)"), gr.Checkbox(value=False, label="weight_class_Women's Bantamweight (wc_WB)"),
    gr.Checkbox(value=False, label="weight_class_Women's Featherweight (wc_WF)"), gr.Checkbox(value=False, label="weight_class_Women's Flyweight (wc_WFl)"),
    gr.Checkbox(value=False, label="weight_class_Women's Strawweight (wc_WS)")
]

outputs = [gr.Textbox(label="Ganador Predicho"), gr.Textbox(label="Confianza (%)")]

gr.Interface(
    fn=predict_winner,
    inputs=inputs,
    outputs=outputs,
    title="🥊 Predictor del Ganador de Combates UFC",
    description="Modelo Random Forest para predecir si el Peleador 1 o el Peleador 2 ganará."
).launch(server_name="0.0.0.0", server_port=7860)