34 lines
1.1 KiB
Python
34 lines
1.1 KiB
Python
# entrenar_modelo.py
|
|
"""
|
|
Entrena y evalúa un modelo simple para predecir quinielas (1/X/2).
|
|
"""
|
|
import pandas as pd
|
|
from sklearn.model_selection import train_test_split
|
|
from sklearn.ensemble import RandomForestClassifier
|
|
from sklearn.metrics import classification_report, accuracy_score
|
|
import os
|
|
|
|
# Cargar datos
|
|
DATA_PATH = os.path.join(os.path.dirname(__file__), '../data/espana/partidos_todos.csv')
|
|
df = pd.read_csv(DATA_PATH)
|
|
|
|
# Features simples: diferencia de goles históricos entre local y visitante
|
|
# (Para un modelo más avanzado, se pueden agregar más features)
|
|
df['dif_goles'] = df['goles_local'] - df['goles_visitante']
|
|
|
|
# Features y etiquetas
|
|
X = df[['dif_goles']]
|
|
y = df['resultado']
|
|
|
|
# Separar en train/test
|
|
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
|
|
|
|
# Modelo
|
|
clf = RandomForestClassifier(n_estimators=100, random_state=42)
|
|
clf.fit(X_train, y_train)
|
|
|
|
# Predicción y evaluación
|
|
y_pred = clf.predict(X_test)
|
|
print("Accuracy:", accuracy_score(y_test, y_pred))
|
|
print("\nClassification report:\n", classification_report(y_test, y_pred))
|