from sklearn.datasets import fetch_california_housing
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeRegressor
from sklearn.model_selection import GridSearchCV
california = fetch_california_housing()
X = california.data
y = california.target
# Dividiendo los datos entre entrenamiento y prueba
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.25, random_state=42)
# Definición de los hiperparámetros a ser probados
param_grid = {
'max_depth': [5, 10, 15, 20],
'min_samples_split': [3, 6, 11],
'min_samples_leaf': [2, 4, 6]
}
# Creando el modelo
model = DecisionTreeRegressor()
# Aplicando Grid Search
grid_search = GridSearchCV(model, param_grid, cv=5, scoring='neg_mean_squared_error')
grid_search.fit(X_train, y_train)
# Mostrando los mejores parámetros encontrados
print(f"Mejores parámetros: {grid_search.best_params_}")
import pandas as pd
from sklearn.datasets import load_diabetes
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestRegressor
import matplotlib.pyplot as plt
# Cargar los datos
diabetes = load_diabetes()
X = diabetes.data
y = diabetes.target
# Dividir los datos entre entrenamiento y prueba
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.25, random_state=42)
# Entrenar el modelo
model = RandomForestRegressor()
model.fit(X_train, y_train)
df_importancia = pd.DataFrame({'Feature': feature_names, 'Importance': importances})
df_importancia = df_importancia.sort_values(by='Importance', ascending=True)
plt.figure(figsize=(10, 6))
plt.barh(df_importancia['Feature'], df_importancia['Importance'], color='skyblue')
plt.title("Importancia de las Características - Dataset Diabetes")
plt.xlabel("Nivel de Importancia")
plt.ylabel("Características Predictoras")
plt.show()
