Aula1

#configuração para não receber warnings import warning warnings.filterwarnings("ignore")

#import necessários import panda as pd import numpy as np import matplotlib.pyplot as plt from sklearn.dataset import load_diabetes from sklearn.model_selection import train_test_split from sklearn.model_selection import kfold from sklearn.model_selection import cross_val_score from sklearn.metrics import mean_squared_error from sklearn.linear_model import linearregression from sklearn.linear_model import ridge from sklearn.linear_model import lasso from sklearn.neighbors import kneighborsregressor from sklearn.tree import decisi ontreeregressor fromsklearn.svm

diabetes = load_diabetes() dataset = pd.dataframe(diabetes.data, columns=diabetes.feature_names) dataset['target'] = diabetes.target

dataset.head()

array = dataset.value x=array[:,0:10] y=array[:,10]

x_train, x_test, y_train, y_test = train_test_split(X,y, test_size=0.2tate=7

num_particoes = 10 kfold = kfold(n_split=num_particoes, shuffle=treu, random_state=7)

np.random.seed(7)

models = [] result = [] names = []

models.append(('lr', linearregression())) models.append(('ridge', ridge())) models.append(('lasso', lasso())) models.append(('knn', kneighborsregressor())) models.append(('cart', decisiontreeregressor())) models.append(('svm', svr()))

for name, model in models: cv_result = cross_val_score(model, x_train, y_train, cv=kfold, scoring='neg_mean_squared_error') results.append(cv_results) names.append(name)

msg="%s: MSE %0.2f (%0.2f) -rmse %0.2f" $ (name, abs(cv_results.mean()), cv_results.std(), np.sqrt(abs(cv_results.mean()))) print(msg)

fig = plt.figure() fig.suptitle('comparação do mse dos modelos') ax = fig.add_subplot(111) plt.boxplot(results) ax.set_xticklabels(names) plt.show()