81 lines
2.7 KiB
Python
81 lines
2.7 KiB
Python
"""
|
|
===============================================
|
|
Cross-validation on diabetes Dataset Exercise
|
|
===============================================
|
|
|
|
A tutorial exercise which uses cross-validation with linear models.
|
|
|
|
This exercise is used in the :ref:`cv_estimators_tut` part of the
|
|
:ref:`model_selection_tut` section of the :ref:`stat_learn_tut_index`.
|
|
"""
|
|
|
|
from __future__ import print_function
|
|
print(__doc__)
|
|
|
|
import numpy as np
|
|
import matplotlib.pyplot as plt
|
|
|
|
from sklearn import datasets
|
|
from sklearn.linear_model import LassoCV
|
|
from sklearn.linear_model import Lasso
|
|
from sklearn.model_selection import KFold
|
|
from sklearn.model_selection import GridSearchCV
|
|
|
|
diabetes = datasets.load_diabetes()
|
|
X = diabetes.data[:150]
|
|
y = diabetes.target[:150]
|
|
|
|
lasso = Lasso(random_state=0, max_iter=10000)
|
|
alphas = np.logspace(-4, -0.5, 30)
|
|
|
|
tuned_parameters = [{'alpha': alphas}]
|
|
n_folds = 5
|
|
|
|
clf = GridSearchCV(lasso, tuned_parameters, cv=n_folds, refit=False)
|
|
clf.fit(X, y)
|
|
scores = clf.cv_results_['mean_test_score']
|
|
scores_std = clf.cv_results_['std_test_score']
|
|
plt.figure().set_size_inches(8, 6)
|
|
plt.semilogx(alphas, scores)
|
|
|
|
# plot error lines showing +/- std. errors of the scores
|
|
std_error = scores_std / np.sqrt(n_folds)
|
|
|
|
plt.semilogx(alphas, scores + std_error, 'b--')
|
|
plt.semilogx(alphas, scores - std_error, 'b--')
|
|
|
|
# alpha=0.2 controls the translucency of the fill color
|
|
plt.fill_between(alphas, scores + std_error, scores - std_error, alpha=0.2)
|
|
|
|
plt.ylabel('CV score +/- std error')
|
|
plt.xlabel('alpha')
|
|
plt.axhline(np.max(scores), linestyle='--', color='.5')
|
|
plt.xlim([alphas[0], alphas[-1]])
|
|
|
|
# #############################################################################
|
|
# Bonus: how much can you trust the selection of alpha?
|
|
|
|
# To answer this question we use the LassoCV object that sets its alpha
|
|
# parameter automatically from the data by internal cross-validation (i.e. it
|
|
# performs cross-validation on the training data it receives).
|
|
# We use external cross-validation to see how much the automatically obtained
|
|
# alphas differ across different cross-validation folds.
|
|
lasso_cv = LassoCV(alphas=alphas, cv=5, random_state=0, max_iter=10000)
|
|
k_fold = KFold(3)
|
|
|
|
print("Answer to the bonus question:",
|
|
"how much can you trust the selection of alpha?")
|
|
print()
|
|
print("Alpha parameters maximising the generalization score on different")
|
|
print("subsets of the data:")
|
|
for k, (train, test) in enumerate(k_fold.split(X, y)):
|
|
lasso_cv.fit(X[train], y[train])
|
|
print("[fold {0}] alpha: {1:.5f}, score: {2:.5f}".
|
|
format(k, lasso_cv.alpha_, lasso_cv.score(X[test], y[test])))
|
|
print()
|
|
print("Answer: Not very much since we obtained different alphas for different")
|
|
print("subsets of the data and moreover, the scores for these alphas differ")
|
|
print("quite substantially.")
|
|
|
|
plt.show()
|