<p><a href="http://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LassoCV.html" rel="nofollow noreferrer">^{<cd1>}</a>使用R^2作为评分标准。从<a href="http://scikit-learn.org/stable/modules/grid_search.html#specifying-an-objective-metric" rel="nofollow noreferrer">docs</a>:</p>
<blockquote>
<p>By default, parameter search uses the score function of the estimator
to evaluate a parameter setting. These are the
sklearn.metrics.accuracy_score for classification and
<strong>sklearn.metrics.r2_score for regression</strong>.</p>
</blockquote>
<p>要使用另一种评分标准,例如均方误差,您需要使用<a href="http://scikit-learn.org/stable/modules/generated/sklearn.model_selection.GridSearchCV.html" rel="nofollow noreferrer">^{<cd2>}</a>或<a href="http://scikit-learn.org/stable/modules/generated/sklearn.model_selection.RandomizedSearchCV.html" rel="nofollow noreferrer">^{<cd3>}</a>(而不是<a href="http://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LassoCV.html" rel="nofollow noreferrer">^{<cd1>}</a>),并将<code>scoring</code>参数指定为<code>scoring='neg_mean_squared_error'</code>。从<a href="http://scikit-learn.org/stable/modules/grid_search.html#specifying-an-objective-metric" rel="nofollow noreferrer">docs</a>:</p>
<blockquote>
<p>An alternative scoring function can be specified via the scoring
parameter to <strong>GridSearchCV</strong>, <strong>RandomizedSearchCV</strong> and many of the
specialized cross-validation tools described below.</p>
</blockquote>