parallel_old.py 文件源码

def _fit_multiclass(self, X, y, alpha, C, learning_rate,
                        sample_weight, n_iter):
        """Fit a multi-class classifier by combining binary classifiers

        Each binary classifier predicts one class versus all others. This
        strategy is called OVA: One Versus All.
        """
        # Use joblib to fit OvA in parallel.
        result = Parallel(n_jobs=self.n_jobs, backend="threading",
                          verbose=self.verbose)(
                delayed(fit_binary)(self, i, X, y, alpha, C, learning_rate,
                                    n_iter, self._expanded_class_weight[i], 1.,
                                    sample_weight)
                for i in range(len(self.classes_)))

        for i, (_, intercept) in enumerate(result):
            self.intercept_[i] = intercept

        self.t_ += n_iter * X.shape[0]

        if self.average > 0:
            if self.average <= self.t_ - 1.0:
                self.coef_ = self.average_coef_
                self.intercept_ = self.average_intercept_
            else:
                self.coef_ = self.standard_coef_
                self.standard_intercept_ = np.atleast_1d(self.intercept_)
                self.intercept_ = self.standard_intercept_