custom_logistic.py 文件源码

def fit(self, X, y):
        """
        Train the Logistic model, X and y are numpy arrays.
        """
        X, y = check_X_y(X, y) 
        #, accept_sparse=['csr', 'csc']) # not sure how to handle sparse
        self.classes_, y = np.unique(y, return_inverse=True)

        if self.fit_intercept:
            X = np.insert(X, 0, 1, axis=1)

        w0 = np.zeros(X.shape[1])

        if self.bounds is None:
            self.bounds_ = [(None, None) for v in w0]
        elif isinstance(self.bounds, tuple) and len(self.bounds) == 2:
            self.bounds_ = [self.bounds for v in w0]
        elif self.fit_intercept and len(self.bounds) == len(w0) - 1:
            self.bounds_ = np.concatenate(([(None, None)], self.bounds))
        else:
            self.bounds_ = self.bounds
        if len(self.bounds_) != len(w0):
            raise ValueError("Bounds must be the same length as the coef")

        if isinstance(self.l2, Number):
            self.l2_ = [self.l2 for v in w0]
        elif self.fit_intercept and len(self.l2) == len(w0) - 1:
            self.l2_ = np.insert(self.l2, 0, 0)
        else:
            self.l2_ = self.l2
        if len(self.l2_) != len(w0):
            raise ValueError("L2 penalty must be the same length as the coef, be sure the intercept is accounted for.")

        # the intercept should never be regularized.
        if self.fit_intercept:
            self.l2_[0] = 0.0

        w = minimize(_ll, w0, args=(X, y, self.l2_),
                               jac=_ll_grad, 
                               method=self.method, bounds=self.bounds_,
                               options={'maxiter': self.max_iter, 
                                        #'disp': True
                               })['x']

        if self.fit_intercept:
            self.intercept_ = w[0:1]
            self.coef_ = w[1:]
        else:
            self.intercept_ = np.array([])
            self.coef_ = w
        return self