linear_discriminant_analysis.py 文件源码

def fit(self, X, y):
        # Separate data by class
        X1 = X[y == 0]
        X2 = X[y == 1]

        # Calculate the covariance matrices of the two datasets
        cov1 = calculate_covariance_matrix(X1)
        cov2 = calculate_covariance_matrix(X2)
        cov_tot = cov1 + cov2

        # Calculate the mean of the two datasets
        mean1 = X1.mean(0)
        mean2 = X2.mean(0)
        mean_diff = np.atleast_1d(mean1 - mean2)

        # Determine the vector which when X is projected onto it best separates the
        # data by class. w = (mean1 - mean2) / (cov1 + cov2)
        self.w = np.linalg.pinv(cov_tot).dot(mean_diff)