kmeans.py 文件源码

def step(self):
        """
        Half of the step of k-means
        """
        if self.step_completed:
            d = self.data.X
            points = [d[self.clusters == i] for i in range(len(self.centroids))]
            for i in range(len(self.centroids)):
                c_points = points[i]
                self.centroids[i, :] = (np.average(c_points, axis=0)
                                        if len(c_points) > 0 else np.nan)
            # reinitialize empty centroids

            nan_c = np.isnan(self.centroids).any(axis=1)
            if np.count_nonzero(nan_c) > 0:
                self.centroids[nan_c] = self.random_positioning(
                    np.count_nonzero(nan_c))
            self.centroids_moved = True
        else:
            self.clusters = self.find_clusters(self.centroids)
            self.centroids_moved = False
        self.step_no += 1
        self.centroids_history = self.set_list(
            self.centroids_history, self.step_no, np.copy(self.centroids))