cluster.py 文件源码

def performance(self, group_labels=None):
        """
        Computes performance metrics for clustering algorithm

        Parameters
        ----------
        group_labels : (optional) ndarray(shape=nsubjects)
            Labels for subject groups
        """
        n_samples = len(self.algorithm.labels_)

        if group_labels is None:
            truelab = np.zeros(n_samples)
            unique_labels = np.unique(group_labels)
            self.clusters["true_int"] = truelab
        else:
            truelab = np.zeros(n_samples)
            unique_labels = np.unique(group_labels)

            for i, label_i in enumerate(unique_labels):
                truelab[group_labels == label_i] = i

            self.clusters["true"] = group_labels
            self.clusters["true_int"] = truelab

        lab = self.algorithm.labels_
        self.results["homogeneity"] = homogeneity_score(truelab, lab)
        self.results["completeness"] = completeness_score(truelab, lab)
        self.results["v_measure"] = v_measure_score(truelab, lab)
        self.results["adj_rand"] = adjusted_rand_score(truelab, lab)
        self.results["adj_MI"] = adjusted_mutual_info_score(truelab, lab)