outlier.py 文件源码

def __init__(self, edges, branching_factor=50, threshold=0.1):
        # Make features list.
        features = []
        for i in range(len(edges)):
            edge = edges[i]
            features.append([edge['perimeter'], edge['area'],
                             edge['shape_factor'], edge['radius_deviation']])
        features = np.array(features)

        # Normalize features
        normed_features = features.copy()
        for i in range(features.shape[1]):
            avg = np.median(features[::, i])
            std = np.std(features[::, i])

            normed_features[::, i] -= avg
            normed_features[::, i] /= avg

        self.features = features
        self.normed_features = normed_features
        self.branching_factor = branching_factor
        self.threshold = threshold
        #self.run(Birch, branching_factor=50, threshold=0.1, n_clusters=2)
        self.run(KMeans, n_clusters=2)
        #self.run(AgglomerativeClustering, n_clusters=2)